NAMIC Wiki - User contributions [en]

Projects:RegistrationTBI

2012-11-16T19:36:56Z

Yflou: /* References */

Back to [[Algorithm:BU|Boston University Algorithms]]
__NOTOC__
= Multimodal Deformable Registration of Traumatic Brain Injury MR Volumes using Graphics Processing Units =

= Description =
An estimated 1.7 million Americans sustain traumatic brain injuries (TBI's) every year. The large number of recent TBI cases in soldiers returning from military conflicts has highlighted the critical need for improvement of TBI care and treatment, and has drawn sustained attention to the need for improved methodologies of TBI neuroimaging data analysis. Neuroimaging of TBI is vital for surgical planning by providing important information for anatomic localization and surgical navigation, as well as for monitoring patient case evolution over time. Approximately 2 days after the acute injury, magnetic resonance imaging (MRI) becomes preferable to computed tomography (CT) for the purpose of lesion characterization, and the use of various MR sequences tailored to capture distinct aspects of TBI pathology provides clinicians with essential complementary information for the assessment of TBI-related anatomical insults and pathophysiology.

Image registration plays an essential role in a wide variety of TBI data analysis workflows. It aims to find a transformation between two image sets such that the transformed image becomes similar to the target image according to some chosen metric or criterion. Typically, a similarity measure is first established to quantify how `close` two image volumes are to each other. Next, the transformation that maximizes this similarity is typically computed through an optimization process which constrains the transformation to a predetermined class, such as rigid, affine or deformable. Numerous challenges associated with the task of TBI volume co-registration can exist if data acquisition is performed multimodally, and additional complexities can also arise due to the large degree of algorithmic robustness that may be required in order to properly address pathology-related deformations. Many conventional methods use the sum of squared differences of intensity values between two image sets as a similarity measure, which can perform poorly or even fail for TBI volume registration. Consequently, because the deformation of patient anatomy and soft tissues cannot typically be represented by rigid transforms, image registration often requires deformable image registration (DIR), i.e., the necessity of applying nonparametric infinite-dimensional transformations.

This paper proposes to replace the Mutual Information (MI) criterion for registration with the Bhattachayya distance [1] within a multimodal DIR framework [3]. The advantage of BD over MI is the superior behavior of the square root function compared to that of the logarithm at zero, which yields a more stable algorithm.
This framework we describe takes into account the physical models of tissue motion to regularize the deformation fields and also involves free-form deformation. On the other hand, the DIR algorithm is computationally expensive when implemented on conventional central processing units, which can be detrimental particularly when three-dimensional (3D) volumes-rather than 2D images-need to be co-registered. In clinical settings that involve acute TBI care, the amount of time required by the processing of neuroimaging data sets from patients in critical condition should be minimized. To meet this clinical requirement, we have implemented our algorithm on a graphics processing unit (GPU) platform [2].

== Result ==

MR volumes were acquired at 3 T using a Siemens Trio TIM scanner (Siemens AG, Erlangen, Germany). Because assessing the time evolution of TBI between the acute to the chronic stage is of great interest in the clinical field in order to evaluate case evolution, scanning sessions were held both several days (acute baseline) as well as 6 months (chronic follow-up) after the traumatic injury event. To eliminate the effect of different scanner parameters during each scanning session, every subject was scanned using the same scanner for both acute and chronic time points. The MP-RAGE sequence (Mugler and Brookeman, 1990) was used to acquire T1-weighted images. In addition, MR data were also acquired using fluid-attenuated inversion recovery (FLAIR, (De Coene et al., 1992)), gradient-recalled echo (GRE) T2-weighted images as well as diffusion weighted imaging (DWI), and perfusion imaging.

Before applying our deformable registration algorithm, all image volumes were co-registered by rigid-body transformation to the pre-contrast T1-weighted volume acquired during the acute baseline scanning session. This helps to correct for head tilt and reduce error in computing the local deformation fields. Another technique that was employed before performing the registration is skull stripping, which was useful in our case because images acquired at the acute stage exhibit appreciably more extracranial swelling compared to images acquired chronically. Since all modalities are co-registered to T1, we only need to perform the skull stripping once, i.e. on the T1 volume. Skull stripping is necessary because, without it, the DIR algorithm would deform the interior of the brain to match the outside boundary. This type of deformation is mathematically valid, but does not yield anatomically plausible results. Two possible solutions to this problem are either adding prior knowledge on the boundary or applying skull stripping, of which we opt for the latter due to its common usage in image processing. We use the BrainSuit software [http://users.loni.ucla.edu/~shattuck/brainsuite/corticalsurface/bse/] for the skull stripping.

[[Image:ToT1e1.png|800px]]

Excluding preprocessing steps, the registration of two volumes of sizes 256x256x60 is found to require 6 seconds on the GPU. Registration results are illustrated for a 2D slice in the above figure for acute stage. The norm of the deformation fields and its 2D motion grid are also included. For T2, FLAIR and GRE volumes, the largest amount of deformation is observed bilaterally in the deep periventricular white matter, possibly as a consequence of hemorrhage and/or CSF infiltration into edemic regions, which can alter voxel intensities in GRE and FLAIR imaging, respectively. In the case of DWI, notable deformation is observed frontally and frontolaterally; in the former case, this may be the result of warping artifacts due to the large drop in the physical properties of tissues at the interfaces between brain, bone and air. In the latter case, the deformation is possibly due to the presence of TBI-related edema, which can substantially alter local diffusivity values. Similar effects due to these causes are observed with DWI and with perfusion imaging in both acute and chronic scans.

== Future Work ==

Future work will focus on registration of TBI volumes across time in terms of registering acute to chronic or vice versa. There are a large number of registration algorithms that assume the
smoothness of the vector flow, i.e., the deformation is
diffeomorphic. However, when registering TBI across time, the deformation is not well-defined, let along
to be diffeomorphic, at some regions where bleeding or lesion
occurs. It is challenging and important to design a registration
algorithm that can deal with topological changes for TBI patients.

= Key Investigators =

Georgia Tech: Yifei Lou and Patricio Vela

Boston University: Allen Tannenbaum

UCLA: Andrei Irimia, Micah C. Chambers, Jack Van Horn and Paul M. Vespa

= References =
1.Yifei Lou, Andrei Irimia, Patricio Vela, Micah C. Chambers, Jack Van Horn, Paul M. Vespa and Allen Tannenbaum. Multimodal Deformable Registration of Traumatic Brain Injury MR Volumes via the Bhattacharyya Distance. Submitted to IEEE Transactions on Bioengineering, 2012

2. Yifei Lou, Xun Jia, Xuejun Gu and Allen Tannenbaum. A GPU-based Implementation of Multimodal Deformable Image Registration Based on Mutual Information or Bhattacharyya Distance. Insight Journal, 2011. [http://www.midasjournal.org/browse/publication/803]

3. E. D’Agostino, F. Maes, D. Vandermeulen, and P. Suetens. A viscous fluid model for multimodal non-rigid image registration using mutual information,” MICCAI, 2002, pp. 541–548

Projects:RegistrationTBI

2012-11-16T19:31:36Z

Yflou: /* References */

Back to [[Algorithm:BU|Boston University Algorithms]]
__NOTOC__
= Multimodal Deformable Registration of Traumatic Brain Injury MR Volumes using Graphics Processing Units =

= Description =
An estimated 1.7 million Americans sustain traumatic brain injuries (TBI's) every year. The large number of recent TBI cases in soldiers returning from military conflicts has highlighted the critical need for improvement of TBI care and treatment, and has drawn sustained attention to the need for improved methodologies of TBI neuroimaging data analysis. Neuroimaging of TBI is vital for surgical planning by providing important information for anatomic localization and surgical navigation, as well as for monitoring patient case evolution over time. Approximately 2 days after the acute injury, magnetic resonance imaging (MRI) becomes preferable to computed tomography (CT) for the purpose of lesion characterization, and the use of various MR sequences tailored to capture distinct aspects of TBI pathology provides clinicians with essential complementary information for the assessment of TBI-related anatomical insults and pathophysiology.

Image registration plays an essential role in a wide variety of TBI data analysis workflows. It aims to find a transformation between two image sets such that the transformed image becomes similar to the target image according to some chosen metric or criterion. Typically, a similarity measure is first established to quantify how `close` two image volumes are to each other. Next, the transformation that maximizes this similarity is typically computed through an optimization process which constrains the transformation to a predetermined class, such as rigid, affine or deformable. Numerous challenges associated with the task of TBI volume co-registration can exist if data acquisition is performed multimodally, and additional complexities can also arise due to the large degree of algorithmic robustness that may be required in order to properly address pathology-related deformations. Many conventional methods use the sum of squared differences of intensity values between two image sets as a similarity measure, which can perform poorly or even fail for TBI volume registration. Consequently, because the deformation of patient anatomy and soft tissues cannot typically be represented by rigid transforms, image registration often requires deformable image registration (DIR), i.e., the necessity of applying nonparametric infinite-dimensional transformations.

This paper proposes to replace the Mutual Information (MI) criterion for registration with the Bhattachayya distance [1] within a multimodal DIR framework [3]. The advantage of BD over MI is the superior behavior of the square root function compared to that of the logarithm at zero, which yields a more stable algorithm.
This framework we describe takes into account the physical models of tissue motion to regularize the deformation fields and also involves free-form deformation. On the other hand, the DIR algorithm is computationally expensive when implemented on conventional central processing units, which can be detrimental particularly when three-dimensional (3D) volumes-rather than 2D images-need to be co-registered. In clinical settings that involve acute TBI care, the amount of time required by the processing of neuroimaging data sets from patients in critical condition should be minimized. To meet this clinical requirement, we have implemented our algorithm on a graphics processing unit (GPU) platform [2].

== Result ==

MR volumes were acquired at 3 T using a Siemens Trio TIM scanner (Siemens AG, Erlangen, Germany). Because assessing the time evolution of TBI between the acute to the chronic stage is of great interest in the clinical field in order to evaluate case evolution, scanning sessions were held both several days (acute baseline) as well as 6 months (chronic follow-up) after the traumatic injury event. To eliminate the effect of different scanner parameters during each scanning session, every subject was scanned using the same scanner for both acute and chronic time points. The MP-RAGE sequence (Mugler and Brookeman, 1990) was used to acquire T1-weighted images. In addition, MR data were also acquired using fluid-attenuated inversion recovery (FLAIR, (De Coene et al., 1992)), gradient-recalled echo (GRE) T2-weighted images as well as diffusion weighted imaging (DWI), and perfusion imaging.

Before applying our deformable registration algorithm, all image volumes were co-registered by rigid-body transformation to the pre-contrast T1-weighted volume acquired during the acute baseline scanning session. This helps to correct for head tilt and reduce error in computing the local deformation fields. Another technique that was employed before performing the registration is skull stripping, which was useful in our case because images acquired at the acute stage exhibit appreciably more extracranial swelling compared to images acquired chronically. Since all modalities are co-registered to T1, we only need to perform the skull stripping once, i.e. on the T1 volume. Skull stripping is necessary because, without it, the DIR algorithm would deform the interior of the brain to match the outside boundary. This type of deformation is mathematically valid, but does not yield anatomically plausible results. Two possible solutions to this problem are either adding prior knowledge on the boundary or applying skull stripping, of which we opt for the latter due to its common usage in image processing. We use the BrainSuit software [http://users.loni.ucla.edu/~shattuck/brainsuite/corticalsurface/bse/] for the skull stripping.

[[Image:ToT1e1.png|800px]]

Excluding preprocessing steps, the registration of two volumes of sizes 256x256x60 is found to require 6 seconds on the GPU. Registration results are illustrated for a 2D slice in the above figure for acute stage. The norm of the deformation fields and its 2D motion grid are also included. For T2, FLAIR and GRE volumes, the largest amount of deformation is observed bilaterally in the deep periventricular white matter, possibly as a consequence of hemorrhage and/or CSF infiltration into edemic regions, which can alter voxel intensities in GRE and FLAIR imaging, respectively. In the case of DWI, notable deformation is observed frontally and frontolaterally; in the former case, this may be the result of warping artifacts due to the large drop in the physical properties of tissues at the interfaces between brain, bone and air. In the latter case, the deformation is possibly due to the presence of TBI-related edema, which can substantially alter local diffusivity values. Similar effects due to these causes are observed with DWI and with perfusion imaging in both acute and chronic scans.

== Future Work ==

Future work will focus on registration of TBI volumes across time in terms of registering acute to chronic or vice versa. There are a large number of registration algorithms that assume the
smoothness of the vector flow, i.e., the deformation is
diffeomorphic. However, when registering TBI across time, the deformation is not well-defined, let along
to be diffeomorphic, at some regions where bleeding or lesion
occurs. It is challenging and important to design a registration
algorithm that can deal with topological changes for TBI patients.

= Key Investigators =

Georgia Tech: Yifei Lou and Patricio Vela

Boston University: Allen Tannenbaum

UCLA: Andrei Irimia, Micah C. Chambers, Jack Van Horn and Paul M. Vespa

= References =
1.Yifei Lou, Andrei Irimia, Patricio Vela, Micah C. Chambers, Jack Van Horn, Paul M. Vespa and Allen Tannenbaum. Multimodal Deformable Registration of Traumatic Brain Injury MR Volumes via the Bhattacharyya Distanc. Submitted to IEEE Transactions on Bioengineering, 2012

2. Yifei Lou, Xun Jia, Xuejun Gu and Allen Tannenbaum. A GPU-based Implementation of Multimodal Deformable Image Registration Based on Mutual Information or Bhattacharyya Distance. Insight Journal, 2011. [http://www.midasjournal.org/browse/publication/803]

3. E. D’Agostino, F. Maes, D. Vandermeulen, and P. Suetens. A viscous fluid model for multimodal non-rigid image registration using mutual information,” MICCAI, 2002, pp. 541–548

Projects:RegistrationTBI

2012-11-16T19:31:11Z

Yflou: /* Description */

Back to [[Algorithm:BU|Boston University Algorithms]]
__NOTOC__
= Multimodal Deformable Registration of Traumatic Brain Injury MR Volumes using Graphics Processing Units =

= Description =
An estimated 1.7 million Americans sustain traumatic brain injuries (TBI's) every year. The large number of recent TBI cases in soldiers returning from military conflicts has highlighted the critical need for improvement of TBI care and treatment, and has drawn sustained attention to the need for improved methodologies of TBI neuroimaging data analysis. Neuroimaging of TBI is vital for surgical planning by providing important information for anatomic localization and surgical navigation, as well as for monitoring patient case evolution over time. Approximately 2 days after the acute injury, magnetic resonance imaging (MRI) becomes preferable to computed tomography (CT) for the purpose of lesion characterization, and the use of various MR sequences tailored to capture distinct aspects of TBI pathology provides clinicians with essential complementary information for the assessment of TBI-related anatomical insults and pathophysiology.

Image registration plays an essential role in a wide variety of TBI data analysis workflows. It aims to find a transformation between two image sets such that the transformed image becomes similar to the target image according to some chosen metric or criterion. Typically, a similarity measure is first established to quantify how `close` two image volumes are to each other. Next, the transformation that maximizes this similarity is typically computed through an optimization process which constrains the transformation to a predetermined class, such as rigid, affine or deformable. Numerous challenges associated with the task of TBI volume co-registration can exist if data acquisition is performed multimodally, and additional complexities can also arise due to the large degree of algorithmic robustness that may be required in order to properly address pathology-related deformations. Many conventional methods use the sum of squared differences of intensity values between two image sets as a similarity measure, which can perform poorly or even fail for TBI volume registration. Consequently, because the deformation of patient anatomy and soft tissues cannot typically be represented by rigid transforms, image registration often requires deformable image registration (DIR), i.e., the necessity of applying nonparametric infinite-dimensional transformations.

This paper proposes to replace the Mutual Information (MI) criterion for registration with the Bhattachayya distance [1] within a multimodal DIR framework [3]. The advantage of BD over MI is the superior behavior of the square root function compared to that of the logarithm at zero, which yields a more stable algorithm.
This framework we describe takes into account the physical models of tissue motion to regularize the deformation fields and also involves free-form deformation. On the other hand, the DIR algorithm is computationally expensive when implemented on conventional central processing units, which can be detrimental particularly when three-dimensional (3D) volumes-rather than 2D images-need to be co-registered. In clinical settings that involve acute TBI care, the amount of time required by the processing of neuroimaging data sets from patients in critical condition should be minimized. To meet this clinical requirement, we have implemented our algorithm on a graphics processing unit (GPU) platform [2].

== Result ==

MR volumes were acquired at 3 T using a Siemens Trio TIM scanner (Siemens AG, Erlangen, Germany). Because assessing the time evolution of TBI between the acute to the chronic stage is of great interest in the clinical field in order to evaluate case evolution, scanning sessions were held both several days (acute baseline) as well as 6 months (chronic follow-up) after the traumatic injury event. To eliminate the effect of different scanner parameters during each scanning session, every subject was scanned using the same scanner for both acute and chronic time points. The MP-RAGE sequence (Mugler and Brookeman, 1990) was used to acquire T1-weighted images. In addition, MR data were also acquired using fluid-attenuated inversion recovery (FLAIR, (De Coene et al., 1992)), gradient-recalled echo (GRE) T2-weighted images as well as diffusion weighted imaging (DWI), and perfusion imaging.

Before applying our deformable registration algorithm, all image volumes were co-registered by rigid-body transformation to the pre-contrast T1-weighted volume acquired during the acute baseline scanning session. This helps to correct for head tilt and reduce error in computing the local deformation fields. Another technique that was employed before performing the registration is skull stripping, which was useful in our case because images acquired at the acute stage exhibit appreciably more extracranial swelling compared to images acquired chronically. Since all modalities are co-registered to T1, we only need to perform the skull stripping once, i.e. on the T1 volume. Skull stripping is necessary because, without it, the DIR algorithm would deform the interior of the brain to match the outside boundary. This type of deformation is mathematically valid, but does not yield anatomically plausible results. Two possible solutions to this problem are either adding prior knowledge on the boundary or applying skull stripping, of which we opt for the latter due to its common usage in image processing. We use the BrainSuit software [http://users.loni.ucla.edu/~shattuck/brainsuite/corticalsurface/bse/] for the skull stripping.

[[Image:ToT1e1.png|800px]]

Excluding preprocessing steps, the registration of two volumes of sizes 256x256x60 is found to require 6 seconds on the GPU. Registration results are illustrated for a 2D slice in the above figure for acute stage. The norm of the deformation fields and its 2D motion grid are also included. For T2, FLAIR and GRE volumes, the largest amount of deformation is observed bilaterally in the deep periventricular white matter, possibly as a consequence of hemorrhage and/or CSF infiltration into edemic regions, which can alter voxel intensities in GRE and FLAIR imaging, respectively. In the case of DWI, notable deformation is observed frontally and frontolaterally; in the former case, this may be the result of warping artifacts due to the large drop in the physical properties of tissues at the interfaces between brain, bone and air. In the latter case, the deformation is possibly due to the presence of TBI-related edema, which can substantially alter local diffusivity values. Similar effects due to these causes are observed with DWI and with perfusion imaging in both acute and chronic scans.

== Future Work ==

Future work will focus on registration of TBI volumes across time in terms of registering acute to chronic or vice versa. There are a large number of registration algorithms that assume the
smoothness of the vector flow, i.e., the deformation is
diffeomorphic. However, when registering TBI across time, the deformation is not well-defined, let along
to be diffeomorphic, at some regions where bleeding or lesion
occurs. It is challenging and important to design a registration
algorithm that can deal with topological changes for TBI patients.

= Key Investigators =

Georgia Tech: Yifei Lou and Patricio Vela

Boston University: Allen Tannenbaum

UCLA: Andrei Irimia, Micah C. Chambers, Jack Van Horn and Paul M. Vespa

= References =
1. Yifei Lou, Andrei Irimia, Patricio Vela, Allen Tannenbaum, Micah C. Chambers, Jack Van Horn and Paul M. Vespa. Multimodal Deformable Registration of Traumatic Brain Injury MR Volumes using Graphics Processing Units. Submitted to IEEE Trans. on Medical Imaging. 2011

2. Yifei Lou and Allen Tannenbaum. Multimodal Deformable Image Registration via the Bhattacharyya Distance. Submitted to IEEE Trans. Image Process. 2011

3. Yifei Lou, Xun Jia, Xuejun Gu and Allen Tannenbaum. A GPU-based Implementation of Multimodal Deformable Image Registration Based on Mutual Information or Bhattacharyya Distance. Insight Journal, 2011. [http://www.midasjournal.org/browse/publication/803]

4. E. D’Agostino, F. Maes, D. Vandermeulen, and P. Suetens. A viscous fluid model for multimodal non-rigid image registration using mutual information,” MICCAI, 2002, pp. 541–548

Projects:RegistrationTBI

2012-11-16T19:30:41Z

Yflou: /* Description */

Back to [[Algorithm:BU|Boston University Algorithms]]
__NOTOC__
= Multimodal Deformable Registration of Traumatic Brain Injury MR Volumes using Graphics Processing Units =

= Description =
An estimated 1.7 million Americans sustain traumatic brain injuries (TBI's) every year. The large number of recent TBI cases in soldiers returning from military conflicts has highlighted the critical need for improvement of TBI care and treatment, and has drawn sustained attention to the need for improved methodologies of TBI neuroimaging data analysis. Neuroimaging of TBI is vital for surgical planning by providing important information for anatomic localization and surgical navigation, as well as for monitoring patient case evolution over time. Approximately 2 days after the acute injury, magnetic resonance imaging (MRI) becomes preferable to computed tomography (CT) for the purpose of lesion characterization, and the use of various MR sequences tailored to capture distinct aspects of TBI pathology provides clinicians with essential complementary information for the assessment of TBI-related anatomical insults and pathophysiology.

Image registration plays an essential role in a wide variety of TBI data analysis workflows. It aims to find a transformation between two image sets such that the transformed image becomes similar to the target image according to some chosen metric or criterion. Typically, a similarity measure is first established to quantify how `close` two image volumes are to each other. Next, the transformation that maximizes this similarity is typically computed through an optimization process which constrains the transformation to a predetermined class, such as rigid, affine or deformable. Numerous challenges associated with the task of TBI volume co-registration can exist if data acquisition is performed multimodally, and additional complexities can also arise due to the large degree of algorithmic robustness that may be required in order to properly address pathology-related deformations. Many conventional methods use the sum of squared differences of intensity values between two image sets as a similarity measure, which can perform poorly or even fail for TBI volume registration. Consequently, because the deformation of patient anatomy and soft tissues cannot typically be represented by rigid transforms, image registration often requires deformable image registration (DIR), i.e., the necessity of applying nonparametric infinite-dimensional transformations.

This paper proposes to replace the Mutual Information (MI) criterion for registration with the Bhattachayya distance [1] within a multimodal DIR framework [4]. The advantage of BD over MI is the superior behavior of the square root function compared to that of the logarithm at zero, which yields a more stable algorithm.
This framework we describe takes into account the physical models of tissue motion to regularize the deformation fields and also involves free-form deformation. On the other hand, the DIR algorithm is computationally expensive when implemented on conventional central processing units, which can be detrimental particularly when three-dimensional (3D) volumes-rather than 2D images-need to be co-registered. In clinical settings that involve acute TBI care, the amount of time required by the processing of neuroimaging data sets from patients in critical condition should be minimized. To meet this clinical requirement, we have implemented our algorithm on a graphics processing unit (GPU) platform [3].

== Result ==

MR volumes were acquired at 3 T using a Siemens Trio TIM scanner (Siemens AG, Erlangen, Germany). Because assessing the time evolution of TBI between the acute to the chronic stage is of great interest in the clinical field in order to evaluate case evolution, scanning sessions were held both several days (acute baseline) as well as 6 months (chronic follow-up) after the traumatic injury event. To eliminate the effect of different scanner parameters during each scanning session, every subject was scanned using the same scanner for both acute and chronic time points. The MP-RAGE sequence (Mugler and Brookeman, 1990) was used to acquire T1-weighted images. In addition, MR data were also acquired using fluid-attenuated inversion recovery (FLAIR, (De Coene et al., 1992)), gradient-recalled echo (GRE) T2-weighted images as well as diffusion weighted imaging (DWI), and perfusion imaging.

Before applying our deformable registration algorithm, all image volumes were co-registered by rigid-body transformation to the pre-contrast T1-weighted volume acquired during the acute baseline scanning session. This helps to correct for head tilt and reduce error in computing the local deformation fields. Another technique that was employed before performing the registration is skull stripping, which was useful in our case because images acquired at the acute stage exhibit appreciably more extracranial swelling compared to images acquired chronically. Since all modalities are co-registered to T1, we only need to perform the skull stripping once, i.e. on the T1 volume. Skull stripping is necessary because, without it, the DIR algorithm would deform the interior of the brain to match the outside boundary. This type of deformation is mathematically valid, but does not yield anatomically plausible results. Two possible solutions to this problem are either adding prior knowledge on the boundary or applying skull stripping, of which we opt for the latter due to its common usage in image processing. We use the BrainSuit software [http://users.loni.ucla.edu/~shattuck/brainsuite/corticalsurface/bse/] for the skull stripping.

[[Image:ToT1e1.png|800px]]

Excluding preprocessing steps, the registration of two volumes of sizes 256x256x60 is found to require 6 seconds on the GPU. Registration results are illustrated for a 2D slice in the above figure for acute stage. The norm of the deformation fields and its 2D motion grid are also included. For T2, FLAIR and GRE volumes, the largest amount of deformation is observed bilaterally in the deep periventricular white matter, possibly as a consequence of hemorrhage and/or CSF infiltration into edemic regions, which can alter voxel intensities in GRE and FLAIR imaging, respectively. In the case of DWI, notable deformation is observed frontally and frontolaterally; in the former case, this may be the result of warping artifacts due to the large drop in the physical properties of tissues at the interfaces between brain, bone and air. In the latter case, the deformation is possibly due to the presence of TBI-related edema, which can substantially alter local diffusivity values. Similar effects due to these causes are observed with DWI and with perfusion imaging in both acute and chronic scans.

== Future Work ==

Future work will focus on registration of TBI volumes across time in terms of registering acute to chronic or vice versa. There are a large number of registration algorithms that assume the
smoothness of the vector flow, i.e., the deformation is
diffeomorphic. However, when registering TBI across time, the deformation is not well-defined, let along
to be diffeomorphic, at some regions where bleeding or lesion
occurs. It is challenging and important to design a registration
algorithm that can deal with topological changes for TBI patients.

= Key Investigators =

Georgia Tech: Yifei Lou and Patricio Vela

Boston University: Allen Tannenbaum

UCLA: Andrei Irimia, Micah C. Chambers, Jack Van Horn and Paul M. Vespa

= References =
1. Yifei Lou, Andrei Irimia, Patricio Vela, Allen Tannenbaum, Micah C. Chambers, Jack Van Horn and Paul M. Vespa. Multimodal Deformable Registration of Traumatic Brain Injury MR Volumes using Graphics Processing Units. Submitted to IEEE Trans. on Medical Imaging. 2011

2. Yifei Lou and Allen Tannenbaum. Multimodal Deformable Image Registration via the Bhattacharyya Distance. Submitted to IEEE Trans. Image Process. 2011

3. Yifei Lou, Xun Jia, Xuejun Gu and Allen Tannenbaum. A GPU-based Implementation of Multimodal Deformable Image Registration Based on Mutual Information or Bhattacharyya Distance. Insight Journal, 2011. [http://www.midasjournal.org/browse/publication/803]

4. E. D’Agostino, F. Maes, D. Vandermeulen, and P. Suetens. A viscous fluid model for multimodal non-rigid image registration using mutual information,” MICCAI, 2002, pp. 541–548

2012 Winter Project Week:TBIRegistration

2012-02-06T00:29:42Z

Yflou: /* Key Investigators */

__NOTOC__
<gallery>
Image:PW-SLC2012.png|[[2012_Winter_Project_Week#Projects|Projects List]]
</gallery>

==Key Investigators==
*Georgia Tech: Yifei Lou and Patricio Vela
*Boston University: Allen Tannenbaum
*UCLA: Andrei Irimia, Micah C. Chambers, Jack Van Horn and Paul M. Vespa

<div style="margin: 20px;">
<div style="width: 27%; float: left; padding-right: 3%;">

<h3>Objective</h3>
* A short version of conference submission.
* A in-depth discussion on the similarity measures for TBI image registration as a journal submission.
* Design a registration algorithm that can deal with topological changes for TBI patients.
* Design metrics to quantify the degree of changes of TBI

</div>

<div style="width: 27%; float: left; padding-right: 3%;">

<h3>Approach, Plan</h3>

* Analyze on different similarity measures, such as mutual information, Bhattacharyya Distance, J-R Divergence and cross correlation etc
* Compare with some state-of-the-art registration methods, such as FSL, FNIRT, AIR etc
* Use Dice coefficient as a quantitative metric to measure the quality of registration algorithms

</div>

<div style="width: 40%; float: left;">

<h3>Progress</h3>
* We have tailored a 10-page paper for a conference submission
* We have discussed a few feasible aspects to polish our paper as in Approach
* We will submit a journal version shortly

</div>
</div>

<div style="width: 97%; float: left;">

==Delivery Mechanism==

This work will be delivered to the NA-MIC Kit as a (please select the appropriate options by noting YES against them below)

#Slicer Module
##Extension -- commandline

==References==

1. Yifei Lou, Andrei Irimia, Patricio Vela, Allen Tannenbaum, Micah C. Chambers, Jack Van Horn and Paul M. Vespa. Multimodal Deformable Registration of Traumatic Brain Injury MR Volumes using Graphics Processing Units. Submitted to IEEE Trans. on Medical Imaging. 2011

2. Yifei Lou and Allen Tannenbaum. Multimodal Deformable Image Registration via the Bhattacharyya Distance. Submitted to IEEE Trans. Image Process. 2011

3. Yifei Lou, Xun Jia, Xuejun Gu and Allen Tannenbaum. A GPU-based Implementation of Multimodal Deformable Image Registration Based on Mutual Information or Bhattacharyya Distance. Insight Journal, 2011. [http://www.midasjournal.org/browse/publication/803]

4. E. D’Agostino, F. Maes, D. Vandermeulen, and P. Suetens. A viscous fluid model for multimodal non-rigid image registration using mutual information,” MICCAI, 2002, pp. 541–548
</div>

2012 Winter Project Week:TBIRegistration

2012-02-06T00:25:14Z

Yflou: /* Key Investigators */

__NOTOC__
<gallery>
Image:PW-SLC2012.png|[[2012_Winter_Project_Week#Projects|Projects List]]
</gallery>

==Key Investigators==
*Georgia Tech: Yifei Lou and Patricio Vela
*Boston University: Allen Tannenbaum
*UCLA: Andrei Irimia, Micah C. Chambers, Jack Van Horn and Paul M. Vespa

<div style="margin: 20px;">
<div style="width: 27%; float: left; padding-right: 3%;">

<h3>Objective</h3>
* A short version of conference submission.
* A in-depth discussion on the similarity measures for TBI image registration as a journal submission.
* Design a registration algorithm that can deal with topological changes for TBI patients.
* Design metrics to quantify the degree of changes of TBI

</div>

<div style="width: 27%; float: left; padding-right: 3%;">

<h3>Approach, Plan</h3>

* Analyze on different similarity measures, such as mutual information, Bhattacharyya Distance, J-R Divergence and cross correlation etc
* Compare with some state-of-the-art registration methods, such as FSL, FNIRT, AIR etc
* Use Dice coefficient as a quantitative metric to measure the quality of registration algorithms

</div>

<div style="width: 40%; float: left;">

<h3>Progress</h3>
* We have tailored a 10-page paper for a conference submission
* We have discussed a few aspects on how to polish our paper
* We will submit a journal paper shortly

</div>
</div>

<div style="width: 97%; float: left;">

==Delivery Mechanism==

This work will be delivered to the NA-MIC Kit as a (please select the appropriate options by noting YES against them below)

#Slicer Module
##Extension -- commandline

==References==

1. Yifei Lou, Andrei Irimia, Patricio Vela, Allen Tannenbaum, Micah C. Chambers, Jack Van Horn and Paul M. Vespa. Multimodal Deformable Registration of Traumatic Brain Injury MR Volumes using Graphics Processing Units. Submitted to IEEE Trans. on Medical Imaging. 2011

2. Yifei Lou and Allen Tannenbaum. Multimodal Deformable Image Registration via the Bhattacharyya Distance. Submitted to IEEE Trans. Image Process. 2011

3. Yifei Lou, Xun Jia, Xuejun Gu and Allen Tannenbaum. A GPU-based Implementation of Multimodal Deformable Image Registration Based on Mutual Information or Bhattacharyya Distance. Insight Journal, 2011. [http://www.midasjournal.org/browse/publication/803]

4. E. D’Agostino, F. Maes, D. Vandermeulen, and P. Suetens. A viscous fluid model for multimodal non-rigid image registration using mutual information,” MICCAI, 2002, pp. 541–548
</div>

2012 Winter Project Week:TBIRegistration

2012-01-04T19:47:16Z

Yflou: /* Key Investigators */

__NOTOC__
<gallery>
Image:PW-SLC2012.png|[[2012_Winter_Project_Week#Projects|Projects List]]
</gallery>

==Key Investigators==
*Georgia Tech: Yifei Lou and Patricio Vela
*Boston University: Allen Tannenbaum
*UCLA: Andrei Irimia, Micah C. Chambers, Jack Van Horn and Paul M. Vespa

<div style="margin: 20px;">
<div style="width: 27%; float: left; padding-right: 3%;">

<h3>Objective</h3>
* Design a registration algorithm that can deal with topological changes for TBI patients.
* Design metrics to quantify the degree of changes of TBI

</div>

<div style="width: 27%; float: left; padding-right: 3%;">

<h3>Approach, Plan</h3>

Approach to be filled here.

</div>

<div style="width: 40%; float: left;">

<h3>Progress</h3>

</div>
</div>

<div style="width: 97%; float: left;">

==Delivery Mechanism==

This work will be delivered to the NA-MIC Kit as a (please select the appropriate options by noting YES against them below)

#Slicer Module
##Extension -- commandline

==References==

1. Yifei Lou, Andrei Irimia, Patricio Vela, Allen Tannenbaum, Micah C. Chambers, Jack Van Horn and Paul M. Vespa. Multimodal Deformable Registration of Traumatic Brain Injury MR Volumes using Graphics Processing Units. Submitted to IEEE Trans. on Medical Imaging. 2011

2. Yifei Lou and Allen Tannenbaum. Multimodal Deformable Image Registration via the Bhattacharyya Distance. Submitted to IEEE Trans. Image Process. 2011

3. Yifei Lou, Xun Jia, Xuejun Gu and Allen Tannenbaum. A GPU-based Implementation of Multimodal Deformable Image Registration Based on Mutual Information or Bhattacharyya Distance. Insight Journal, 2011. [http://www.midasjournal.org/browse/publication/803]

4. E. D’Agostino, F. Maes, D. Vandermeulen, and P. Suetens. A viscous fluid model for multimodal non-rigid image registration using mutual information,” MICCAI, 2002, pp. 541–548
</div>

2012 Winter Project Week:TBIRegistration

2011-11-19T04:14:19Z

Yflou: /* Key Investigators */

__NOTOC__
<gallery>
Image:PW-SLC2012.png|[[2012_Winter_Project_Week#Projects|Projects List]]
</gallery>

==Key Investigators==
*Georgia Tech: Yifei Lou and Patricio Vela
*Boston University: Allen Tannenbaum
*UCLA: Andrei Irimia, Micah C. Chambers, Jack Van Horn and Paul M. Vespa

<div style="margin: 20px;">
<div style="width: 27%; float: left; padding-right: 3%;">

<h3>Objective</h3>
* Design a registration algorithm that can deal with topological changes for TBI patients.
* Design metrics to quantify the degree of changes of TBI

</div>

<div style="width: 27%; float: left; padding-right: 3%;">

<h3>Approach, Plan</h3>

Approach to be filled here.

</div>

<div style="width: 40%; float: left;">

<h3>Progress</h3>
The current segmentation module is in the Slicer extension manager.

</div>
</div>

<div style="width: 97%; float: left;">

==Delivery Mechanism==

This work will be delivered to the NA-MIC Kit as a (please select the appropriate options by noting YES against them below)

#Slicer Module
##Extension -- commandline

==References==

1. Yifei Lou, Andrei Irimia, Patricio Vela, Allen Tannenbaum, Micah C. Chambers, Jack Van Horn and Paul M. Vespa. Multimodal Deformable Registration of Traumatic Brain Injury MR Volumes using Graphics Processing Units. Submitted to IEEE Trans. on Medical Imaging. 2011

2. Yifei Lou and Allen Tannenbaum. Multimodal Deformable Image Registration via the Bhattacharyya Distance. Submitted to IEEE Trans. Image Process. 2011

3. Yifei Lou, Xun Jia, Xuejun Gu and Allen Tannenbaum. A GPU-based Implementation of Multimodal Deformable Image Registration Based on Mutual Information or Bhattacharyya Distance. Insight Journal, 2011. [http://www.midasjournal.org/browse/publication/803]

4. E. D’Agostino, F. Maes, D. Vandermeulen, and P. Suetens. A viscous fluid model for multimodal non-rigid image registration using mutual information,” MICCAI, 2002, pp. 541–548
</div>

2012 Winter Project Week:TBIRegistration

2011-11-19T04:11:28Z

Yflou:

__NOTOC__
<gallery>
Image:PW-SLC2012.png|[[2012_Winter_Project_Week#Projects|Projects List]]
</gallery>

==Key Investigators==
*Georgia Tech: Yifei Lou and Patricio Vela
*Boston University: Allen Tannenbaum
*UCLA: Andrei Irimia, Micah C. Chambers, Jack Van Horn and Paul M. Vespa

<div style="margin: 20px;">
<div style="width: 27%; float: left; padding-right: 3%;">

<h3>Objective</h3>
* We are developing methods for segmenting the endocardium from the DE-MRI. The current proposed method is a multi-atlas based registration approach. The user is presented with a weighted average of all registered atlas segmentations. The final LA segmentation is a thresholded volume from this weighted average. Weighting is based on the accuracy of the registration, as determined by a mutual information metric.
* There is a prototype module developed by Yi that is currently in Slicer. We propose to expand and tweak this module to specifications determined by our experience using the algorithm on many real patient datasets.
* We will also discuss posssible collaborative paper ideas based on this work.

</div>

<div style="width: 27%; float: left; padding-right: 3%;">

<h3>Approach, Plan</h3>

Approach to be filled here.

</div>

<div style="width: 40%; float: left;">

<h3>Progress</h3>
The current segmentation module is in the Slicer extension manager.

</div>
</div>

<div style="width: 97%; float: left;">

==Delivery Mechanism==

This work will be delivered to the NA-MIC Kit as a (please select the appropriate options by noting YES against them below)

#Slicer Module
##Extension -- commandline

==References==

1. Yifei Lou, Andrei Irimia, Patricio Vela, Allen Tannenbaum, Micah C. Chambers, Jack Van Horn and Paul M. Vespa. Multimodal Deformable Registration of Traumatic Brain Injury MR Volumes using Graphics Processing Units. Submitted to IEEE Trans. on Medical Imaging. 2011

2. Yifei Lou and Allen Tannenbaum. Multimodal Deformable Image Registration via the Bhattacharyya Distance. Submitted to IEEE Trans. Image Process. 2011

3. Yifei Lou, Xun Jia, Xuejun Gu and Allen Tannenbaum. A GPU-based Implementation of Multimodal Deformable Image Registration Based on Mutual Information or Bhattacharyya Distance. Insight Journal, 2011. [http://www.midasjournal.org/browse/publication/803]

4. E. D’Agostino, F. Maes, D. Vandermeulen, and P. Suetens. A viscous fluid model for multimodal non-rigid image registration using mutual information,” MICCAI, 2002, pp. 541–548
</div>

2012 Winter Project Week:TBIRegistration

2011-11-19T04:05:39Z

Yflou: Created page with '==Key Investigators== *Georgia Tech: Yifei Lou and Patricio Vela *Boston University: Allen Tannenbaum *UCLA: Andrei Irimia, Micah C. Chambers, Jack Van Horn and Paul M. Vespa <d…'

==Key Investigators==
*Georgia Tech: Yifei Lou and Patricio Vela
*Boston University: Allen Tannenbaum
*UCLA: Andrei Irimia, Micah C. Chambers, Jack Van Horn and Paul M. Vespa

<div style="margin: 20px;">

<div style="width: 27%; float: left; padding-right: 3%;">
<h3>Objective</h3>
We are developing a Slicer4 module that can receive tracked ultrasound images through an OpenIGTLink connection, and create a representation of the real-time ultrasound image in the Slicer scene.
</div>

<div style="width: 27%; float: left; padding-right: 3%;">
<h3>Approach, Plan</h3>
The PLUS (Public Library for Ultrasound) library will send OpenIGTLink messages to Slicer. Images to update the ultrasound image data, and transforms to update the ultrasound slice position and other surgical tools in the scene.
</div>

<div style="width: 40%; float: left;">

<h3>Progress</h3>

</div>
</div>

<div style="width: 97%; float: left;">

2012 Winter Project Week

2011-11-19T03:58:18Z

Yflou: /* Traumatic Brain Injury DBP */

Back to [[Project Events]], [[Events]]
Back to [[Project Events]], [[AHM_2012]], [[Events]]

__NOTOC__
[[image:PW-SLC2012.png|300px]]

== Dates.Venue.Registration ==

Please [[AHM_2012#Dates_Venue_Registration|click here for Dates, Venue, and Registration]] for this event.

== Agenda==

Please [[AHM_2012#Agenda|click here for the agenda for AHM 2012 and Project Week]].

==Background==

From January 9-13, 2012, the 14th project week for hands-on research and development activity in Neuroscience and Image-Guided Therapy applications will be hosted in Salt Lake City, Utah. Participant engage in open source programming using the [[NA-MIC-Kit|NA-MIC Kit]], algorithms, medical imaging sequence development, tracking experiments, and clinical applications. The main goal of this event is to further the translational research deliverables of the sponsoring centers ([http://www.na-mic.org NA-MIC], [http://www.ncigt.org NCIGT], [http://nac.spl.harvard.edu NAC], [http://catalyst.harvard.edu/home.html Harvard Catalyst], and [http://www.cimit.org CIMIT]) and their collaborators by identifying and solving programming problems during planned and ad hoc break-out sessions.

Active preparation for this conference begins with a kick-off teleconference. Invitations to this call are sent to members of the sponsoring communities, their collaborators, past attendees of the event, as well as any parties expressing an interest in working with these centers. The main goal of the initial teleconference is to gather information about which groups/projects would be active at the upcoming event to ensure that there were sufficient resources available to meet everyone's needs. Focused discussions about individual projects are conducted during several subsequent teleconferences and permits the hosts to finalize the project teams, consolidate any common components, and identify topics that should be discussed in break-out sessions. In the final days leading up to the meeting, all project teams are asked to complete a template page on the wiki describing the objectives and research plan for each project.

On the first day of the conference, each project team leader delivers a short presentation to introduce their topic and individual members of their team. These brief presentations serve to both familiarize other teams doing similar work about common problems or practical solutions, and to identify potential subsets of individuals who might benefit from collaborative work. For the remainder of the conference, about 50% time is devoted to break-out discussions on topics of common interest to particular subsets and 50% to hands-on project work. For hands-on project work, attendees are organized into 30-50 small teams comprised of 2-4 individuals with a mix of multi-disciplinary expertise. To facilitate this work, a large room is setup with ample work tables, internet connection, and power access. This enables each computer software development-based team to gather on a table with their individual laptops, connect to the internet, download their software and data, and work on specific projects. On the final day of the event, each project team summarizes their accomplishments in a closing presentation.

A summary of all past NA-MIC Project Events is available [[Project_Events#Past|here]].

==Projects==

===IGT===
*MR guided laser ablation for neurosurgery (Dan Orringer, MD BWH, Jason Stafford, MD Anderson, Isaiah Norton BWH)
*Pelvic Registration (Sandy Wells, Firdaus Janoos, Mehdi Moradi UBC/BWH, jan egger, andrey fedorov)
*OpenIGTLink interface for Slicer4(Junichi, Clif Burdette/Jack Blevins, Tamas Ungi, Andras Lasso)
*Needle tracking (atushi yamada, radhika tibrewal, a needle navigation person)
*?mr susceptability (clare poynton, mr physics person?)
* [[2012_Winter_Project_Week:LiveUltrasound|Live ultrasound in Slicer4 using Plus and OpenIGTLink]] (Tamas Ungi, Elvis Chen)

===Traumatic Brain Injury DBP===

* [[2012_Winter_Project_Week:TBIClinicalAnalysis|Quantitative clinical analysis of longitudinal TBI using current registration and segmentation algorithms]] (Marcel Prastawa, Bo Wang, Andrei Irimia, Jack van Horn, Guido Gerig)
* [[2012_Winter_Project_Week:TBIDTI|Analysis of DTI data in TBI]] (Marcel Prastawa, Bo Wang, Andrei Irimia, Jack van Horn, Guido Gerig)
* [[2012_Winter_Project_Week:TBIValidation|Validation of analysis algorithms for TBI]] (Marcel Prastawa, Bo Wang, Andrei Irimia, Jack van Horn, Guido Gerig)
*Geometric Metamorphosis for TBI (Danielle Pace, Marc Niethammer)
* [[2012_Winter_Project_Week:TBIRegistration|Multimodal Deformable Registration of Traumatic Brain Injury MR Volumes using Graphics Processing Units]] (Yifei Lou, Andrei Irimia, Patricio Vela, Allen Tannenbaum, Micah C. Chambers, Jack Van Horn and Paul M. Vespa)

===Predict Huntington's Disease DBP===
* [[2012_Winter_Project_Week:FVLight|FiberViewerLight: a fiber bundle visualization and clustering tool]] (Jean-Baptiste Berger, Clement Vachet, Martin Styner)
* [[2012_Winter_Project_Week:DTIAFA|DTIAtlasFiberAnalyzer]] (Jean-Baptiste Berger, Yundi Shi, Clement Vachet, Martin Styner)
* [[2012_Winter_Project_Week:PairWiseDTIRegistration|Pairwise DTI registration: DTI-Reg]] (Clement Vachet, Hans Johnson, Martin Styner)

===Atrial fibrillation DBP===
* [[2012_Winter_Project_Week:EndoSeg|Endocardial Segmentation in DE-MRI for AFib]] (Yi Gao, Liang-Jia Zhu, Josh Cates, Greg Gardner, Alan Morris, Danny Perry, Rob MacLeod, Sylvain Bouix, Allen Tannenbaum)
* [[2012_Winter_Project_Week:LAWallRegistration|Longitudinal Alignment and Visualization of Left-Atrial Wall from DEMRI and MRA]] (Josh Cates, Yi Gao, Liang-Jia Zhu, Greg Gardner, Alan Morris, Danny Perry, Rob MacLeod, Sylvain Bouix, Allen Tannenbaum)
* [[2012_Winter_Project_Week:PVRegistration|Longitudinal Alignment and Visualization of Pulmonary Veins from DEMRI and MRA]] (Josh Cates, Yi Gao, Liang-Jia Zhu, Greg Gardner, Alan Morris, Danny Perry, Rob MacLeod, Sylvain Bouix, Allen Tannenbaum)
* [[2012_Winter_Project_Week:RealTime|OpenIGT for realtime MRI-guided RF ablation]] (Gene Payne, Rob MacLeod, and Junichi Tokuda)

===Head and Neck Cancer DBP===
* A patch-based approach to the segmentation of organs of risk (Christian Wachinger, Polina Golland)

===Radiation therapy===
* [[2012_Winter_Project_Week:RTTools|RT tools for Slicer4]] (Csaba Pinter, Kevin Wang, Andras Lasso, Greg Sharp)

===NA-MIC Kit Internals===
*Slicer4 Scene Views Module (Nicole Aucoin)
*Slicer4 Annotations Module
** File format refactor (Nicole Aucoin)
** QT 3D Text rendering proof of concept (Julien Finet, Steve Pieper, Nicole Aucoin)
* Editor Extension Examples and Debugging (Steve Pieper)

=== Preparation ===

#Please make sure that you are on the [http://public.kitware.com/cgi-bin/mailman/listinfo/na-mic-project-week na-mic-project-week mailing list]
#Starting Thursday, October 27th, part of the weekly Thursday 3pm NA-MIC Engineering TCON will be used to prepare for this meeting. The schedule for these preparatory calls is as follows:
#*October 27: MGH DBP
#*November 3: Iowa DBP Huntingtons, Engineering Infrastructure Topics
#*November 10: Utah Atrial Fibrillation DBP
#*November 17: UCLA TBI DBP
#*November 24: No call. thanksgiving.
#*December 1:
#*December 8:
#*December 15:Finalize Projects
#*January 5: Loose Ends
#By December 15: [[Project_Week/Template|Complete a templated wiki page for your project]]. Please do not edit the template page itself, but create a new page for your project and cut-and-paste the text from this template page. If you have questions, please send an email to tkapur at bwh.harvard.edu.
#By December 15: Create a directory for each project on the [[Engineering:SandBox|NAMIC Sandbox]] (Zack)
##[https://www.kitware.com/Admin/SendPassword.cgi Ask Zack for a Sandbox account]
##Commit on each sandbox directory the code examples/snippets that represent our first guesses of appropriate methods. (Luis and Steve will help with this, as needed)
##Gather test images in any of the Data sharing resources we have (e.g. MIDAS, xNAT). These ones don't have to be many. At least three different cases, so we can get an idea of the modality-specific characteristics of these images. Put the IDs of these data sets on the wiki page. (the participants must do this.)
##Setup nightly tests on a separate Dashboard, where we will run the methods that we are experimenting with. The test should post result images and computation time. (Zack)
#Please note that by the time we get to the project event, we should be trying to close off a project milestone rather than starting to work on one...

Projects:RegistrationTBI

2011-10-25T18:34:15Z

Yflou: /* References */

Back to [[Algorithm:BU|Boston University Algorithms]]
__NOTOC__
= Multimodal Deformable Registration of Traumatic Brain Injury MR Volumes using Graphics Processing Units =

= Description =
An estimated 1.7 million Americans sustain traumatic brain injuries (TBI's) every year. The large number of recent TBI cases in soldiers returning from military conflicts has highlighted the critical need for improvement of TBI care and treatment, and has drawn sustained attention to the need for improved methodologies of TBI neuroimaging data analysis. Neuroimaging of TBI is vital for surgical planning by providing important information for anatomic localization and surgical navigation, as well as for monitoring patient case evolution over time. Approximately 2 days after the acute injury, magnetic resonance imaging (MRI) becomes preferable to computed tomography (CT) for the purpose of lesion characterization, and the use of various MR sequences tailored to capture distinct aspects of TBI pathology provides clinicians with essential complementary information for the assessment of TBI-related anatomical insults and pathophysiology.

Image registration plays an essential role in a wide variety of TBI data analysis workflows. It aims to find a transformation between two image sets such that the transformed image becomes similar to the target image according to some chosen metric or criterion. Typically, a similarity measure is first established to quantify how `close` two image volumes are to each other. Next, the transformation that maximizes this similarity is typically computed through an optimization process which constrains the transformation to a predetermined class, such as rigid, affine or deformable. Numerous challenges associated with the task of TBI volume co-registration can exist if data acquisition is performed multimodally, and additional complexities can also arise due to the large degree of algorithmic robustness that may be required in order to properly address pathology-related deformations. Many conventional methods use the sum of squared differences of intensity values between two image sets as a similarity measure, which can perform poorly or even fail for TBI volume registration. Consequently, because the deformation of patient anatomy and soft tissues cannot typically be represented by rigid transforms, image registration often requires deformable image registration (DIR), i.e., the necessity of applying nonparametric infinite-dimensional transformations.

This paper proposes to replace the Mutual Information (MI) criterion for registration with the Bhattachayya distance [2] within a multimodal DIR framework [4]. The advantage of BD over MI is the superior behavior of the square root function compared to that of the logarithm at zero, which yields a more stable algorithm.
This framework we describe takes into account the physical models of tissue motion to regularize the deformation fields and also involves free-form deformation. On the other hand, the DIR algorithm is computationally expensive when implemented on conventional central processing units, which can be detrimental particularly when three-dimensional (3D) volumes-rather than 2D images-need to be co-registered. In clinical settings that involve acute TBI care, the amount of time required by the processing of neuroimaging data sets from patients in critical condition should be minimized. To meet this clinical requirement, we have implemented our algorithm on a graphics processing unit (GPU) platform [3].

== Result ==

MR volumes were acquired at 3 T using a Siemens Trio TIM scanner (Siemens AG, Erlangen, Germany). Because assessing the time evolution of TBI between the acute to the chronic stage is of great interest in the clinical field in order to evaluate case evolution, scanning sessions were held both several days (acute baseline) as well as 6 months (chronic follow-up) after the traumatic injury event. To eliminate the effect of different scanner parameters during each scanning session, every subject was scanned using the same scanner for both acute and chronic time points. The MP-RAGE sequence (Mugler and Brookeman, 1990) was used to acquire T1-weighted images. In addition, MR data were also acquired using fluid-attenuated inversion recovery (FLAIR, (De Coene et al., 1992)), gradient-recalled echo (GRE) T2-weighted images as well as diffusion weighted imaging (DWI), and perfusion imaging.

Before applying our deformable registration algorithm, all image volumes were co-registered by rigid-body transformation to the pre-contrast T1-weighted volume acquired during the acute baseline scanning session. This helps to correct for head tilt and reduce error in computing the local deformation fields. Another technique that was employed before performing the registration is skull stripping, which was useful in our case because images acquired at the acute stage exhibit appreciably more extracranial swelling compared to images acquired chronically. Since all modalities are co-registered to T1, we only need to perform the skull stripping once, i.e. on the T1 volume. Skull stripping is necessary because, without it, the DIR algorithm would deform the interior of the brain to match the outside boundary. This type of deformation is mathematically valid, but does not yield anatomically plausible results. Two possible solutions to this problem are either adding prior knowledge on the boundary or applying skull stripping, of which we opt for the latter due to its common usage in image processing. We use the BrainSuit software [http://users.loni.ucla.edu/~shattuck/brainsuite/corticalsurface/bse/] for the skull stripping.

[[Image:ToT1e1.png|800px]]

Excluding preprocessing steps, the registration of two volumes of sizes 256x256x60 is found to require 6 seconds on the GPU. Registration results are illustrated for a 2D slice in the above figure for acute stage. The norm of the deformation fields and its 2D motion grid are also included. For T2, FLAIR and GRE volumes, the largest amount of deformation is observed bilaterally in the deep periventricular white matter, possibly as a consequence of hemorrhage and/or CSF infiltration into edemic regions, which can alter voxel intensities in GRE and FLAIR imaging, respectively. In the case of DWI, notable deformation is observed frontally and frontolaterally; in the former case, this may be the result of warping artifacts due to the large drop in the physical properties of tissues at the interfaces between brain, bone and air. In the latter case, the deformation is possibly due to the presence of TBI-related edema, which can substantially alter local diffusivity values. Similar effects due to these causes are observed with DWI and with perfusion imaging in both acute and chronic scans.

== Future Work ==

Future work will focus on registration of TBI volumes across time in terms of registering acute to chronic or vice versa. There are a large number of registration algorithms that assume the
smoothness of the vector flow, i.e., the deformation is
diffeomorphic. However, when registering TBI across time, the deformation is not well-defined, let along
to be diffeomorphic, at some regions where bleeding or lesion
occurs. It is challenging and important to design a registration
algorithm that can deal with topological changes for TBI patients.

= Key Investigators =

Georgia Tech: Yifei Lou and Patricio Vela

Boston University: Allen Tannenbaum

UCLA: Andrei Irimia, Micah C. Chambers, Jack Van Horn and Paul M. Vespa

= References =
1. Yifei Lou, Andrei Irimia, Patricio Vela, Allen Tannenbaum, Micah C. Chambers, Jack Van Horn and Paul M. Vespa. Multimodal Deformable Registration of Traumatic Brain Injury MR Volumes using Graphics Processing Units. Submitted to IEEE Trans. on Medical Imaging. 2011

2. Yifei Lou and Allen Tannenbaum. Multimodal Deformable Image Registration via the Bhattacharyya Distance. Submitted to IEEE Trans. Image Process. 2011

3. Yifei Lou, Xun Jia, Xuejun Gu and Allen Tannenbaum. A GPU-based Implementation of Multimodal Deformable Image Registration Based on Mutual Information or Bhattacharyya Distance. Insight Journal, 2011. [http://www.midasjournal.org/browse/publication/803]

4. E. D’Agostino, F. Maes, D. Vandermeulen, and P. Suetens. A viscous fluid model for multimodal non-rigid image registration using mutual information,” MICCAI, 2002, pp. 541–548

Projects:RegistrationTBI

2011-10-17T15:51:42Z

Yflou: /* Description */

Back to [[Algorithm:BU|Boston University Algorithms]]
__NOTOC__
= Multimodal Deformable Registration of Traumatic Brain Injury MR Volumes using Graphics Processing Units =

= Description =
An estimated 1.7 million Americans sustain traumatic brain injuries (TBI's) every year. The large number of recent TBI cases in soldiers returning from military conflicts has highlighted the critical need for improvement of TBI care and treatment, and has drawn sustained attention to the need for improved methodologies of TBI neuroimaging data analysis. Neuroimaging of TBI is vital for surgical planning by providing important information for anatomic localization and surgical navigation, as well as for monitoring patient case evolution over time. Approximately 2 days after the acute injury, magnetic resonance imaging (MRI) becomes preferable to computed tomography (CT) for the purpose of lesion characterization, and the use of various MR sequences tailored to capture distinct aspects of TBI pathology provides clinicians with essential complementary information for the assessment of TBI-related anatomical insults and pathophysiology.

Image registration plays an essential role in a wide variety of TBI data analysis workflows. It aims to find a transformation between two image sets such that the transformed image becomes similar to the target image according to some chosen metric or criterion. Typically, a similarity measure is first established to quantify how `close` two image volumes are to each other. Next, the transformation that maximizes this similarity is typically computed through an optimization process which constrains the transformation to a predetermined class, such as rigid, affine or deformable. Numerous challenges associated with the task of TBI volume co-registration can exist if data acquisition is performed multimodally, and additional complexities can also arise due to the large degree of algorithmic robustness that may be required in order to properly address pathology-related deformations. Many conventional methods use the sum of squared differences of intensity values between two image sets as a similarity measure, which can perform poorly or even fail for TBI volume registration. Consequently, because the deformation of patient anatomy and soft tissues cannot typically be represented by rigid transforms, image registration often requires deformable image registration (DIR), i.e., the necessity of applying nonparametric infinite-dimensional transformations.

This paper proposes to replace the Mutual Information (MI) criterion for registration with the Bhattachayya distance [2] within a multimodal DIR framework [4]. The advantage of BD over MI is the superior behavior of the square root function compared to that of the logarithm at zero, which yields a more stable algorithm.
This framework we describe takes into account the physical models of tissue motion to regularize the deformation fields and also involves free-form deformation. On the other hand, the DIR algorithm is computationally expensive when implemented on conventional central processing units, which can be detrimental particularly when three-dimensional (3D) volumes-rather than 2D images-need to be co-registered. In clinical settings that involve acute TBI care, the amount of time required by the processing of neuroimaging data sets from patients in critical condition should be minimized. To meet this clinical requirement, we have implemented our algorithm on a graphics processing unit (GPU) platform [3].

== Result ==

MR volumes were acquired at 3 T using a Siemens Trio TIM scanner (Siemens AG, Erlangen, Germany). Because assessing the time evolution of TBI between the acute to the chronic stage is of great interest in the clinical field in order to evaluate case evolution, scanning sessions were held both several days (acute baseline) as well as 6 months (chronic follow-up) after the traumatic injury event. To eliminate the effect of different scanner parameters during each scanning session, every subject was scanned using the same scanner for both acute and chronic time points. The MP-RAGE sequence (Mugler and Brookeman, 1990) was used to acquire T1-weighted images. In addition, MR data were also acquired using fluid-attenuated inversion recovery (FLAIR, (De Coene et al., 1992)), gradient-recalled echo (GRE) T2-weighted images as well as diffusion weighted imaging (DWI), and perfusion imaging.

Before applying our deformable registration algorithm, all image volumes were co-registered by rigid-body transformation to the pre-contrast T1-weighted volume acquired during the acute baseline scanning session. This helps to correct for head tilt and reduce error in computing the local deformation fields. Another technique that was employed before performing the registration is skull stripping, which was useful in our case because images acquired at the acute stage exhibit appreciably more extracranial swelling compared to images acquired chronically. Since all modalities are co-registered to T1, we only need to perform the skull stripping once, i.e. on the T1 volume. Skull stripping is necessary because, without it, the DIR algorithm would deform the interior of the brain to match the outside boundary. This type of deformation is mathematically valid, but does not yield anatomically plausible results. Two possible solutions to this problem are either adding prior knowledge on the boundary or applying skull stripping, of which we opt for the latter due to its common usage in image processing. We use the BrainSuit software [http://users.loni.ucla.edu/~shattuck/brainsuite/corticalsurface/bse/] for the skull stripping.

[[Image:ToT1e1.png|800px]]

Excluding preprocessing steps, the registration of two volumes of sizes 256x256x60 is found to require 6 seconds on the GPU. Registration results are illustrated for a 2D slice in the above figure for acute stage. The norm of the deformation fields and its 2D motion grid are also included. For T2, FLAIR and GRE volumes, the largest amount of deformation is observed bilaterally in the deep periventricular white matter, possibly as a consequence of hemorrhage and/or CSF infiltration into edemic regions, which can alter voxel intensities in GRE and FLAIR imaging, respectively. In the case of DWI, notable deformation is observed frontally and frontolaterally; in the former case, this may be the result of warping artifacts due to the large drop in the physical properties of tissues at the interfaces between brain, bone and air. In the latter case, the deformation is possibly due to the presence of TBI-related edema, which can substantially alter local diffusivity values. Similar effects due to these causes are observed with DWI and with perfusion imaging in both acute and chronic scans.

== Future Work ==

Future work will focus on registration of TBI volumes across time in terms of registering acute to chronic or vice versa. There are a large number of registration algorithms that assume the
smoothness of the vector flow, i.e., the deformation is
diffeomorphic. However, when registering TBI across time, the deformation is not well-defined, let along
to be diffeomorphic, at some regions where bleeding or lesion
occurs. It is challenging and important to design a registration
algorithm that can deal with topological changes for TBI patients.

= Key Investigators =

Georgia Tech: Yifei Lou and Patricio Vela

Boston University: Allen Tannenbaum

UCLA: Andrei Irimia, Micah C. Chambers, Jack Van Horn and Paul M. Vespa

= References =
1. Yifei Lou, Andrei Irimia, Patricio Vela, Allen Tannenbaum, Micah C. Chambers, Jack Van Horn and Paul M. Vespa. Multimodal Deformable Registration of Traumatic Brain Injury MR Volumes using Graphics Processing Units. ''In preparation.'' 2011

2. Yifei Lou and Allen Tannenbaum. Multimodal Deformable Image Registration via the Bhattacharyya Distance. Submitted to IEEE Trans. Image Process. 2011

3. Yifei Lou, Xun Jia, Xuejun Gu and Allen Tannenbaum. A GPU-based Implementation of Multimodal Deformable Image Registration Based on Mutual Information or Bhattacharyya Distance. Insight Journal, 2011. [http://www.midasjournal.org/browse/publication/803]

4. E. D’Agostino, F. Maes, D. Vandermeulen, and P. Suetens. A viscous fluid model for multimodal non-rigid image registration using mutual information,” MICCAI, 2002, pp. 541–548

Projects:RegistrationTBI

2011-10-17T15:51:20Z

Yflou:

Back to [[Algorithm:BU|Boston University Algorithms]]
__NOTOC__
= Multimodal Deformable Registration of Traumatic Brain Injury MR Volumes using Graphics Processing Units =

= Description =
An estimated 1.7 million Americans sustain traumatic brain injuries (TBI's) every year. The large number of recent TBI cases in soldiers returning from military conflicts has highlighted the critical need for improvement of TBI care and treatment, and has drawn sustained attention to the need for improved methodologies of TBI neuroimaging data analysis. Neuroimaging of TBI is vital for surgical planning by providing important information for anatomic localization and surgical navigation, as well as for monitoring patient case evolution over time. Approximately 2 days after the acute injury, magnetic resonance imaging (MRI) becomes preferable to computed tomography (CT) for the purpose of lesion characterization, and the use of various MR sequences tailored to capture distinct aspects of TBI pathology provides clinicians with essential complementary information for the assessment of TBI-related anatomical insults and pathophysiology.

Image registration plays an essential role in a wide variety of TBI data analysis workflows. It aims to find a transformation between two image sets such that the transformed image becomes similar to the target image according to some chosen metric or criterion. Typically, a similarity measure is first established to quantify how `close` two image volumes are to each other. Next, the transformation that maximizes this similarity is typically computed through an optimization process which constrains the transformation to a predetermined class, such as rigid, affine or deformable. Numerous challenges associated with the task of TBI volume co-registration can exist if data acquisition is performed multimodally, and additional complexities can also arise due to the large degree of algorithmic robustness that may be required in order to properly address pathology-related deformations. Many conventional methods use the sum of squared differences of intensity values between two image sets as a similarity measure, which can perform poorly or even fail for TBI volume registration. Consequently, because the deformation of patient anatomy and soft tissues cannot typically be represented by rigid transforms, image registration often requires deformable image registration (DIR), i.e., the necessity of applying nonparametric infinite-dimensional transformations.

This paper proposes to replace the Mutual Information (MI) criterion for registration with the Bhattachayya distance [2] within a multimodal DIR framework [4]. The advantage of BD over MI is the superior behavior of the square root function compared to that of the logarithm at zero, which yields a more stable algorithm.
This framework we describe takes into account the physical models of tissue motion to regularize the deformation fields and also involves free-form deformation. On the other hand, the DIR algorithm is computationally expensive when implemented on conventional central processing units, which can be detrimental particularly when three-dimensional (3D) volumes-rather than 2D images-need to be co-registered.

In clinical settings that involve acute TBI care, the amount of time required by the processing of neuroimaging data sets from patients in critical condition should be minimized. To meet this clinical requirement, we have implemented our algorithm on a graphics processing unit (GPU) platform [3].

== Result ==

MR volumes were acquired at 3 T using a Siemens Trio TIM scanner (Siemens AG, Erlangen, Germany). Because assessing the time evolution of TBI between the acute to the chronic stage is of great interest in the clinical field in order to evaluate case evolution, scanning sessions were held both several days (acute baseline) as well as 6 months (chronic follow-up) after the traumatic injury event. To eliminate the effect of different scanner parameters during each scanning session, every subject was scanned using the same scanner for both acute and chronic time points. The MP-RAGE sequence (Mugler and Brookeman, 1990) was used to acquire T1-weighted images. In addition, MR data were also acquired using fluid-attenuated inversion recovery (FLAIR, (De Coene et al., 1992)), gradient-recalled echo (GRE) T2-weighted images as well as diffusion weighted imaging (DWI), and perfusion imaging.

Before applying our deformable registration algorithm, all image volumes were co-registered by rigid-body transformation to the pre-contrast T1-weighted volume acquired during the acute baseline scanning session. This helps to correct for head tilt and reduce error in computing the local deformation fields. Another technique that was employed before performing the registration is skull stripping, which was useful in our case because images acquired at the acute stage exhibit appreciably more extracranial swelling compared to images acquired chronically. Since all modalities are co-registered to T1, we only need to perform the skull stripping once, i.e. on the T1 volume. Skull stripping is necessary because, without it, the DIR algorithm would deform the interior of the brain to match the outside boundary. This type of deformation is mathematically valid, but does not yield anatomically plausible results. Two possible solutions to this problem are either adding prior knowledge on the boundary or applying skull stripping, of which we opt for the latter due to its common usage in image processing. We use the BrainSuit software [http://users.loni.ucla.edu/~shattuck/brainsuite/corticalsurface/bse/] for the skull stripping.

[[Image:ToT1e1.png|800px]]

Excluding preprocessing steps, the registration of two volumes of sizes 256x256x60 is found to require 6 seconds on the GPU. Registration results are illustrated for a 2D slice in the above figure for acute stage. The norm of the deformation fields and its 2D motion grid are also included. For T2, FLAIR and GRE volumes, the largest amount of deformation is observed bilaterally in the deep periventricular white matter, possibly as a consequence of hemorrhage and/or CSF infiltration into edemic regions, which can alter voxel intensities in GRE and FLAIR imaging, respectively. In the case of DWI, notable deformation is observed frontally and frontolaterally; in the former case, this may be the result of warping artifacts due to the large drop in the physical properties of tissues at the interfaces between brain, bone and air. In the latter case, the deformation is possibly due to the presence of TBI-related edema, which can substantially alter local diffusivity values. Similar effects due to these causes are observed with DWI and with perfusion imaging in both acute and chronic scans.

== Future Work ==

Future work will focus on registration of TBI volumes across time in terms of registering acute to chronic or vice versa. There are a large number of registration algorithms that assume the
smoothness of the vector flow, i.e., the deformation is
diffeomorphic. However, when registering TBI across time, the deformation is not well-defined, let along
to be diffeomorphic, at some regions where bleeding or lesion
occurs. It is challenging and important to design a registration
algorithm that can deal with topological changes for TBI patients.

= Key Investigators =

Georgia Tech: Yifei Lou and Patricio Vela

Boston University: Allen Tannenbaum

UCLA: Andrei Irimia, Micah C. Chambers, Jack Van Horn and Paul M. Vespa

= References =
1. Yifei Lou, Andrei Irimia, Patricio Vela, Allen Tannenbaum, Micah C. Chambers, Jack Van Horn and Paul M. Vespa. Multimodal Deformable Registration of Traumatic Brain Injury MR Volumes using Graphics Processing Units. ''In preparation.'' 2011

2. Yifei Lou and Allen Tannenbaum. Multimodal Deformable Image Registration via the Bhattacharyya Distance. Submitted to IEEE Trans. Image Process. 2011

3. Yifei Lou, Xun Jia, Xuejun Gu and Allen Tannenbaum. A GPU-based Implementation of Multimodal Deformable Image Registration Based on Mutual Information or Bhattacharyya Distance. Insight Journal, 2011. [http://www.midasjournal.org/browse/publication/803]

4. E. D’Agostino, F. Maes, D. Vandermeulen, and P. Suetens. A viscous fluid model for multimodal non-rigid image registration using mutual information,” MICCAI, 2002, pp. 541–548

Projects:RegistrationTBI

2011-10-17T15:49:12Z

Yflou:

Back to [[Algorithm:BU|Boston University Algorithms]]
__NOTOC__
= Multimodal Deformable Registration of Traumatic Brain Injury MR Volumes using Graphics Processing Units =

= Description =
An estimated 1.7 million Americans sustain traumatic brain injuries (TBI's) every year. The large number of recent TBI cases in soldiers returning from military conflicts has highlighted the critical need for improvement of TBI care and treatment, and has drawn sustained attention to the need for improved methodologies of TBI neuroimaging data analysis. Neuroimaging of TBI is vital for surgical planning by providing important information for anatomic localization and surgical navigation, as well as for monitoring patient case evolution over time. Approximately 2 days after the acute injury, magnetic resonance imaging (MRI) becomes preferable to computed tomography (CT) for the purpose of lesion characterization, and the use of various MR sequences tailored to capture distinct aspects of TBI pathology provides clinicians with essential complementary information for the assessment of TBI-related anatomical insults and pathophysiology.

Image registration plays an essential role in a wide variety of TBI data analysis workflows. It aims to find a transformation between two image sets such that the transformed image becomes similar to the target image according to some chosen metric or criterion. Typically, a similarity measure is first established to quantify how `close` two image volumes are to each other. Next, the transformation that maximizes this similarity is typically computed through an optimization process which constrains the transformation to a predetermined class, such as rigid, affine or deformable. Numerous challenges associated with the task of TBI volume co-registration can exist if data acquisition is performed multimodally, and additional complexities can also arise due to the large degree of algorithmic robustness that may be required in order to properly address pathology-related deformations. Many conventional methods use the sum of squared differences of intensity values between two image sets as a similarity measure, which can perform poorly or even fail for TBI volume registration. Consequently, because the deformation of patient anatomy and soft tissues cannot typically be represented by rigid transforms, image registration often requires deformable image registration (DIR), i.e., the necessity of applying nonparametric infinite-dimensional transformations.

This paper proposes to replace the Mutual Information (MI) criterion for registration with the Bhattachayya distance [2] within a multimodal DIR framework [4]. The advantage of BD over MI is the superior behavior of the square root function compared to that of the logarithm at zero, which yields a more stable algorithm.
This framework we describe takes into account the physical models of tissue motion to regularize the deformation fields and also involves free-form deformation. On the other hand, the DIR algorithm is computationally expensive when implemented on conventional central processing units, which can be detrimental particularly when three-dimensional (3D) volumes-rather than 2D images-need to be co-registered.

In clinical settings that involve acute TBI care, the amount of time required by the processing of neuroimaging data sets from patients in critical condition should be minimized. To meet this clinical requirement, we have implemented our algorithm on a graphics processing unit (GPU) platform [3].

== Result ==

MR volumes were acquired at 3 T using a Siemens Trio TIM scanner (Siemens AG, Erlangen, Germany). Because assessing the time evolution of TBI between the acute to the chronic stage is of great interest in the clinical field in order to evaluate case evolution, scanning sessions were held both several days (acute baseline) as well as 6 months (chronic follow-up) after the traumatic injury event. To eliminate the effect of different scanner parameters during each scanning session, every subject was scanned using the same scanner for both acute and chronic time points. The MP-RAGE sequence (Mugler and Brookeman, 1990) was used to acquire T1-weighted images. In addition, MR data were also acquired using fluid-attenuated inversion recovery (FLAIR, (De Coene et al., 1992)), gradient-recalled echo (GRE) T2-weighted images as well as diffusion weighted imaging (DWI), and perfusion imaging.

Before applying our deformable registration algorithm, all image volumes were co-registered by rigid-body transformation to the pre-contrast T1-weighted volume acquired during the acute baseline scanning session. This helps to correct for head tilt and reduce error in computing the local deformation fields. Another technique that was employed before performing the registration is skull stripping, which was useful in our case because images acquired at the acute stage exhibit appreciably more extracranial swelling compared to images acquired chronically. Since all modalities are co-registered to T1, we only need to perform the skull stripping once, i.e. on the T1 volume. Skull stripping is necessary because, without it, the DIR algorithm would deform the interior of the brain to match the outside boundary. This type of deformation is mathematically valid, but does not yield anatomically plausible results. Two possible solutions to this problem are either adding prior knowledge on the boundary or applying skull stripping, of which we opt for the latter due to its common usage in image processing. We use the BrainSuit software [http://users.loni.ucla.edu/~shattuck/brainsuite/corticalsurface/bse/] for the skull stripping.

[[Image:ToT1e1.png|800px]]

The method is also applied on caudate. Similarly to the hippocampus cases, in the figure below, we show the segmentation results. In the first and third rows, the yellow colored shapes are the segmentation results output by the method. In the second and forth rows, the colors on the shapes indicate the difference with the manual segmentation results: For each point on the shape (result of the segmentation algorithm), we compute the closest point on the manual segmented surface, and record the distance to that point. Such distances are encoded by the color shown in those rows.

[[Image:MultiScaleCaudateSegmentationHausdorf.png|800px]]

= Key Investigators =

Georgia Tech: Yifei Lou and Patricio Vela

Boston University: Allen Tannenbaum

UCLA: Andrei Irimia, Micah C. Chambers, Jack Van Horn and Paul M. Vespa

= References =
1. Yifei Lou, Andrei Irimia, Patricio Vela, Allen Tannenbaum, Micah C. Chambers, Jack Van Horn and Paul M. Vespa. Multimodal Deformable Registration of Traumatic Brain Injury MR Volumes using Graphics Processing Units. ''In preparation.'' 2011

2. Yifei Lou and Allen Tannenbaum. Multimodal Deformable Image Registration via the Bhattacharyya Distance. Submitted to IEEE Trans. Image Process. 2011

3. Yifei Lou, Xun Jia, Xuejun Gu and Allen Tannenbaum. A GPU-based Implementation of Multimodal Deformable Image Registration Based on Mutual Information or Bhattacharyya Distance. Insight Journal, 2011. [http://www.midasjournal.org/browse/publication/803]

4. E. D’Agostino, F. Maes, D. Vandermeulen, and P. Suetens. A viscous fluid model for multimodal non-rigid image registration using mutual information,” MICCAI, 2002, pp. 541–548

Projects:RegistrationTBI

2011-10-17T15:40:41Z

Yflou: Created page with ' Back to Georgia Tech Algorithms __NOTOC__ = Multimodal Deformable Registration of Traumatic Brain Injury MR Volumes using Graphics Processing Units = = Des…'

Back to [[Algorithm:GATech|Georgia Tech Algorithms]]
__NOTOC__
= Multimodal Deformable Registration of Traumatic Brain Injury MR Volumes using Graphics Processing Units =

= Description =
An estimated 1.7 million Americans sustain traumatic brain injuries (TBI's) every year. The large number of recent TBI cases in soldiers returning from military conflicts has highlighted the critical need for improvement of TBI care and treatment, and has drawn sustained attention to the need for improved methodologies of TBI neuroimaging data analysis. Neuroimaging of TBI is vital for surgical planning by providing important information for anatomic localization and surgical navigation, as well as for monitoring patient case evolution over time. Approximately 2 days after the acute injury, magnetic resonance imaging (MRI) becomes preferable to computed tomography (CT) for the purpose of lesion characterization, and the use of various MR sequences tailored to capture distinct aspects of TBI pathology provides clinicians with essential complementary information for the assessment of TBI-related anatomical insults and pathophysiology.

Image registration plays an essential role in a wide variety of TBI data analysis workflows. It aims to find a transformation between two image sets such that the transformed image becomes similar to the target image according to some chosen metric or criterion. Typically, a similarity measure is first established to quantify how `close` two image volumes are to each other. Next, the transformation that maximizes this similarity is typically computed through an optimization process which constrains the transformation to a predetermined class, such as rigid, affine or deformable. Numerous challenges associated with the task of TBI volume co-registration can exist if data acquisition is performed multimodally, and additional complexities can also arise due to the large degree of algorithmic robustness that may be required in order to properly address pathology-related deformations. Many conventional methods use the sum of squared differences of intensity values between two image sets as a similarity measure, which can perform poorly or even fail for TBI volume registration. Consequently, because the deformation of patient anatomy and soft tissues cannot typically be represented by rigid transforms, image registration often requires deformable image registration (DIR), i.e., the necessity of applying nonparametric infinite-dimensional transformations.

This paper proposes to replace the Mutual Information (MI) criterion for registration with the Bhattachayya distance [2] within a multimodal DIR framework [4]. The advantage of BD over MI is the superior behavior of the square root function compared to that of the logarithm at zero, which yields a more stable algorithm.
This framework we describe takes into account the physical models of tissue motion to regularize the deformation fields and also involves free-form deformation. On the other hand, the DIR algorithm is computationally expensive when implemented on conventional central processing units, which can be detrimental particularly when three-dimensional (3D) volumes-rather than 2D images-need to be co-registered.

In clinical settings that involve acute TBI care, the amount of time required by the processing of neuroimaging data sets from patients in critical condition should be minimized. To meet this clinical requirement, we have implemented our algorithm on a graphics processing unit (GPU) platform.

== Result ==

The segmentation method is applied on hippocampus. In the figure below, we show the segmentation results. In the first, third, and the fifth rows, the yellow colored shapes are the segmentation results output by the method. In the second, forth, and sixth rows, the colors on the shapes indicate the difference with the manual segmentation results: For each point on the shape (result of the segmentation algorithm), we compute the closest point on the manual segmented surface, and record the distance to that point. Such distances are encoded by the color shown in those rows.

[[Image:MultiScaleHippoSegmentationHausdorf.png|800px]]

The method is also applied on caudate. Similarly to the hippocampus cases, in the figure below, we show the segmentation results. In the first and third rows, the yellow colored shapes are the segmentation results output by the method. In the second and forth rows, the colors on the shapes indicate the difference with the manual segmentation results: For each point on the shape (result of the segmentation algorithm), we compute the closest point on the manual segmented surface, and record the distance to that point. Such distances are encoded by the color shown in those rows.

[[Image:MultiScaleCaudateSegmentationHausdorf.png|800px]]

= Key Investigators =

Georgia Tech: Yifei Lou and Patricio Vela
Boston University: Allen Tannenbaum
UCLA: Andrei Irimia, Micah C. Chambers, Jack Van Horn and Paul M. Vespa

= References =
1. Yifei Lou, Andrei Irimia, Patricio Vela, Allen Tannenbaum, Micah C. Chambers, Jack Van Horn and Paul M. Vespa. Multimodal Deformable Registration of Traumatic Brain Injury MR Volumes using Graphics Processing Units. ''In preparation.'' 2011

2. Yifei Lou and Allen Tannenbaum. Multimodal Deformable Image Registration via the Bhattacharyya Distance. Submitted to IEEE Trans. Image Process. 2011

3. Yifei Lou, Xun Jia, Xuejun Gu and Allen Tannenbaum. A GPU-based Implementation of Multimodal Deformable Image Registration Based on Mutual Information or Bhattacharyya Distance. Insight Journal, 2011. [online version][http://www.midasjournal.org/browse/publication/803]

4. E. D’Agostino, F. Maes, D. Vandermeulen, and P. Suetens. A viscous fluid model for multimodal non-rigid image registration using mutual information,” MICCAI, 2002, pp. 541–548

Algorithm:BU

2011-10-17T15:13:00Z

Yflou: /* Multimodal Deformable Registration of Traumatic Brain Injury MR Volumes using Graphics Processing Units */

Back to [[Algorithm:Main|NA-MIC Algorithms]]
__NOTOC__
= Overview of Boston University Algorithms (PI: Allen Tannenbaum) =

At Boston University, we are broadly interested in a range of mathematical image analysis algorithms for segmentation, registration, diffusion-weighted MRI analysis, and statistical analysis. For many applications, we cast the problem in an energy minimization framework wherein we define a partial differential equation whose numeric solution corresponds to the desired algorithmic outcome. The following are many examples of PDE techniques applied to medical image analysis.

= Boston University Projects =

{| cellpadding="10" style="text-align:left;"

| | [[Image:toT1e1.png|200px|]]
| |

== [[Projects:RegistrationTBI|Multimodal Deformable Registration of Traumatic Brain Injury MR Volumes using Graphics Processing Units]] ==

Time-efficient processing and analysis of magnetic resonance imaging (MRI) volumes is desirable is for the neurocritical care and monitoring of traumatic brain injury (TBI) patients. An important problem of TBI neuroimaging data analysis is the task of co-registering MR volumes acquired using distinct sequences in the presence of widely variable pixel intensities that are due to the presence of pathology. Here we address this important and challenging problems using an implementation of multimodal deformable registration on graphics processing units (GPU). We follow a viscous fluid model framework and replace mutual information with the Bhattacharyya distance as the measure of similarity between image volumes. The proposed algorithm is implemented on a GPU and its robustness is illustrated using a longitudinal multimodal TBI dataset. [[Projects:RegistrationTBI|More...]]

|-

| | [[Image:MultiScaleHippoSegmentationHausdorf.png|200px]]
| |

== [[Projects:MultiScaleShapeSegmentation|Multi-scale Shape Representation and Segmentation With Applications to Radiotherapy]] ==

We present in this work a multiscale representation for shapes with arbitrary topology, and a method to segment the target organ/tissue from medical images having very low contrast with respect to surrounding regions using multiscale shape information and local image features. In a number of previous papers, shape knowledge was incorporated by first constructing a shape space from training data, and then constraining the segmentation process to be within the resulting shape space. However, such an approach has certain limitations including the fact that small scale shape variances may be overwhelmed by those on larger scale, and therefore the local shape information is lost. In this work, first we handle this problem by providing a multiscale shape representation using the wavelet transform. Consequently, the shape variances captured by the statistical learning step are also represented at various scales. In doing so, not only is the diversity of shape enriched, but also small scale changes are nicely captured. [[Projects:MultiScaleShapeSegmentation|More...]]

|-

| | [[Image:GT-SPD-img1.png|200px|]]
| |

== [[Projects:SoftPlaqueDetection|Soft Plaque Detection in CTA Imagery]] ==

The ability to detect and measure non-calciﬁed plaques (also known as soft plaques) may improve physicians’ ability to predict cardiac events. This work automatically detects soft plaques in CTA imagery using active contours driven by spatially localized probabilistic models. Plaques are identified by simultaneously segmenting the vessel from the inside-out and the outside-in using carefully chosen localized energies [[Projects:SoftPlaqueDetection|More...]]

<font color="red">'''New: '''</font> Soft Plaque Detection and Automatic Vessel Segmentation. PMMIA Workshop in MICCAI, Sep. 2009.
|-

| | [[Image:3D_Segmentation_LA.png|200px]]
| |

== [[Projects:SegmentationEndocardialWall|Segmentation of the Left Atrial Wall for Atrial Fibrillation Ablation Therapy]] ==

Magnetic resonance imaging (MRI) has been used for both pre- and and post-ablation assessment of the atrial wall. MRI can aid in selecting the right candidate for the ablation procedure and assessing post-ablation scar formations. Image processing techniques can be used for automatic segmentation of the atrial wall, which facilitates an accurate statistical assessment of the region. As a first step towards the general solution to the computer-assisted segmentation of the left atrial wall, in this research we propose a shape-based image segmentation framework to segment the endocardial wall of the left atrium.[[Projects:SegmentationEpicardialWall|More...]]

<font color="red">'''New: '''</font> Y. Gao, B. Gholami, R. S. MacLeod, J, Blauer, W. M. Haddad, and A. R. Tannenbaum, Segmentation of the Endocardial Wall of the Left Atrium using Local Region-Based Active Contours and Statistical Shape Learning, SPIE Medical Imaging, San Diego, CA, 2010.

|-

| | [[Image:Pain1.JPG|200px]]
| |

== [[Projects:PainAssessment|Agitation and Pain Assessment Using Digital Imaging]] ==

Pain assessment in patients who are unable to verbally
communicate with medical staff is a challenging problem
in patient critical care. The fundamental limitations in sedation
and pain assessment in the intensive care unit (ICU) stem
from subjective assessment criteria, rather than quantifiable,
measurable data for ICU sedation and analgesia. This often
results in poor quality and inconsistent treatment of patient
agitation and pain from nurse to nurse. Recent advancements in
pattern recognition techniques using a relevance vector machine
algorithm can assist medical staff in assessing sedation and pain
by constantly monitoring the patient and providing the clinician
with quantifiable data for ICU sedation. In this paper, we show
that the pain intensity assessment given by a computer classifier
has a strong correlation with the pain intensity assessed by
expert and non-expert human examiners.[[Projects:PainAssessment|More...]]

<font color="red">'''New: '''</font> B. Gholami, W. M. Haddad, and A. Tannenbaum, “Relevance Vector Machine Learning for Neonate Pain Intensity Assessment Using Digital Imaging,” IEEE Trans. Biomed. Eng., vol. 57, pp. 1457-1466.

B. Gholami, W. M. Haddad, and A. R. Tannenbaum, “Agitation and Pain Assessment Using Digital Imaging,” Proc. IEEE Eng. Med. Biolog. Conf., Minneapolis, MN, pp. 2176-2179, 2009 (Awarded National Institute of Biomedical Imaging and Bioengineering/National Institute of Health Student Travel Fellowship).

|-

| | [[Image:MultiObjSeg.png|200px|]]
| |

== [[RobustStatisticsSegmentation|Simultaneous Multiple Object Segmentation using Robust Statistics Features ]] ==

Multiple objects are segmented simultaneously using several interactive active contours based on the feature image which utilizes the robust statistics of the image. [[RobustStatisticsSegmentation|More...]]

|-

| | [[Image:ShapeBasePstSegSlicer.png|200px|]]
| |

== [[Projects:ProstateSegmentation|Prostate Segmentation]] ==

The 3D prostate MRI images are collected by collaborators at Queen’s University. With a little manual initialization, the algorithm provided the results give to the left. The method mainly uses Random Walk algorithm. [[Projects:ProstateSegmentation|More...]]

<font color="red">'''New: '''</font> Y. Gao, A. Tannenbaum; Shape based MRI prostate image segmentation using local information driven directional distance Bayesian method. SPIE Medical Imaging 2010.

|-

| | [[Image:ProstateRegSupineToProneInParaview.png|200px|]]
| |

== [[Projects:pfPtSetImgReg|Particle Filter Registration of Medical Imagery]] ==

3D volumetric image registration is performed. The method is based on registering the images through point sets, which is able to handle long distance between as well as registration between Supine and Prone pose prostate. [[Projects:pfPtSetImgReg|More...]]

<font color="red">'''New: '''</font> Y. Gao, R. Sandhu, G. Fichtinger, A. Tannenbaum; A coupled global registration and segmentation framework with application to magnetic resonance prostate imagery. IEEE TMI vol.29, pp1781, 2010
.

|-

| | [[Image:GT-DWI-Reorientation-1.jpg|200px]]
| |

== [[Projects:DWIReorientation|Re-Orientation Approach for Segmentation of DW-MRI]] ==

This work proposes a methodology to segment tubular fiber bundles from diffusion weighted magnetic resonance images (DW-MRI). Segmentation is simplified by locally reorienting diffusion information based on large-scale fiber bundle geometry. [[Projects:DWIReorientation|More...]]

<font color="red">'''New: '''</font> Near-tubular fiber bundle segmentation for diffusion weighted imaging: segmentation through frame reorientation. Neuroimage, Mar 2009.

|-

| | [[Image:GTTubSurfaceSeg-Img1.png|200px]]
| |

== [[Projects:TubularSurfaceSegmentation|Tubular Surface Segmentation Framework]] ==

We have proposed a new model for tubular surfaces that transforms the problem of detecting a surface in 3D space, to detecting a curve in 4D space. Besides allowing us to impose a "soft" tubular shape prior, this also leads to computational efficiency over conventional surface segmentation approaches. [[Projects:TubularSurfaceSegmentation|More...]]

<font color="red">'''New: '''</font> V. Mohan, G. Sundaramoorthi, M. Kubicki and A. Tannenbaum. Tubular Surface Evolution for Segmentation of the Cingulum Bundle From DW-MRI. September 2008. Proceedings of the Second Workshop on Mathematical Foundations of Computational Anatomy (MFCA'08), Int Conf Med Image Comput Comput Assist Interv. 2008.

<font color="red">'''New: '''</font> V. Mohan, G. Sundaramoorthi, A. Stillman and A. Tannenbaum. Vessel Segmentation with Automatic Centerline Extraction using Tubular Surface Segmentation. September 2009. Proceedings of the Workshop on Cardiac Interventional Imaging and Biophysical Modelling (CI2BM'09), Int Conf Med Image Comput Comput Assist Interv. 2009.

<font color="red">'''New: '''</font> V. Mohan, G. Sundaramoorthi and A. Tannenbaum. Tubular Surface Segmentation for Extracting Anatomical Structures from Medical Imagery (in submission). IEEE Transactions on Medical Imaging.

|-

| | [[Image:GT-PopStudyVis OnCBs Case19-View2.jpg|200px]]
| |

== [[Projects:TubularSurfaceSegmentationPopStudy|Group Study on DW-MRI using the Tubular Surface Model]] ==

We have proposed a new framework for performing group studies on DW-MRI data sets using the Tubular Surface Model of Mohan et al. We successfully apply this framework to discriminating schizophrenic cases from normal controls, as well as towards visualizing the regions of the Cingulum Bundle that are affected by Schizophrenia. [[Projects:TubularSurfaceSegmentationPopStudy|More...]]

<font color="red">'''New: '''</font> V. Mohan, G. Sundaramoorthi, M. Kubicki, D. Terry and A. Tannenbaum. Population Analysis of the Cingulum Bundle using the Tubular Surface Model for Schizophrenia Detection. SPIE Medical Imaging 2010.

<font color="red">'''New: '''</font> V. Mohan, G. Sundaramoorthi, M. Kubicki and A. Tannenbaum. Population Analysis of neural fiber bundles towards schizophrenia detection and characterization, using the Tubular Surface model. Neuroimage (in preparation)

|-

| | [[Image:Model3D_upTrans.png|200px]]
| |

== [[Projects:MGH-HeadAndNeck-RT|Adaptive Radiotherapy for head, neck and thorax]] ==

We proposed an algorithm to include prior knowledge in previously segmented anatomical structures to help in the segmentation of the next structure. This will add enough prior information to allow the Graph Cuts algorithm to segment structures with fuzzy boundaries. [[Projects:MGH-HeadAndNeck-RT|More...]]

<font color="red">'''New: '''</font> I. Kolesov, V. Mohan, G. Sharp and A. Tannenbaum. Coupled Segmentation for Anatomical Structures by Combining Shape and Relational Spatial Information. MTNS 2010.

|-

| | [[Image:Circle seg.PNG|200px|]]
| |

== [[Projects:KPCASegmentation|Kernel PCA for Segmentation]] ==

Segmentation performances using active contours can be drastically improved if the possible shapes of the object of interest are learnt. The goal of this work is to use Kernel PCA to learn shape priors. Kernel PCA allows for learning non linear dependencies in data sets, leading to more robust shape priors. [[Projects:KPCASegmentation|More...]]

<font color="red">'''New: '''</font> S. Dambreville, Y. Rathi, and A. Tannenbaum. A Framework for Image Segmentation using Image Shape Models and Kernel PCA Shape Priors. IEEE Trans Pattern Anal Mach Intell. 2008 Aug;30(8):1385-99

|-
| | [[Image:ZoomedResultWithModel.png|200px]]
| |

== [[Projects:GeodesicTractographySegmentation|Geodesic Tractography Segmentation]] ==

In this work, we provide an energy minimization framework which allows one to find fiber tracts and volumetric fiber bundles in brain diffusion-weighted MRI (DW-MRI). [[Projects:GeodesicTractographySegmentation|More...]]

<font color="red">'''New: '''</font> J. Melonakos, E. Pichon, S. Angenet, and A. Tannenbaum. Finsler Active Contours. IEEE Transactions on Pattern Analysis and Machine Intelligence, March 2008, Vol 30, Num 3.

|-

| | [[Image:P1_small.png|200px|]]
| |

== [[Projects:LabelSpace|Label Space: A Coupled Multi-Shape Representation]] ==

Many techniques for multi-shape representation may often develop inaccuracies stemming from either approximations or inherent variation. Label space is an implicit representation that offers unbiased algebraic manipulation and natural expression of label uncertainty. We demonstrate smoothing and registration on multi-label brain MRI. [[Projects:LabelSpace|More...]]

<font color="red">'''New: '''</font> J. Malcolm, Y. Rathi, A. Tannenbaum. "Label Space: A Multi-Object Shape Representation." In Combinatorial Image Analysis, 2008.

|-

| | [[Image:BasePair3DModel.JPG|200px|]]
| |

== [[Projects:NonParametricClustering|Non Parametric Clustering for Biomolecular Structural Analysis]] ==

High accuracy imaging and image processing techniques allow for collecting structural information of biomolecules with atomistic accuracy. Direct interpretation of the dynamics and the functionality of these structures with physical models, is yet to be developed. Clustering of molecular conformations into classes seems to be the first stage in recovering the formation and the functionality of these molecules. [[Projects:NonParametricClustering|More...]]

<font color="red">'''New: '''</font> E. Hershkovits, A. Tannenbaum, and R. Tannenbaum. Adsorption of Block Copolymers from Selective Solvents on Curved Surfaces. Macromolecules. 2008.

|-

| | [[Image:TruckInitialization.png|200px|]]
| |

== [[Projects:PointSetRigidRegistration|Point Set Rigid Registration]] ==

In this work, we propose a particle filtering approach for the problem of registering two point sets that differ by
a rigid body transformation. Experimental results are provided that demonstrate the robustness of the algorithm to initialization, noise, missing structures or differing point densities in each sets, on challenging 2D and 3D registration tasks. [[Projects:PointSetRigidRegistration|More...]]

<font color="red">'''New: '''</font> R. Sandhu, S. Dambreville, A. Tannenbaum. Particle Filtering for Registration of 2D and 3D Point Sets with Stochastic Dynamics. In CVPR, 2008.

|-

| | [[Image:Results brain sag.JPG|200px]]
| |

== [[Projects:OptimalMassTransportRegistration|Optimal Mass Transport Registration]] ==

The goal of this project is to implement a computationaly efficient Elastic/Non-rigid Registration algorithm based on the Monge-Kantorovich theory of optimal mass transport for 3D Medical Imagery. Our technique is based on Multigrid and Multiresolution techniques. This method is particularly useful because it is parameter free and utilizes all of the grayscale data in the image pairs in a symmetric fashion and no landmarks need to be specified for correspondence. [[Projects:OptimalMassTransportRegistration|More...]]

<font color="red">'''New: '''</font> Eldad Haber, Tauseef Rehman, and Allen Tannenbaum. An Efficient Numerical Method for the Solution of the L2 Optimal Mass Transfer Problem. In submission - SIAM Journal of Scientific Computing, 2009.

<font color="red">'''New: '''</font> Tauseef Rehman, Eldad Haber, Gallagher Pryor, and Allen Tannenbaum. Fast Optimal Mass Transport for 2D Image Registration and Morphing. Accepted for - Elsevier Journal of Image and Vision Computing, 2009.

|-

| | [[Image:Gatech caudateBands.PNG|200px]]
| |

== [[Projects:MultiscaleShapeSegmentation|Multiscale Shape Segmentation Techniques]] ==

To represent multiscale variations in a shape population in order to drive the segmentation of deep brain structures, such as the caudate nucleus or the hippocampus. [[Projects:MultiscaleShapeSegmentation|More...]]

|-

| | [[Image:Caudate Nucleus Denoising.JPG|200px|]]
| |

== [[Projects:WaveletShrinkage|Wavelet Shrinkage for Shape Analysis]] ==

Shape analysis has become a topic of interest in medical imaging since local variations of a shape could carry relevant information about a disease that may affect only a portion of an organ. We developed a novel wavelet-based denoising and compression statistical model for 3D shapes. [[Projects:WaveletShrinkage|More...]]

|-

| | [[Image:Basis membership.png|200px]]
| |

== [[Projects:MultiscaleShapeAnalysis|Multiscale Shape Analysis]] ==

We present a novel method of statistical surface-based morphometry based on the use of non-parametric permutation tests and a spherical wavelet (SWC) shape representation. [[Projects:MultiscaleShapeAnalysis|More...]]

|-

| | [[Image:Dlpfc1.jpg|200px|]]
| |

== [[Projects:RuleBasedDLPFCSegmentation|Rule-Based DLPFC Segmentation]] ==

In this work, we provide software to semi-automate the implementation of segmentation procedures based on expert neuroanatomist rules for the dorsolateral prefrontal cortex. [[Projects:RuleBasedDLPFCSegmentation|More...]]

|-

| | [[Image:Striatum1.png|200px|]]
| |

== [[Projects:RuleBasedStriatumSegmentation|Rule-Based Striatum Segmentation]] ==

In this work, we provide software to semi-automate the implementation of segmentation procedures based on expert neuroanatomist rules for the striatum. [[Projects:RuleBasedStriatumSegmentation|More...]]

|-

| | [[Image:Brain-flat.PNG|200px]]
| |

== [[Projects:ConformalFlatteningRegistration|Conformal Flattening (inactive)]] ==

The goal of this project is for better visualizing and computation of neural activity from fMRI brain imagery. Also, with this technique, shapes can be mapped to shperes for shape analysis, registration or other purposes. Our technique is based on conformal mappings which map genus-zero surface: in fmri case cortical or other surfaces, onto a sphere in an angle preserving manner. [[Projects:ConformalFlatteningRegistration|More...]]

|-

| | [[Image:Fig1yan.PNG|200px|]]
| |

== [[Projects:BloodVesselSegmentation|Blood Vessel Segmentation]] ==

The goal of this work is to develop blood vessel segmentation techniques for 3D MRI and CT data. The methods have been applied to coronary arteries and portal veins, with promising results. [[Projects:BloodVesselSegmentation|More...]]

<font color="red">'''New: '''</font> V.Mohan, G. Sundaramoorthi, A. Stillman and A. Tannenbaum. Vessel Segmentation with Automatic Centerline Extraction Using Tubular Tree Segmentation. CI2BM at MICCAI 2009, September 2009.

|-

| | [[Image:Fig67.png|200px|]]
| |

== [[Projects:KnowledgeBasedBayesianSegmentation|Knowledge-Based Bayesian Segmentation]] ==

This ITK filter is a segmentation algorithm that utilizes Bayes's Rule along with an affine-invariant anisotropic smoothing filter. [[Projects:KnowledgeBasedBayesianSegmentation|More...]]

|-

| | [[Image:Stochastic-snake.png|200px|]]
| |

== [[Projects:StochasticMethodsSegmentation|Stochastic Methods for Segmentation]] ==

New stochastic methods for implementing curvature driven flows for various medical tasks such as segmentation. [[Projects:StochasticMethodsSegmentation|More...]]

|-

| | [[Image:GT-SulciOutlining1.jpg|200px]]
| |

== [[Projects:SulciOutlining|Automatic Outlining of sulci on the brain surface]] ==

We present a method to automatically extract certain key features on a surface. We apply this technique to outline sulci on the cortical surface of a brain. [[Projects:SulciOutlining|More...]]

|-

| | [[Image:Table1.png|200px|]]
| |

== [[Projects:KPCA_LLE_KLLE_ShapeAnalysis|KPCA, LLE, KLLE Shape Analysis]] ==

The goal of this work is to study and compare shape learning techniques. The techniques considered are Linear Principal Components Analysis (PCA), Kernel PCA, Locally Linear Embedding (LLE) and Kernel LLE. [[Projects:KPCA_LLE_KLLE_ShapeAnalysis|More...]]

|-

| | [[Image:Gatech SlicerModel2.jpg|200px]]
| |

== [[Projects:StatisticalSegmentationSlicer2|Statistical/PDE Methods using Fast Marching for Segmentation]] ==

This Fast Marching based flow was added to Slicer 2. [[Projects:StatisticalSegmentationSlicer2|More...]]

|}

Algorithm:BU

2011-10-17T15:12:24Z

Yflou: /* Boston University Projects */

Back to [[Algorithm:Main|NA-MIC Algorithms]]
__NOTOC__
= Overview of Boston University Algorithms (PI: Allen Tannenbaum) =

At Boston University, we are broadly interested in a range of mathematical image analysis algorithms for segmentation, registration, diffusion-weighted MRI analysis, and statistical analysis. For many applications, we cast the problem in an energy minimization framework wherein we define a partial differential equation whose numeric solution corresponds to the desired algorithmic outcome. The following are many examples of PDE techniques applied to medical image analysis.

= Boston University Projects =

{| cellpadding="10" style="text-align:left;"

| | [[Image:toT1e1.png|200px|]]
| |

== [[Projects:RegistrationTBI|Multimodal Deformable Registration of Traumatic Brain Injury MR Volumes using Graphics Processing Units]] ==

Time-efficient processing and analysis of magnetic resonance imaging (MRI) volumes can be critical for both medical diagnosis as well as for the formulation of acute treatment strategies. One context where such efficiency is desirable is for the neurocritical care and monitoring of traumatic brain injury (TBI) patients. An important problem of TBI neuroimaging data analysis is the task of co-registering MR volumes acquired using distinct sequences in the presence of widely variable pixel intensities that are due to the presence of pathology. Here we address this important and challenging problems using an implementation of multimodal deformable registration on graphics processing units (GPU). We follow a viscous fluid model framework and replace mutual information with the Bhattacharyya distance as the measure of similarity between image volumes. The proposed algorithm is implemented on a GPU and its robustness is illustrated using a longitudinal multimodal TBI dataset. [[Projects:SoftPlaqueDetection|More...]]

|-

| | [[Image:MultiScaleHippoSegmentationHausdorf.png|200px]]
| |

== [[Projects:MultiScaleShapeSegmentation|Multi-scale Shape Representation and Segmentation With Applications to Radiotherapy]] ==

We present in this work a multiscale representation for shapes with arbitrary topology, and a method to segment the target organ/tissue from medical images having very low contrast with respect to surrounding regions using multiscale shape information and local image features. In a number of previous papers, shape knowledge was incorporated by first constructing a shape space from training data, and then constraining the segmentation process to be within the resulting shape space. However, such an approach has certain limitations including the fact that small scale shape variances may be overwhelmed by those on larger scale, and therefore the local shape information is lost. In this work, first we handle this problem by providing a multiscale shape representation using the wavelet transform. Consequently, the shape variances captured by the statistical learning step are also represented at various scales. In doing so, not only is the diversity of shape enriched, but also small scale changes are nicely captured. [[Projects:MultiScaleShapeSegmentation|More...]]

|-

| | [[Image:GT-SPD-img1.png|200px|]]
| |

== [[Projects:SoftPlaqueDetection|Soft Plaque Detection in CTA Imagery]] ==

The ability to detect and measure non-calciﬁed plaques (also known as soft plaques) may improve physicians’ ability to predict cardiac events. This work automatically detects soft plaques in CTA imagery using active contours driven by spatially localized probabilistic models. Plaques are identified by simultaneously segmenting the vessel from the inside-out and the outside-in using carefully chosen localized energies [[Projects:SoftPlaqueDetection|More...]]

<font color="red">'''New: '''</font> Soft Plaque Detection and Automatic Vessel Segmentation. PMMIA Workshop in MICCAI, Sep. 2009.
|-

| | [[Image:3D_Segmentation_LA.png|200px]]
| |

== [[Projects:SegmentationEndocardialWall|Segmentation of the Left Atrial Wall for Atrial Fibrillation Ablation Therapy]] ==

Magnetic resonance imaging (MRI) has been used for both pre- and and post-ablation assessment of the atrial wall. MRI can aid in selecting the right candidate for the ablation procedure and assessing post-ablation scar formations. Image processing techniques can be used for automatic segmentation of the atrial wall, which facilitates an accurate statistical assessment of the region. As a first step towards the general solution to the computer-assisted segmentation of the left atrial wall, in this research we propose a shape-based image segmentation framework to segment the endocardial wall of the left atrium.[[Projects:SegmentationEpicardialWall|More...]]

<font color="red">'''New: '''</font> Y. Gao, B. Gholami, R. S. MacLeod, J, Blauer, W. M. Haddad, and A. R. Tannenbaum, Segmentation of the Endocardial Wall of the Left Atrium using Local Region-Based Active Contours and Statistical Shape Learning, SPIE Medical Imaging, San Diego, CA, 2010.

|-

| | [[Image:Pain1.JPG|200px]]
| |

== [[Projects:PainAssessment|Agitation and Pain Assessment Using Digital Imaging]] ==

Pain assessment in patients who are unable to verbally
communicate with medical staff is a challenging problem
in patient critical care. The fundamental limitations in sedation
and pain assessment in the intensive care unit (ICU) stem
from subjective assessment criteria, rather than quantifiable,
measurable data for ICU sedation and analgesia. This often
results in poor quality and inconsistent treatment of patient
agitation and pain from nurse to nurse. Recent advancements in
pattern recognition techniques using a relevance vector machine
algorithm can assist medical staff in assessing sedation and pain
by constantly monitoring the patient and providing the clinician
with quantifiable data for ICU sedation. In this paper, we show
that the pain intensity assessment given by a computer classifier
has a strong correlation with the pain intensity assessed by
expert and non-expert human examiners.[[Projects:PainAssessment|More...]]

<font color="red">'''New: '''</font> B. Gholami, W. M. Haddad, and A. Tannenbaum, “Relevance Vector Machine Learning for Neonate Pain Intensity Assessment Using Digital Imaging,” IEEE Trans. Biomed. Eng., vol. 57, pp. 1457-1466.

B. Gholami, W. M. Haddad, and A. R. Tannenbaum, “Agitation and Pain Assessment Using Digital Imaging,” Proc. IEEE Eng. Med. Biolog. Conf., Minneapolis, MN, pp. 2176-2179, 2009 (Awarded National Institute of Biomedical Imaging and Bioengineering/National Institute of Health Student Travel Fellowship).

|-

| | [[Image:MultiObjSeg.png|200px|]]
| |

== [[RobustStatisticsSegmentation|Simultaneous Multiple Object Segmentation using Robust Statistics Features ]] ==

Multiple objects are segmented simultaneously using several interactive active contours based on the feature image which utilizes the robust statistics of the image. [[RobustStatisticsSegmentation|More...]]

|-

| | [[Image:ShapeBasePstSegSlicer.png|200px|]]
| |

== [[Projects:ProstateSegmentation|Prostate Segmentation]] ==

The 3D prostate MRI images are collected by collaborators at Queen’s University. With a little manual initialization, the algorithm provided the results give to the left. The method mainly uses Random Walk algorithm. [[Projects:ProstateSegmentation|More...]]

<font color="red">'''New: '''</font> Y. Gao, A. Tannenbaum; Shape based MRI prostate image segmentation using local information driven directional distance Bayesian method. SPIE Medical Imaging 2010.

|-

| | [[Image:ProstateRegSupineToProneInParaview.png|200px|]]
| |

== [[Projects:pfPtSetImgReg|Particle Filter Registration of Medical Imagery]] ==

3D volumetric image registration is performed. The method is based on registering the images through point sets, which is able to handle long distance between as well as registration between Supine and Prone pose prostate. [[Projects:pfPtSetImgReg|More...]]

<font color="red">'''New: '''</font> Y. Gao, R. Sandhu, G. Fichtinger, A. Tannenbaum; A coupled global registration and segmentation framework with application to magnetic resonance prostate imagery. IEEE TMI vol.29, pp1781, 2010
.

|-

| | [[Image:GT-DWI-Reorientation-1.jpg|200px]]
| |

== [[Projects:DWIReorientation|Re-Orientation Approach for Segmentation of DW-MRI]] ==

This work proposes a methodology to segment tubular fiber bundles from diffusion weighted magnetic resonance images (DW-MRI). Segmentation is simplified by locally reorienting diffusion information based on large-scale fiber bundle geometry. [[Projects:DWIReorientation|More...]]

<font color="red">'''New: '''</font> Near-tubular fiber bundle segmentation for diffusion weighted imaging: segmentation through frame reorientation. Neuroimage, Mar 2009.

|-

| | [[Image:GTTubSurfaceSeg-Img1.png|200px]]
| |

== [[Projects:TubularSurfaceSegmentation|Tubular Surface Segmentation Framework]] ==

We have proposed a new model for tubular surfaces that transforms the problem of detecting a surface in 3D space, to detecting a curve in 4D space. Besides allowing us to impose a "soft" tubular shape prior, this also leads to computational efficiency over conventional surface segmentation approaches. [[Projects:TubularSurfaceSegmentation|More...]]

<font color="red">'''New: '''</font> V. Mohan, G. Sundaramoorthi, M. Kubicki and A. Tannenbaum. Tubular Surface Evolution for Segmentation of the Cingulum Bundle From DW-MRI. September 2008. Proceedings of the Second Workshop on Mathematical Foundations of Computational Anatomy (MFCA'08), Int Conf Med Image Comput Comput Assist Interv. 2008.

<font color="red">'''New: '''</font> V. Mohan, G. Sundaramoorthi, A. Stillman and A. Tannenbaum. Vessel Segmentation with Automatic Centerline Extraction using Tubular Surface Segmentation. September 2009. Proceedings of the Workshop on Cardiac Interventional Imaging and Biophysical Modelling (CI2BM'09), Int Conf Med Image Comput Comput Assist Interv. 2009.

<font color="red">'''New: '''</font> V. Mohan, G. Sundaramoorthi and A. Tannenbaum. Tubular Surface Segmentation for Extracting Anatomical Structures from Medical Imagery (in submission). IEEE Transactions on Medical Imaging.

|-

| | [[Image:GT-PopStudyVis OnCBs Case19-View2.jpg|200px]]
| |

== [[Projects:TubularSurfaceSegmentationPopStudy|Group Study on DW-MRI using the Tubular Surface Model]] ==

We have proposed a new framework for performing group studies on DW-MRI data sets using the Tubular Surface Model of Mohan et al. We successfully apply this framework to discriminating schizophrenic cases from normal controls, as well as towards visualizing the regions of the Cingulum Bundle that are affected by Schizophrenia. [[Projects:TubularSurfaceSegmentationPopStudy|More...]]

<font color="red">'''New: '''</font> V. Mohan, G. Sundaramoorthi, M. Kubicki, D. Terry and A. Tannenbaum. Population Analysis of the Cingulum Bundle using the Tubular Surface Model for Schizophrenia Detection. SPIE Medical Imaging 2010.

<font color="red">'''New: '''</font> V. Mohan, G. Sundaramoorthi, M. Kubicki and A. Tannenbaum. Population Analysis of neural fiber bundles towards schizophrenia detection and characterization, using the Tubular Surface model. Neuroimage (in preparation)

|-

| | [[Image:Model3D_upTrans.png|200px]]
| |

== [[Projects:MGH-HeadAndNeck-RT|Adaptive Radiotherapy for head, neck and thorax]] ==

We proposed an algorithm to include prior knowledge in previously segmented anatomical structures to help in the segmentation of the next structure. This will add enough prior information to allow the Graph Cuts algorithm to segment structures with fuzzy boundaries. [[Projects:MGH-HeadAndNeck-RT|More...]]

<font color="red">'''New: '''</font> I. Kolesov, V. Mohan, G. Sharp and A. Tannenbaum. Coupled Segmentation for Anatomical Structures by Combining Shape and Relational Spatial Information. MTNS 2010.

|-

| | [[Image:Circle seg.PNG|200px|]]
| |

== [[Projects:KPCASegmentation|Kernel PCA for Segmentation]] ==

Segmentation performances using active contours can be drastically improved if the possible shapes of the object of interest are learnt. The goal of this work is to use Kernel PCA to learn shape priors. Kernel PCA allows for learning non linear dependencies in data sets, leading to more robust shape priors. [[Projects:KPCASegmentation|More...]]

<font color="red">'''New: '''</font> S. Dambreville, Y. Rathi, and A. Tannenbaum. A Framework for Image Segmentation using Image Shape Models and Kernel PCA Shape Priors. IEEE Trans Pattern Anal Mach Intell. 2008 Aug;30(8):1385-99

|-
| | [[Image:ZoomedResultWithModel.png|200px]]
| |

== [[Projects:GeodesicTractographySegmentation|Geodesic Tractography Segmentation]] ==

In this work, we provide an energy minimization framework which allows one to find fiber tracts and volumetric fiber bundles in brain diffusion-weighted MRI (DW-MRI). [[Projects:GeodesicTractographySegmentation|More...]]

<font color="red">'''New: '''</font> J. Melonakos, E. Pichon, S. Angenet, and A. Tannenbaum. Finsler Active Contours. IEEE Transactions on Pattern Analysis and Machine Intelligence, March 2008, Vol 30, Num 3.

|-

| | [[Image:P1_small.png|200px|]]
| |

== [[Projects:LabelSpace|Label Space: A Coupled Multi-Shape Representation]] ==

Many techniques for multi-shape representation may often develop inaccuracies stemming from either approximations or inherent variation. Label space is an implicit representation that offers unbiased algebraic manipulation and natural expression of label uncertainty. We demonstrate smoothing and registration on multi-label brain MRI. [[Projects:LabelSpace|More...]]

<font color="red">'''New: '''</font> J. Malcolm, Y. Rathi, A. Tannenbaum. "Label Space: A Multi-Object Shape Representation." In Combinatorial Image Analysis, 2008.

|-

| | [[Image:BasePair3DModel.JPG|200px|]]
| |

== [[Projects:NonParametricClustering|Non Parametric Clustering for Biomolecular Structural Analysis]] ==

High accuracy imaging and image processing techniques allow for collecting structural information of biomolecules with atomistic accuracy. Direct interpretation of the dynamics and the functionality of these structures with physical models, is yet to be developed. Clustering of molecular conformations into classes seems to be the first stage in recovering the formation and the functionality of these molecules. [[Projects:NonParametricClustering|More...]]

<font color="red">'''New: '''</font> E. Hershkovits, A. Tannenbaum, and R. Tannenbaum. Adsorption of Block Copolymers from Selective Solvents on Curved Surfaces. Macromolecules. 2008.

|-

| | [[Image:TruckInitialization.png|200px|]]
| |

== [[Projects:PointSetRigidRegistration|Point Set Rigid Registration]] ==

In this work, we propose a particle filtering approach for the problem of registering two point sets that differ by
a rigid body transformation. Experimental results are provided that demonstrate the robustness of the algorithm to initialization, noise, missing structures or differing point densities in each sets, on challenging 2D and 3D registration tasks. [[Projects:PointSetRigidRegistration|More...]]

<font color="red">'''New: '''</font> R. Sandhu, S. Dambreville, A. Tannenbaum. Particle Filtering for Registration of 2D and 3D Point Sets with Stochastic Dynamics. In CVPR, 2008.

|-

| | [[Image:Results brain sag.JPG|200px]]
| |

== [[Projects:OptimalMassTransportRegistration|Optimal Mass Transport Registration]] ==

The goal of this project is to implement a computationaly efficient Elastic/Non-rigid Registration algorithm based on the Monge-Kantorovich theory of optimal mass transport for 3D Medical Imagery. Our technique is based on Multigrid and Multiresolution techniques. This method is particularly useful because it is parameter free and utilizes all of the grayscale data in the image pairs in a symmetric fashion and no landmarks need to be specified for correspondence. [[Projects:OptimalMassTransportRegistration|More...]]

<font color="red">'''New: '''</font> Eldad Haber, Tauseef Rehman, and Allen Tannenbaum. An Efficient Numerical Method for the Solution of the L2 Optimal Mass Transfer Problem. In submission - SIAM Journal of Scientific Computing, 2009.

<font color="red">'''New: '''</font> Tauseef Rehman, Eldad Haber, Gallagher Pryor, and Allen Tannenbaum. Fast Optimal Mass Transport for 2D Image Registration and Morphing. Accepted for - Elsevier Journal of Image and Vision Computing, 2009.

|-

| | [[Image:Gatech caudateBands.PNG|200px]]
| |

== [[Projects:MultiscaleShapeSegmentation|Multiscale Shape Segmentation Techniques]] ==

To represent multiscale variations in a shape population in order to drive the segmentation of deep brain structures, such as the caudate nucleus or the hippocampus. [[Projects:MultiscaleShapeSegmentation|More...]]

|-

| | [[Image:Caudate Nucleus Denoising.JPG|200px|]]
| |

== [[Projects:WaveletShrinkage|Wavelet Shrinkage for Shape Analysis]] ==

Shape analysis has become a topic of interest in medical imaging since local variations of a shape could carry relevant information about a disease that may affect only a portion of an organ. We developed a novel wavelet-based denoising and compression statistical model for 3D shapes. [[Projects:WaveletShrinkage|More...]]

|-

| | [[Image:Basis membership.png|200px]]
| |

== [[Projects:MultiscaleShapeAnalysis|Multiscale Shape Analysis]] ==

We present a novel method of statistical surface-based morphometry based on the use of non-parametric permutation tests and a spherical wavelet (SWC) shape representation. [[Projects:MultiscaleShapeAnalysis|More...]]

|-

| | [[Image:Dlpfc1.jpg|200px|]]
| |

== [[Projects:RuleBasedDLPFCSegmentation|Rule-Based DLPFC Segmentation]] ==

In this work, we provide software to semi-automate the implementation of segmentation procedures based on expert neuroanatomist rules for the dorsolateral prefrontal cortex. [[Projects:RuleBasedDLPFCSegmentation|More...]]

|-

| | [[Image:Striatum1.png|200px|]]
| |

== [[Projects:RuleBasedStriatumSegmentation|Rule-Based Striatum Segmentation]] ==

In this work, we provide software to semi-automate the implementation of segmentation procedures based on expert neuroanatomist rules for the striatum. [[Projects:RuleBasedStriatumSegmentation|More...]]

|-

| | [[Image:Brain-flat.PNG|200px]]
| |

== [[Projects:ConformalFlatteningRegistration|Conformal Flattening (inactive)]] ==

The goal of this project is for better visualizing and computation of neural activity from fMRI brain imagery. Also, with this technique, shapes can be mapped to shperes for shape analysis, registration or other purposes. Our technique is based on conformal mappings which map genus-zero surface: in fmri case cortical or other surfaces, onto a sphere in an angle preserving manner. [[Projects:ConformalFlatteningRegistration|More...]]

|-

| | [[Image:Fig1yan.PNG|200px|]]
| |

== [[Projects:BloodVesselSegmentation|Blood Vessel Segmentation]] ==

The goal of this work is to develop blood vessel segmentation techniques for 3D MRI and CT data. The methods have been applied to coronary arteries and portal veins, with promising results. [[Projects:BloodVesselSegmentation|More...]]

<font color="red">'''New: '''</font> V.Mohan, G. Sundaramoorthi, A. Stillman and A. Tannenbaum. Vessel Segmentation with Automatic Centerline Extraction Using Tubular Tree Segmentation. CI2BM at MICCAI 2009, September 2009.

|-

| | [[Image:Fig67.png|200px|]]
| |

== [[Projects:KnowledgeBasedBayesianSegmentation|Knowledge-Based Bayesian Segmentation]] ==

This ITK filter is a segmentation algorithm that utilizes Bayes's Rule along with an affine-invariant anisotropic smoothing filter. [[Projects:KnowledgeBasedBayesianSegmentation|More...]]

|-

| | [[Image:Stochastic-snake.png|200px|]]
| |

== [[Projects:StochasticMethodsSegmentation|Stochastic Methods for Segmentation]] ==

New stochastic methods for implementing curvature driven flows for various medical tasks such as segmentation. [[Projects:StochasticMethodsSegmentation|More...]]

|-

| | [[Image:GT-SulciOutlining1.jpg|200px]]
| |

== [[Projects:SulciOutlining|Automatic Outlining of sulci on the brain surface]] ==

We present a method to automatically extract certain key features on a surface. We apply this technique to outline sulci on the cortical surface of a brain. [[Projects:SulciOutlining|More...]]

|-

| | [[Image:Table1.png|200px|]]
| |

== [[Projects:KPCA_LLE_KLLE_ShapeAnalysis|KPCA, LLE, KLLE Shape Analysis]] ==

The goal of this work is to study and compare shape learning techniques. The techniques considered are Linear Principal Components Analysis (PCA), Kernel PCA, Locally Linear Embedding (LLE) and Kernel LLE. [[Projects:KPCA_LLE_KLLE_ShapeAnalysis|More...]]

|-

| | [[Image:Gatech SlicerModel2.jpg|200px]]
| |

== [[Projects:StatisticalSegmentationSlicer2|Statistical/PDE Methods using Fast Marching for Segmentation]] ==

This Fast Marching based flow was added to Slicer 2. [[Projects:StatisticalSegmentationSlicer2|More...]]

|}

File:ToT1e1.png

2011-10-17T15:11:42Z

Yflou:

Algorithm:BU

2011-10-17T15:05:32Z

Yflou:

Back to [[Algorithm:Main|NA-MIC Algorithms]]
__NOTOC__
= Overview of Boston University Algorithms (PI: Allen Tannenbaum) =

At Boston University, we are broadly interested in a range of mathematical image analysis algorithms for segmentation, registration, diffusion-weighted MRI analysis, and statistical analysis. For many applications, we cast the problem in an energy minimization framework wherein we define a partial differential equation whose numeric solution corresponds to the desired algorithmic outcome. The following are many examples of PDE techniques applied to medical image analysis.

= Boston University Projects =

{| cellpadding="10" style="text-align:left;"

| | [[Image:toT1e1.pdf|200px|]]
| |

== [[Projects:RegistrationTBI|Multimodal Deformable Registration of Traumatic Brain Injury MR Volumes using Graphics Processing Units]] ==

Time-efficient processing and analysis of magnetic resonance imaging (MRI) volumes can be critical for both medical diagnosis as well as for the formulation of acute treatment strategies. One context where such efficiency is desirable is for the neurocritical care and monitoring of traumatic brain injury (TBI) patients. An important problem of TBI neuroimaging data analysis is the task of co-registering MR volumes acquired using distinct sequences in the presence of widely variable pixel intensities that are due to the presence of pathology. Here we address this important and challenging problems using an implementation of multimodal deformable registration on graphics processing units (GPU). We follow a viscous fluid model framework and replace mutual information with the Bhattacharyya distance as the measure of similarity between image volumes. The proposed algorithm is implemented on a GPU and its robustness is illustrated using a longitudinal multimodal TBI dataset. [[Projects:SoftPlaqueDetection|More...]]

|-

| | [[Image:MultiScaleHippoSegmentationHausdorf.png|200px]]
| |

== [[Projects:MultiScaleShapeSegmentation|Multi-scale Shape Representation and Segmentation With Applications to Radiotherapy]] ==

We present in this work a multiscale representation for shapes with arbitrary topology, and a method to segment the target organ/tissue from medical images having very low contrast with respect to surrounding regions using multiscale shape information and local image features. In a number of previous papers, shape knowledge was incorporated by first constructing a shape space from training data, and then constraining the segmentation process to be within the resulting shape space. However, such an approach has certain limitations including the fact that small scale shape variances may be overwhelmed by those on larger scale, and therefore the local shape information is lost. In this work, first we handle this problem by providing a multiscale shape representation using the wavelet transform. Consequently, the shape variances captured by the statistical learning step are also represented at various scales. In doing so, not only is the diversity of shape enriched, but also small scale changes are nicely captured. [[Projects:MultiScaleShapeSegmentation|More...]]

|-

| | [[Image:GT-SPD-img1.png|200px|]]
| |

== [[Projects:SoftPlaqueDetection|Soft Plaque Detection in CTA Imagery]] ==

The ability to detect and measure non-calciﬁed plaques (also known as soft plaques) may improve physicians’ ability to predict cardiac events. This work automatically detects soft plaques in CTA imagery using active contours driven by spatially localized probabilistic models. Plaques are identified by simultaneously segmenting the vessel from the inside-out and the outside-in using carefully chosen localized energies [[Projects:SoftPlaqueDetection|More...]]

<font color="red">'''New: '''</font> Soft Plaque Detection and Automatic Vessel Segmentation. PMMIA Workshop in MICCAI, Sep. 2009.
|-

| | [[Image:3D_Segmentation_LA.png|200px]]
| |

== [[Projects:SegmentationEndocardialWall|Segmentation of the Left Atrial Wall for Atrial Fibrillation Ablation Therapy]] ==

Magnetic resonance imaging (MRI) has been used for both pre- and and post-ablation assessment of the atrial wall. MRI can aid in selecting the right candidate for the ablation procedure and assessing post-ablation scar formations. Image processing techniques can be used for automatic segmentation of the atrial wall, which facilitates an accurate statistical assessment of the region. As a first step towards the general solution to the computer-assisted segmentation of the left atrial wall, in this research we propose a shape-based image segmentation framework to segment the endocardial wall of the left atrium.[[Projects:SegmentationEpicardialWall|More...]]

<font color="red">'''New: '''</font> Y. Gao, B. Gholami, R. S. MacLeod, J, Blauer, W. M. Haddad, and A. R. Tannenbaum, Segmentation of the Endocardial Wall of the Left Atrium using Local Region-Based Active Contours and Statistical Shape Learning, SPIE Medical Imaging, San Diego, CA, 2010.

|-

| | [[Image:Pain1.JPG|200px]]
| |

== [[Projects:PainAssessment|Agitation and Pain Assessment Using Digital Imaging]] ==

Pain assessment in patients who are unable to verbally
communicate with medical staff is a challenging problem
in patient critical care. The fundamental limitations in sedation
and pain assessment in the intensive care unit (ICU) stem
from subjective assessment criteria, rather than quantifiable,
measurable data for ICU sedation and analgesia. This often
results in poor quality and inconsistent treatment of patient
agitation and pain from nurse to nurse. Recent advancements in
pattern recognition techniques using a relevance vector machine
algorithm can assist medical staff in assessing sedation and pain
by constantly monitoring the patient and providing the clinician
with quantifiable data for ICU sedation. In this paper, we show
that the pain intensity assessment given by a computer classifier
has a strong correlation with the pain intensity assessed by
expert and non-expert human examiners.[[Projects:PainAssessment|More...]]

<font color="red">'''New: '''</font> B. Gholami, W. M. Haddad, and A. Tannenbaum, “Relevance Vector Machine Learning for Neonate Pain Intensity Assessment Using Digital Imaging,” IEEE Trans. Biomed. Eng., vol. 57, pp. 1457-1466.

B. Gholami, W. M. Haddad, and A. R. Tannenbaum, “Agitation and Pain Assessment Using Digital Imaging,” Proc. IEEE Eng. Med. Biolog. Conf., Minneapolis, MN, pp. 2176-2179, 2009 (Awarded National Institute of Biomedical Imaging and Bioengineering/National Institute of Health Student Travel Fellowship).

|-

| | [[Image:MultiObjSeg.png|200px|]]
| |

== [[RobustStatisticsSegmentation|Simultaneous Multiple Object Segmentation using Robust Statistics Features ]] ==

Multiple objects are segmented simultaneously using several interactive active contours based on the feature image which utilizes the robust statistics of the image. [[RobustStatisticsSegmentation|More...]]

|-

| | [[Image:ShapeBasePstSegSlicer.png|200px|]]
| |

== [[Projects:ProstateSegmentation|Prostate Segmentation]] ==

The 3D prostate MRI images are collected by collaborators at Queen’s University. With a little manual initialization, the algorithm provided the results give to the left. The method mainly uses Random Walk algorithm. [[Projects:ProstateSegmentation|More...]]

<font color="red">'''New: '''</font> Y. Gao, A. Tannenbaum; Shape based MRI prostate image segmentation using local information driven directional distance Bayesian method. SPIE Medical Imaging 2010.

|-

| | [[Image:ProstateRegSupineToProneInParaview.png|200px|]]
| |

== [[Projects:pfPtSetImgReg|Particle Filter Registration of Medical Imagery]] ==

3D volumetric image registration is performed. The method is based on registering the images through point sets, which is able to handle long distance between as well as registration between Supine and Prone pose prostate. [[Projects:pfPtSetImgReg|More...]]

<font color="red">'''New: '''</font> Y. Gao, R. Sandhu, G. Fichtinger, A. Tannenbaum; A coupled global registration and segmentation framework with application to magnetic resonance prostate imagery. IEEE TMI vol.29, pp1781, 2010
.

|-

| | [[Image:GT-DWI-Reorientation-1.jpg|200px]]
| |

== [[Projects:DWIReorientation|Re-Orientation Approach for Segmentation of DW-MRI]] ==

This work proposes a methodology to segment tubular fiber bundles from diffusion weighted magnetic resonance images (DW-MRI). Segmentation is simplified by locally reorienting diffusion information based on large-scale fiber bundle geometry. [[Projects:DWIReorientation|More...]]

<font color="red">'''New: '''</font> Near-tubular fiber bundle segmentation for diffusion weighted imaging: segmentation through frame reorientation. Neuroimage, Mar 2009.

|-

| | [[Image:GTTubSurfaceSeg-Img1.png|200px]]
| |

== [[Projects:TubularSurfaceSegmentation|Tubular Surface Segmentation Framework]] ==

We have proposed a new model for tubular surfaces that transforms the problem of detecting a surface in 3D space, to detecting a curve in 4D space. Besides allowing us to impose a "soft" tubular shape prior, this also leads to computational efficiency over conventional surface segmentation approaches. [[Projects:TubularSurfaceSegmentation|More...]]

<font color="red">'''New: '''</font> V. Mohan, G. Sundaramoorthi, M. Kubicki and A. Tannenbaum. Tubular Surface Evolution for Segmentation of the Cingulum Bundle From DW-MRI. September 2008. Proceedings of the Second Workshop on Mathematical Foundations of Computational Anatomy (MFCA'08), Int Conf Med Image Comput Comput Assist Interv. 2008.

<font color="red">'''New: '''</font> V. Mohan, G. Sundaramoorthi, A. Stillman and A. Tannenbaum. Vessel Segmentation with Automatic Centerline Extraction using Tubular Surface Segmentation. September 2009. Proceedings of the Workshop on Cardiac Interventional Imaging and Biophysical Modelling (CI2BM'09), Int Conf Med Image Comput Comput Assist Interv. 2009.

<font color="red">'''New: '''</font> V. Mohan, G. Sundaramoorthi and A. Tannenbaum. Tubular Surface Segmentation for Extracting Anatomical Structures from Medical Imagery (in submission). IEEE Transactions on Medical Imaging.

|-

| | [[Image:GT-PopStudyVis OnCBs Case19-View2.jpg|200px]]
| |

== [[Projects:TubularSurfaceSegmentationPopStudy|Group Study on DW-MRI using the Tubular Surface Model]] ==

We have proposed a new framework for performing group studies on DW-MRI data sets using the Tubular Surface Model of Mohan et al. We successfully apply this framework to discriminating schizophrenic cases from normal controls, as well as towards visualizing the regions of the Cingulum Bundle that are affected by Schizophrenia. [[Projects:TubularSurfaceSegmentationPopStudy|More...]]

<font color="red">'''New: '''</font> V. Mohan, G. Sundaramoorthi, M. Kubicki, D. Terry and A. Tannenbaum. Population Analysis of the Cingulum Bundle using the Tubular Surface Model for Schizophrenia Detection. SPIE Medical Imaging 2010.

<font color="red">'''New: '''</font> V. Mohan, G. Sundaramoorthi, M. Kubicki and A. Tannenbaum. Population Analysis of neural fiber bundles towards schizophrenia detection and characterization, using the Tubular Surface model. Neuroimage (in preparation)

|-

| | [[Image:Model3D_upTrans.png|200px]]
| |

== [[Projects:MGH-HeadAndNeck-RT|Adaptive Radiotherapy for head, neck and thorax]] ==

We proposed an algorithm to include prior knowledge in previously segmented anatomical structures to help in the segmentation of the next structure. This will add enough prior information to allow the Graph Cuts algorithm to segment structures with fuzzy boundaries. [[Projects:MGH-HeadAndNeck-RT|More...]]

<font color="red">'''New: '''</font> I. Kolesov, V. Mohan, G. Sharp and A. Tannenbaum. Coupled Segmentation for Anatomical Structures by Combining Shape and Relational Spatial Information. MTNS 2010.

|-

| | [[Image:Circle seg.PNG|200px|]]
| |

== [[Projects:KPCASegmentation|Kernel PCA for Segmentation]] ==

Segmentation performances using active contours can be drastically improved if the possible shapes of the object of interest are learnt. The goal of this work is to use Kernel PCA to learn shape priors. Kernel PCA allows for learning non linear dependencies in data sets, leading to more robust shape priors. [[Projects:KPCASegmentation|More...]]

<font color="red">'''New: '''</font> S. Dambreville, Y. Rathi, and A. Tannenbaum. A Framework for Image Segmentation using Image Shape Models and Kernel PCA Shape Priors. IEEE Trans Pattern Anal Mach Intell. 2008 Aug;30(8):1385-99

|-
| | [[Image:ZoomedResultWithModel.png|200px]]
| |

== [[Projects:GeodesicTractographySegmentation|Geodesic Tractography Segmentation]] ==

In this work, we provide an energy minimization framework which allows one to find fiber tracts and volumetric fiber bundles in brain diffusion-weighted MRI (DW-MRI). [[Projects:GeodesicTractographySegmentation|More...]]

<font color="red">'''New: '''</font> J. Melonakos, E. Pichon, S. Angenet, and A. Tannenbaum. Finsler Active Contours. IEEE Transactions on Pattern Analysis and Machine Intelligence, March 2008, Vol 30, Num 3.

|-

| | [[Image:P1_small.png|200px|]]
| |

== [[Projects:LabelSpace|Label Space: A Coupled Multi-Shape Representation]] ==

Many techniques for multi-shape representation may often develop inaccuracies stemming from either approximations or inherent variation. Label space is an implicit representation that offers unbiased algebraic manipulation and natural expression of label uncertainty. We demonstrate smoothing and registration on multi-label brain MRI. [[Projects:LabelSpace|More...]]

<font color="red">'''New: '''</font> J. Malcolm, Y. Rathi, A. Tannenbaum. "Label Space: A Multi-Object Shape Representation." In Combinatorial Image Analysis, 2008.

|-

| | [[Image:BasePair3DModel.JPG|200px|]]
| |

== [[Projects:NonParametricClustering|Non Parametric Clustering for Biomolecular Structural Analysis]] ==

High accuracy imaging and image processing techniques allow for collecting structural information of biomolecules with atomistic accuracy. Direct interpretation of the dynamics and the functionality of these structures with physical models, is yet to be developed. Clustering of molecular conformations into classes seems to be the first stage in recovering the formation and the functionality of these molecules. [[Projects:NonParametricClustering|More...]]

<font color="red">'''New: '''</font> E. Hershkovits, A. Tannenbaum, and R. Tannenbaum. Adsorption of Block Copolymers from Selective Solvents on Curved Surfaces. Macromolecules. 2008.

|-

| | [[Image:TruckInitialization.png|200px|]]
| |

== [[Projects:PointSetRigidRegistration|Point Set Rigid Registration]] ==

In this work, we propose a particle filtering approach for the problem of registering two point sets that differ by
a rigid body transformation. Experimental results are provided that demonstrate the robustness of the algorithm to initialization, noise, missing structures or differing point densities in each sets, on challenging 2D and 3D registration tasks. [[Projects:PointSetRigidRegistration|More...]]

<font color="red">'''New: '''</font> R. Sandhu, S. Dambreville, A. Tannenbaum. Particle Filtering for Registration of 2D and 3D Point Sets with Stochastic Dynamics. In CVPR, 2008.

|-

| | [[Image:Results brain sag.JPG|200px]]
| |

== [[Projects:OptimalMassTransportRegistration|Optimal Mass Transport Registration]] ==

The goal of this project is to implement a computationaly efficient Elastic/Non-rigid Registration algorithm based on the Monge-Kantorovich theory of optimal mass transport for 3D Medical Imagery. Our technique is based on Multigrid and Multiresolution techniques. This method is particularly useful because it is parameter free and utilizes all of the grayscale data in the image pairs in a symmetric fashion and no landmarks need to be specified for correspondence. [[Projects:OptimalMassTransportRegistration|More...]]

<font color="red">'''New: '''</font> Eldad Haber, Tauseef Rehman, and Allen Tannenbaum. An Efficient Numerical Method for the Solution of the L2 Optimal Mass Transfer Problem. In submission - SIAM Journal of Scientific Computing, 2009.

<font color="red">'''New: '''</font> Tauseef Rehman, Eldad Haber, Gallagher Pryor, and Allen Tannenbaum. Fast Optimal Mass Transport for 2D Image Registration and Morphing. Accepted for - Elsevier Journal of Image and Vision Computing, 2009.

|-

| | [[Image:Gatech caudateBands.PNG|200px]]
| |

== [[Projects:MultiscaleShapeSegmentation|Multiscale Shape Segmentation Techniques]] ==

To represent multiscale variations in a shape population in order to drive the segmentation of deep brain structures, such as the caudate nucleus or the hippocampus. [[Projects:MultiscaleShapeSegmentation|More...]]

|-

| | [[Image:Caudate Nucleus Denoising.JPG|200px|]]
| |

== [[Projects:WaveletShrinkage|Wavelet Shrinkage for Shape Analysis]] ==

Shape analysis has become a topic of interest in medical imaging since local variations of a shape could carry relevant information about a disease that may affect only a portion of an organ. We developed a novel wavelet-based denoising and compression statistical model for 3D shapes. [[Projects:WaveletShrinkage|More...]]

|-

| | [[Image:Basis membership.png|200px]]
| |

== [[Projects:MultiscaleShapeAnalysis|Multiscale Shape Analysis]] ==

We present a novel method of statistical surface-based morphometry based on the use of non-parametric permutation tests and a spherical wavelet (SWC) shape representation. [[Projects:MultiscaleShapeAnalysis|More...]]

|-

| | [[Image:Dlpfc1.jpg|200px|]]
| |

== [[Projects:RuleBasedDLPFCSegmentation|Rule-Based DLPFC Segmentation]] ==

In this work, we provide software to semi-automate the implementation of segmentation procedures based on expert neuroanatomist rules for the dorsolateral prefrontal cortex. [[Projects:RuleBasedDLPFCSegmentation|More...]]

|-

| | [[Image:Striatum1.png|200px|]]
| |

== [[Projects:RuleBasedStriatumSegmentation|Rule-Based Striatum Segmentation]] ==

In this work, we provide software to semi-automate the implementation of segmentation procedures based on expert neuroanatomist rules for the striatum. [[Projects:RuleBasedStriatumSegmentation|More...]]

|-

| | [[Image:Brain-flat.PNG|200px]]
| |

== [[Projects:ConformalFlatteningRegistration|Conformal Flattening (inactive)]] ==

The goal of this project is for better visualizing and computation of neural activity from fMRI brain imagery. Also, with this technique, shapes can be mapped to shperes for shape analysis, registration or other purposes. Our technique is based on conformal mappings which map genus-zero surface: in fmri case cortical or other surfaces, onto a sphere in an angle preserving manner. [[Projects:ConformalFlatteningRegistration|More...]]

|-

| | [[Image:Fig1yan.PNG|200px|]]
| |

== [[Projects:BloodVesselSegmentation|Blood Vessel Segmentation]] ==

The goal of this work is to develop blood vessel segmentation techniques for 3D MRI and CT data. The methods have been applied to coronary arteries and portal veins, with promising results. [[Projects:BloodVesselSegmentation|More...]]

<font color="red">'''New: '''</font> V.Mohan, G. Sundaramoorthi, A. Stillman and A. Tannenbaum. Vessel Segmentation with Automatic Centerline Extraction Using Tubular Tree Segmentation. CI2BM at MICCAI 2009, September 2009.

|-

| | [[Image:Fig67.png|200px|]]
| |

== [[Projects:KnowledgeBasedBayesianSegmentation|Knowledge-Based Bayesian Segmentation]] ==

This ITK filter is a segmentation algorithm that utilizes Bayes's Rule along with an affine-invariant anisotropic smoothing filter. [[Projects:KnowledgeBasedBayesianSegmentation|More...]]

|-

| | [[Image:Stochastic-snake.png|200px|]]
| |

== [[Projects:StochasticMethodsSegmentation|Stochastic Methods for Segmentation]] ==

New stochastic methods for implementing curvature driven flows for various medical tasks such as segmentation. [[Projects:StochasticMethodsSegmentation|More...]]

|-

| | [[Image:GT-SulciOutlining1.jpg|200px]]
| |

== [[Projects:SulciOutlining|Automatic Outlining of sulci on the brain surface]] ==

We present a method to automatically extract certain key features on a surface. We apply this technique to outline sulci on the cortical surface of a brain. [[Projects:SulciOutlining|More...]]

|-

| | [[Image:Table1.png|200px|]]
| |

== [[Projects:KPCA_LLE_KLLE_ShapeAnalysis|KPCA, LLE, KLLE Shape Analysis]] ==

The goal of this work is to study and compare shape learning techniques. The techniques considered are Linear Principal Components Analysis (PCA), Kernel PCA, Locally Linear Embedding (LLE) and Kernel LLE. [[Projects:KPCA_LLE_KLLE_ShapeAnalysis|More...]]

|-

| | [[Image:Gatech SlicerModel2.jpg|200px]]
| |

== [[Projects:StatisticalSegmentationSlicer2|Statistical/PDE Methods using Fast Marching for Segmentation]] ==

This Fast Marching based flow was added to Slicer 2. [[Projects:StatisticalSegmentationSlicer2|More...]]

|}

Algorithm:BU

2011-10-17T15:01:01Z

Yflou: /* Multimodal Deformable Registration of Traumatic Brain Injury MR Volumes using Graphics Processing Units */

Back to [[Algorithm:Main|NA-MIC Algorithms]]
__NOTOC__
= Overview of Boston University Algorithms (PI: Allen Tannenbaum) =

At Boston University, we are broadly interested in a range of mathematical image analysis algorithms for segmentation, registration, diffusion-weighted MRI analysis, and statistical analysis. For many applications, we cast the problem in an energy minimization framework wherein we define a partial differential equation whose numeric solution corresponds to the desired algorithmic outcome. The following are many examples of PDE techniques applied to medical image analysis.

= Boston University Projects =

{| cellpadding="10" style="text-align:left;"

| | [[Image:GT-SPD-img1.png|200px|]]
| |

== [[Projects:RegistrationTBI|Multimodal Deformable Registration of Traumatic Brain Injury MR Volumes using Graphics Processing Units]] ==

Time-efficient processing and analysis of magnetic resonance imaging (MRI) volumes is desirable is for the neurocritical care and monitoring of traumatic brain injury (TBI) patients. An important problem of TBI neuroimaging data analysis is the task of co-registering MR volumes acquired using distinct sequences in the presence of widely variable pixel intensities that are due to the presence of pathology. Here we address this important and challenging problems using an implementation of multimodal deformable registration on graphics processing units (GPU). We follow a viscous fluid model framework and replace mutual information with the Bhattacharyya distance as the measure of similarity between image volumes. The proposed algorithm is implemented on a GPU and its robustness is illustrated using a longitudinal multimodal TBI dataset. [[Projects:RegistrationTBI|More...]]

|-

| | [[Image:ToT1e1.pdf|200px]]
| |

== [[Projects:MultiScaleShapeSegmentation|Multi-scale Shape Representation and Segmentation With Applications to Radiotherapy]] ==

We present in this work a multiscale representation for shapes with arbitrary topology, and a method to segment the target organ/tissue from medical images having very low contrast with respect to surrounding regions using multiscale shape information and local image features. In a number of previous papers, shape knowledge was incorporated by first constructing a shape space from training data, and then constraining the segmentation process to be within the resulting shape space. However, such an approach has certain limitations including the fact that small scale shape variances may be overwhelmed by those on larger scale, and therefore the local shape information is lost. In this work, first we handle this problem by providing a multiscale shape representation using the wavelet transform. Consequently, the shape variances captured by the statistical learning step are also represented at various scales. In doing so, not only is the diversity of shape enriched, but also small scale changes are nicely captured. [[Projects:MultiScaleShapeSegmentation|More...]]

|-

| | [[Image:GT-SPD-img1.png|200px|]]
| |

== [[Projects:SoftPlaqueDetection|Soft Plaque Detection in CTA Imagery]] ==

The ability to detect and measure non-calciﬁed plaques (also known as soft plaques) may improve physicians’ ability to predict cardiac events. This work automatically detects soft plaques in CTA imagery using active contours driven by spatially localized probabilistic models. Plaques are identified by simultaneously segmenting the vessel from the inside-out and the outside-in using carefully chosen localized energies [[Projects:SoftPlaqueDetection|More...]]

<font color="red">'''New: '''</font> Soft Plaque Detection and Automatic Vessel Segmentation. PMMIA Workshop in MICCAI, Sep. 2009.
|-

| | [[Image:3D_Segmentation_LA.png|200px]]
| |

== [[Projects:SegmentationEndocardialWall|Segmentation of the Left Atrial Wall for Atrial Fibrillation Ablation Therapy]] ==

Magnetic resonance imaging (MRI) has been used for both pre- and and post-ablation assessment of the atrial wall. MRI can aid in selecting the right candidate for the ablation procedure and assessing post-ablation scar formations. Image processing techniques can be used for automatic segmentation of the atrial wall, which facilitates an accurate statistical assessment of the region. As a first step towards the general solution to the computer-assisted segmentation of the left atrial wall, in this research we propose a shape-based image segmentation framework to segment the endocardial wall of the left atrium.[[Projects:SegmentationEpicardialWall|More...]]

<font color="red">'''New: '''</font> Y. Gao, B. Gholami, R. S. MacLeod, J, Blauer, W. M. Haddad, and A. R. Tannenbaum, Segmentation of the Endocardial Wall of the Left Atrium using Local Region-Based Active Contours and Statistical Shape Learning, SPIE Medical Imaging, San Diego, CA, 2010.

|-

| | [[Image:Pain1.JPG|200px]]
| |

== [[Projects:PainAssessment|Agitation and Pain Assessment Using Digital Imaging]] ==

Pain assessment in patients who are unable to verbally
communicate with medical staff is a challenging problem
in patient critical care. The fundamental limitations in sedation
and pain assessment in the intensive care unit (ICU) stem
from subjective assessment criteria, rather than quantifiable,
measurable data for ICU sedation and analgesia. This often
results in poor quality and inconsistent treatment of patient
agitation and pain from nurse to nurse. Recent advancements in
pattern recognition techniques using a relevance vector machine
algorithm can assist medical staff in assessing sedation and pain
by constantly monitoring the patient and providing the clinician
with quantifiable data for ICU sedation. In this paper, we show
that the pain intensity assessment given by a computer classifier
has a strong correlation with the pain intensity assessed by
expert and non-expert human examiners.[[Projects:PainAssessment|More...]]

<font color="red">'''New: '''</font> B. Gholami, W. M. Haddad, and A. Tannenbaum, “Relevance Vector Machine Learning for Neonate Pain Intensity Assessment Using Digital Imaging,” IEEE Trans. Biomed. Eng., vol. 57, pp. 1457-1466.

B. Gholami, W. M. Haddad, and A. R. Tannenbaum, “Agitation and Pain Assessment Using Digital Imaging,” Proc. IEEE Eng. Med. Biolog. Conf., Minneapolis, MN, pp. 2176-2179, 2009 (Awarded National Institute of Biomedical Imaging and Bioengineering/National Institute of Health Student Travel Fellowship).

|-

| | [[Image:MultiObjSeg.png|200px|]]
| |

== [[RobustStatisticsSegmentation|Simultaneous Multiple Object Segmentation using Robust Statistics Features ]] ==

Multiple objects are segmented simultaneously using several interactive active contours based on the feature image which utilizes the robust statistics of the image. [[RobustStatisticsSegmentation|More...]]

|-

| | [[Image:ShapeBasePstSegSlicer.png|200px|]]
| |

== [[Projects:ProstateSegmentation|Prostate Segmentation]] ==

The 3D prostate MRI images are collected by collaborators at Queen’s University. With a little manual initialization, the algorithm provided the results give to the left. The method mainly uses Random Walk algorithm. [[Projects:ProstateSegmentation|More...]]

<font color="red">'''New: '''</font> Y. Gao, A. Tannenbaum; Shape based MRI prostate image segmentation using local information driven directional distance Bayesian method. SPIE Medical Imaging 2010.

|-

| | [[Image:ProstateRegSupineToProneInParaview.png|200px|]]
| |

== [[Projects:pfPtSetImgReg|Particle Filter Registration of Medical Imagery]] ==

3D volumetric image registration is performed. The method is based on registering the images through point sets, which is able to handle long distance between as well as registration between Supine and Prone pose prostate. [[Projects:pfPtSetImgReg|More...]]

<font color="red">'''New: '''</font> Y. Gao, R. Sandhu, G. Fichtinger, A. Tannenbaum; A coupled global registration and segmentation framework with application to magnetic resonance prostate imagery. IEEE TMI vol.29, pp1781, 2010
.

|-

| | [[Image:GT-DWI-Reorientation-1.jpg|200px]]
| |

== [[Projects:DWIReorientation|Re-Orientation Approach for Segmentation of DW-MRI]] ==

This work proposes a methodology to segment tubular fiber bundles from diffusion weighted magnetic resonance images (DW-MRI). Segmentation is simplified by locally reorienting diffusion information based on large-scale fiber bundle geometry. [[Projects:DWIReorientation|More...]]

<font color="red">'''New: '''</font> Near-tubular fiber bundle segmentation for diffusion weighted imaging: segmentation through frame reorientation. Neuroimage, Mar 2009.

|-

| | [[Image:GTTubSurfaceSeg-Img1.png|200px]]
| |

== [[Projects:TubularSurfaceSegmentation|Tubular Surface Segmentation Framework]] ==

We have proposed a new model for tubular surfaces that transforms the problem of detecting a surface in 3D space, to detecting a curve in 4D space. Besides allowing us to impose a "soft" tubular shape prior, this also leads to computational efficiency over conventional surface segmentation approaches. [[Projects:TubularSurfaceSegmentation|More...]]

<font color="red">'''New: '''</font> V. Mohan, G. Sundaramoorthi, M. Kubicki and A. Tannenbaum. Tubular Surface Evolution for Segmentation of the Cingulum Bundle From DW-MRI. September 2008. Proceedings of the Second Workshop on Mathematical Foundations of Computational Anatomy (MFCA'08), Int Conf Med Image Comput Comput Assist Interv. 2008.

<font color="red">'''New: '''</font> V. Mohan, G. Sundaramoorthi, A. Stillman and A. Tannenbaum. Vessel Segmentation with Automatic Centerline Extraction using Tubular Surface Segmentation. September 2009. Proceedings of the Workshop on Cardiac Interventional Imaging and Biophysical Modelling (CI2BM'09), Int Conf Med Image Comput Comput Assist Interv. 2009.

<font color="red">'''New: '''</font> V. Mohan, G. Sundaramoorthi and A. Tannenbaum. Tubular Surface Segmentation for Extracting Anatomical Structures from Medical Imagery (in submission). IEEE Transactions on Medical Imaging.

|-

| | [[Image:GT-PopStudyVis OnCBs Case19-View2.jpg|200px]]
| |

== [[Projects:TubularSurfaceSegmentationPopStudy|Group Study on DW-MRI using the Tubular Surface Model]] ==

We have proposed a new framework for performing group studies on DW-MRI data sets using the Tubular Surface Model of Mohan et al. We successfully apply this framework to discriminating schizophrenic cases from normal controls, as well as towards visualizing the regions of the Cingulum Bundle that are affected by Schizophrenia. [[Projects:TubularSurfaceSegmentationPopStudy|More...]]

<font color="red">'''New: '''</font> V. Mohan, G. Sundaramoorthi, M. Kubicki, D. Terry and A. Tannenbaum. Population Analysis of the Cingulum Bundle using the Tubular Surface Model for Schizophrenia Detection. SPIE Medical Imaging 2010.

<font color="red">'''New: '''</font> V. Mohan, G. Sundaramoorthi, M. Kubicki and A. Tannenbaum. Population Analysis of neural fiber bundles towards schizophrenia detection and characterization, using the Tubular Surface model. Neuroimage (in preparation)

|-

| | [[Image:Model3D_upTrans.png|200px]]
| |

== [[Projects:MGH-HeadAndNeck-RT|Adaptive Radiotherapy for head, neck and thorax]] ==

We proposed an algorithm to include prior knowledge in previously segmented anatomical structures to help in the segmentation of the next structure. This will add enough prior information to allow the Graph Cuts algorithm to segment structures with fuzzy boundaries. [[Projects:MGH-HeadAndNeck-RT|More...]]

<font color="red">'''New: '''</font> I. Kolesov, V. Mohan, G. Sharp and A. Tannenbaum. Coupled Segmentation for Anatomical Structures by Combining Shape and Relational Spatial Information. MTNS 2010.

|-

| | [[Image:Circle seg.PNG|200px|]]
| |

== [[Projects:KPCASegmentation|Kernel PCA for Segmentation]] ==

Segmentation performances using active contours can be drastically improved if the possible shapes of the object of interest are learnt. The goal of this work is to use Kernel PCA to learn shape priors. Kernel PCA allows for learning non linear dependencies in data sets, leading to more robust shape priors. [[Projects:KPCASegmentation|More...]]

<font color="red">'''New: '''</font> S. Dambreville, Y. Rathi, and A. Tannenbaum. A Framework for Image Segmentation using Image Shape Models and Kernel PCA Shape Priors. IEEE Trans Pattern Anal Mach Intell. 2008 Aug;30(8):1385-99

|-
| | [[Image:ZoomedResultWithModel.png|200px]]
| |

== [[Projects:GeodesicTractographySegmentation|Geodesic Tractography Segmentation]] ==

In this work, we provide an energy minimization framework which allows one to find fiber tracts and volumetric fiber bundles in brain diffusion-weighted MRI (DW-MRI). [[Projects:GeodesicTractographySegmentation|More...]]

<font color="red">'''New: '''</font> J. Melonakos, E. Pichon, S. Angenet, and A. Tannenbaum. Finsler Active Contours. IEEE Transactions on Pattern Analysis and Machine Intelligence, March 2008, Vol 30, Num 3.

|-

| | [[Image:P1_small.png|200px|]]
| |

== [[Projects:LabelSpace|Label Space: A Coupled Multi-Shape Representation]] ==

Many techniques for multi-shape representation may often develop inaccuracies stemming from either approximations or inherent variation. Label space is an implicit representation that offers unbiased algebraic manipulation and natural expression of label uncertainty. We demonstrate smoothing and registration on multi-label brain MRI. [[Projects:LabelSpace|More...]]

<font color="red">'''New: '''</font> J. Malcolm, Y. Rathi, A. Tannenbaum. "Label Space: A Multi-Object Shape Representation." In Combinatorial Image Analysis, 2008.

|-

| | [[Image:BasePair3DModel.JPG|200px|]]
| |

== [[Projects:NonParametricClustering|Non Parametric Clustering for Biomolecular Structural Analysis]] ==

High accuracy imaging and image processing techniques allow for collecting structural information of biomolecules with atomistic accuracy. Direct interpretation of the dynamics and the functionality of these structures with physical models, is yet to be developed. Clustering of molecular conformations into classes seems to be the first stage in recovering the formation and the functionality of these molecules. [[Projects:NonParametricClustering|More...]]

<font color="red">'''New: '''</font> E. Hershkovits, A. Tannenbaum, and R. Tannenbaum. Adsorption of Block Copolymers from Selective Solvents on Curved Surfaces. Macromolecules. 2008.

|-

| | [[Image:TruckInitialization.png|200px|]]
| |

== [[Projects:PointSetRigidRegistration|Point Set Rigid Registration]] ==

In this work, we propose a particle filtering approach for the problem of registering two point sets that differ by
a rigid body transformation. Experimental results are provided that demonstrate the robustness of the algorithm to initialization, noise, missing structures or differing point densities in each sets, on challenging 2D and 3D registration tasks. [[Projects:PointSetRigidRegistration|More...]]

<font color="red">'''New: '''</font> R. Sandhu, S. Dambreville, A. Tannenbaum. Particle Filtering for Registration of 2D and 3D Point Sets with Stochastic Dynamics. In CVPR, 2008.

|-

| | [[Image:Results brain sag.JPG|200px]]
| |

== [[Projects:OptimalMassTransportRegistration|Optimal Mass Transport Registration]] ==

The goal of this project is to implement a computationaly efficient Elastic/Non-rigid Registration algorithm based on the Monge-Kantorovich theory of optimal mass transport for 3D Medical Imagery. Our technique is based on Multigrid and Multiresolution techniques. This method is particularly useful because it is parameter free and utilizes all of the grayscale data in the image pairs in a symmetric fashion and no landmarks need to be specified for correspondence. [[Projects:OptimalMassTransportRegistration|More...]]

<font color="red">'''New: '''</font> Eldad Haber, Tauseef Rehman, and Allen Tannenbaum. An Efficient Numerical Method for the Solution of the L2 Optimal Mass Transfer Problem. In submission - SIAM Journal of Scientific Computing, 2009.

<font color="red">'''New: '''</font> Tauseef Rehman, Eldad Haber, Gallagher Pryor, and Allen Tannenbaum. Fast Optimal Mass Transport for 2D Image Registration and Morphing. Accepted for - Elsevier Journal of Image and Vision Computing, 2009.

|-

| | [[Image:Gatech caudateBands.PNG|200px]]
| |

== [[Projects:MultiscaleShapeSegmentation|Multiscale Shape Segmentation Techniques]] ==

To represent multiscale variations in a shape population in order to drive the segmentation of deep brain structures, such as the caudate nucleus or the hippocampus. [[Projects:MultiscaleShapeSegmentation|More...]]

|-

| | [[Image:Caudate Nucleus Denoising.JPG|200px|]]
| |

== [[Projects:WaveletShrinkage|Wavelet Shrinkage for Shape Analysis]] ==

Shape analysis has become a topic of interest in medical imaging since local variations of a shape could carry relevant information about a disease that may affect only a portion of an organ. We developed a novel wavelet-based denoising and compression statistical model for 3D shapes. [[Projects:WaveletShrinkage|More...]]

|-

| | [[Image:Basis membership.png|200px]]
| |

== [[Projects:MultiscaleShapeAnalysis|Multiscale Shape Analysis]] ==

We present a novel method of statistical surface-based morphometry based on the use of non-parametric permutation tests and a spherical wavelet (SWC) shape representation. [[Projects:MultiscaleShapeAnalysis|More...]]

|-

| | [[Image:Dlpfc1.jpg|200px|]]
| |

== [[Projects:RuleBasedDLPFCSegmentation|Rule-Based DLPFC Segmentation]] ==

In this work, we provide software to semi-automate the implementation of segmentation procedures based on expert neuroanatomist rules for the dorsolateral prefrontal cortex. [[Projects:RuleBasedDLPFCSegmentation|More...]]

|-

| | [[Image:Striatum1.png|200px|]]
| |

== [[Projects:RuleBasedStriatumSegmentation|Rule-Based Striatum Segmentation]] ==

In this work, we provide software to semi-automate the implementation of segmentation procedures based on expert neuroanatomist rules for the striatum. [[Projects:RuleBasedStriatumSegmentation|More...]]

|-

| | [[Image:Brain-flat.PNG|200px]]
| |

== [[Projects:ConformalFlatteningRegistration|Conformal Flattening (inactive)]] ==

The goal of this project is for better visualizing and computation of neural activity from fMRI brain imagery. Also, with this technique, shapes can be mapped to shperes for shape analysis, registration or other purposes. Our technique is based on conformal mappings which map genus-zero surface: in fmri case cortical or other surfaces, onto a sphere in an angle preserving manner. [[Projects:ConformalFlatteningRegistration|More...]]

|-

| | [[Image:Fig1yan.PNG|200px|]]
| |

== [[Projects:BloodVesselSegmentation|Blood Vessel Segmentation]] ==

The goal of this work is to develop blood vessel segmentation techniques for 3D MRI and CT data. The methods have been applied to coronary arteries and portal veins, with promising results. [[Projects:BloodVesselSegmentation|More...]]

<font color="red">'''New: '''</font> V.Mohan, G. Sundaramoorthi, A. Stillman and A. Tannenbaum. Vessel Segmentation with Automatic Centerline Extraction Using Tubular Tree Segmentation. CI2BM at MICCAI 2009, September 2009.

|-

| | [[Image:Fig67.png|200px|]]
| |

== [[Projects:KnowledgeBasedBayesianSegmentation|Knowledge-Based Bayesian Segmentation]] ==

This ITK filter is a segmentation algorithm that utilizes Bayes's Rule along with an affine-invariant anisotropic smoothing filter. [[Projects:KnowledgeBasedBayesianSegmentation|More...]]

|-

| | [[Image:Stochastic-snake.png|200px|]]
| |

== [[Projects:StochasticMethodsSegmentation|Stochastic Methods for Segmentation]] ==

New stochastic methods for implementing curvature driven flows for various medical tasks such as segmentation. [[Projects:StochasticMethodsSegmentation|More...]]

|-

| | [[Image:GT-SulciOutlining1.jpg|200px]]
| |

== [[Projects:SulciOutlining|Automatic Outlining of sulci on the brain surface]] ==

We present a method to automatically extract certain key features on a surface. We apply this technique to outline sulci on the cortical surface of a brain. [[Projects:SulciOutlining|More...]]

|-

| | [[Image:Table1.png|200px|]]
| |

== [[Projects:KPCA_LLE_KLLE_ShapeAnalysis|KPCA, LLE, KLLE Shape Analysis]] ==

The goal of this work is to study and compare shape learning techniques. The techniques considered are Linear Principal Components Analysis (PCA), Kernel PCA, Locally Linear Embedding (LLE) and Kernel LLE. [[Projects:KPCA_LLE_KLLE_ShapeAnalysis|More...]]

|-

| | [[Image:Gatech SlicerModel2.jpg|200px]]
| |

== [[Projects:StatisticalSegmentationSlicer2|Statistical/PDE Methods using Fast Marching for Segmentation]] ==

This Fast Marching based flow was added to Slicer 2. [[Projects:StatisticalSegmentationSlicer2|More...]]

|}

File:ToT1e1.pdf

2011-10-17T14:59:53Z

Yflou:

Algorithm:BU

2011-10-17T14:58:49Z

Yflou: /* Multimodal Deformable Registration of Traumatic Brain Injury MR Volumes using Graphics Processing Units */

Back to [[Algorithm:Main|NA-MIC Algorithms]]
__NOTOC__
= Overview of Boston University Algorithms (PI: Allen Tannenbaum) =

At Boston University, we are broadly interested in a range of mathematical image analysis algorithms for segmentation, registration, diffusion-weighted MRI analysis, and statistical analysis. For many applications, we cast the problem in an energy minimization framework wherein we define a partial differential equation whose numeric solution corresponds to the desired algorithmic outcome. The following are many examples of PDE techniques applied to medical image analysis.

= Boston University Projects =

{| cellpadding="10" style="text-align:left;"

| | [[Image:GT-SPD-img1.png|200px|]]
| |

== [[Projects:RegistrationTBI|Multimodal Deformable Registration of Traumatic Brain Injury MR Volumes using Graphics Processing Units]] ==

Time-efficient processing and analysis of magnetic resonance imaging (MRI) volumes is desirable is for the neurocritical care and monitoring of traumatic brain injury (TBI) patients. An important problem of TBI neuroimaging data analysis is the task of co-registering MR volumes acquired using distinct sequences in the presence of widely variable pixel intensities that are due to the presence of pathology. Here we address this important and challenging problems using an implementation of multimodal deformable registration on graphics processing units (GPU). We follow a viscous fluid model framework and replace mutual information with the Bhattacharyya distance as the measure of similarity between image volumes. The proposed algorithm is implemented on a GPU and its robustness is illustrated using a longitudinal multimodal TBI dataset. [[Projects:RegistrationTBI|More...]]

|-

| | [[Image:MultiScaleHippoSegmentationHausdorf.png|200px]]
| |

== [[Projects:MultiScaleShapeSegmentation|Multi-scale Shape Representation and Segmentation With Applications to Radiotherapy]] ==

We present in this work a multiscale representation for shapes with arbitrary topology, and a method to segment the target organ/tissue from medical images having very low contrast with respect to surrounding regions using multiscale shape information and local image features. In a number of previous papers, shape knowledge was incorporated by first constructing a shape space from training data, and then constraining the segmentation process to be within the resulting shape space. However, such an approach has certain limitations including the fact that small scale shape variances may be overwhelmed by those on larger scale, and therefore the local shape information is lost. In this work, first we handle this problem by providing a multiscale shape representation using the wavelet transform. Consequently, the shape variances captured by the statistical learning step are also represented at various scales. In doing so, not only is the diversity of shape enriched, but also small scale changes are nicely captured. [[Projects:MultiScaleShapeSegmentation|More...]]

|-

| | [[Image:GT-SPD-img1.png|200px|]]
| |

== [[Projects:SoftPlaqueDetection|Soft Plaque Detection in CTA Imagery]] ==

The ability to detect and measure non-calciﬁed plaques (also known as soft plaques) may improve physicians’ ability to predict cardiac events. This work automatically detects soft plaques in CTA imagery using active contours driven by spatially localized probabilistic models. Plaques are identified by simultaneously segmenting the vessel from the inside-out and the outside-in using carefully chosen localized energies [[Projects:SoftPlaqueDetection|More...]]

<font color="red">'''New: '''</font> Soft Plaque Detection and Automatic Vessel Segmentation. PMMIA Workshop in MICCAI, Sep. 2009.
|-

| | [[Image:3D_Segmentation_LA.png|200px]]
| |

== [[Projects:SegmentationEndocardialWall|Segmentation of the Left Atrial Wall for Atrial Fibrillation Ablation Therapy]] ==

Magnetic resonance imaging (MRI) has been used for both pre- and and post-ablation assessment of the atrial wall. MRI can aid in selecting the right candidate for the ablation procedure and assessing post-ablation scar formations. Image processing techniques can be used for automatic segmentation of the atrial wall, which facilitates an accurate statistical assessment of the region. As a first step towards the general solution to the computer-assisted segmentation of the left atrial wall, in this research we propose a shape-based image segmentation framework to segment the endocardial wall of the left atrium.[[Projects:SegmentationEpicardialWall|More...]]

<font color="red">'''New: '''</font> Y. Gao, B. Gholami, R. S. MacLeod, J, Blauer, W. M. Haddad, and A. R. Tannenbaum, Segmentation of the Endocardial Wall of the Left Atrium using Local Region-Based Active Contours and Statistical Shape Learning, SPIE Medical Imaging, San Diego, CA, 2010.

|-

| | [[Image:Pain1.JPG|200px]]
| |

== [[Projects:PainAssessment|Agitation and Pain Assessment Using Digital Imaging]] ==

Pain assessment in patients who are unable to verbally
communicate with medical staff is a challenging problem
in patient critical care. The fundamental limitations in sedation
and pain assessment in the intensive care unit (ICU) stem
from subjective assessment criteria, rather than quantifiable,
measurable data for ICU sedation and analgesia. This often
results in poor quality and inconsistent treatment of patient
agitation and pain from nurse to nurse. Recent advancements in
pattern recognition techniques using a relevance vector machine
algorithm can assist medical staff in assessing sedation and pain
by constantly monitoring the patient and providing the clinician
with quantifiable data for ICU sedation. In this paper, we show
that the pain intensity assessment given by a computer classifier
has a strong correlation with the pain intensity assessed by
expert and non-expert human examiners.[[Projects:PainAssessment|More...]]

<font color="red">'''New: '''</font> B. Gholami, W. M. Haddad, and A. Tannenbaum, “Relevance Vector Machine Learning for Neonate Pain Intensity Assessment Using Digital Imaging,” IEEE Trans. Biomed. Eng., vol. 57, pp. 1457-1466.

B. Gholami, W. M. Haddad, and A. R. Tannenbaum, “Agitation and Pain Assessment Using Digital Imaging,” Proc. IEEE Eng. Med. Biolog. Conf., Minneapolis, MN, pp. 2176-2179, 2009 (Awarded National Institute of Biomedical Imaging and Bioengineering/National Institute of Health Student Travel Fellowship).

|-

| | [[Image:MultiObjSeg.png|200px|]]
| |

== [[RobustStatisticsSegmentation|Simultaneous Multiple Object Segmentation using Robust Statistics Features ]] ==

Multiple objects are segmented simultaneously using several interactive active contours based on the feature image which utilizes the robust statistics of the image. [[RobustStatisticsSegmentation|More...]]

|-

| | [[Image:ShapeBasePstSegSlicer.png|200px|]]
| |

== [[Projects:ProstateSegmentation|Prostate Segmentation]] ==

The 3D prostate MRI images are collected by collaborators at Queen’s University. With a little manual initialization, the algorithm provided the results give to the left. The method mainly uses Random Walk algorithm. [[Projects:ProstateSegmentation|More...]]

<font color="red">'''New: '''</font> Y. Gao, A. Tannenbaum; Shape based MRI prostate image segmentation using local information driven directional distance Bayesian method. SPIE Medical Imaging 2010.

|-

| | [[Image:ProstateRegSupineToProneInParaview.png|200px|]]
| |

== [[Projects:pfPtSetImgReg|Particle Filter Registration of Medical Imagery]] ==

3D volumetric image registration is performed. The method is based on registering the images through point sets, which is able to handle long distance between as well as registration between Supine and Prone pose prostate. [[Projects:pfPtSetImgReg|More...]]

<font color="red">'''New: '''</font> Y. Gao, R. Sandhu, G. Fichtinger, A. Tannenbaum; A coupled global registration and segmentation framework with application to magnetic resonance prostate imagery. IEEE TMI vol.29, pp1781, 2010
.

|-

| | [[Image:GT-DWI-Reorientation-1.jpg|200px]]
| |

== [[Projects:DWIReorientation|Re-Orientation Approach for Segmentation of DW-MRI]] ==

This work proposes a methodology to segment tubular fiber bundles from diffusion weighted magnetic resonance images (DW-MRI). Segmentation is simplified by locally reorienting diffusion information based on large-scale fiber bundle geometry. [[Projects:DWIReorientation|More...]]

<font color="red">'''New: '''</font> Near-tubular fiber bundle segmentation for diffusion weighted imaging: segmentation through frame reorientation. Neuroimage, Mar 2009.

|-

| | [[Image:GTTubSurfaceSeg-Img1.png|200px]]
| |

== [[Projects:TubularSurfaceSegmentation|Tubular Surface Segmentation Framework]] ==

We have proposed a new model for tubular surfaces that transforms the problem of detecting a surface in 3D space, to detecting a curve in 4D space. Besides allowing us to impose a "soft" tubular shape prior, this also leads to computational efficiency over conventional surface segmentation approaches. [[Projects:TubularSurfaceSegmentation|More...]]

<font color="red">'''New: '''</font> V. Mohan, G. Sundaramoorthi, M. Kubicki and A. Tannenbaum. Tubular Surface Evolution for Segmentation of the Cingulum Bundle From DW-MRI. September 2008. Proceedings of the Second Workshop on Mathematical Foundations of Computational Anatomy (MFCA'08), Int Conf Med Image Comput Comput Assist Interv. 2008.

<font color="red">'''New: '''</font> V. Mohan, G. Sundaramoorthi, A. Stillman and A. Tannenbaum. Vessel Segmentation with Automatic Centerline Extraction using Tubular Surface Segmentation. September 2009. Proceedings of the Workshop on Cardiac Interventional Imaging and Biophysical Modelling (CI2BM'09), Int Conf Med Image Comput Comput Assist Interv. 2009.

<font color="red">'''New: '''</font> V. Mohan, G. Sundaramoorthi and A. Tannenbaum. Tubular Surface Segmentation for Extracting Anatomical Structures from Medical Imagery (in submission). IEEE Transactions on Medical Imaging.

|-

| | [[Image:GT-PopStudyVis OnCBs Case19-View2.jpg|200px]]
| |

== [[Projects:TubularSurfaceSegmentationPopStudy|Group Study on DW-MRI using the Tubular Surface Model]] ==

We have proposed a new framework for performing group studies on DW-MRI data sets using the Tubular Surface Model of Mohan et al. We successfully apply this framework to discriminating schizophrenic cases from normal controls, as well as towards visualizing the regions of the Cingulum Bundle that are affected by Schizophrenia. [[Projects:TubularSurfaceSegmentationPopStudy|More...]]

<font color="red">'''New: '''</font> V. Mohan, G. Sundaramoorthi, M. Kubicki, D. Terry and A. Tannenbaum. Population Analysis of the Cingulum Bundle using the Tubular Surface Model for Schizophrenia Detection. SPIE Medical Imaging 2010.

<font color="red">'''New: '''</font> V. Mohan, G. Sundaramoorthi, M. Kubicki and A. Tannenbaum. Population Analysis of neural fiber bundles towards schizophrenia detection and characterization, using the Tubular Surface model. Neuroimage (in preparation)

|-

| | [[Image:Model3D_upTrans.png|200px]]
| |

== [[Projects:MGH-HeadAndNeck-RT|Adaptive Radiotherapy for head, neck and thorax]] ==

We proposed an algorithm to include prior knowledge in previously segmented anatomical structures to help in the segmentation of the next structure. This will add enough prior information to allow the Graph Cuts algorithm to segment structures with fuzzy boundaries. [[Projects:MGH-HeadAndNeck-RT|More...]]

<font color="red">'''New: '''</font> I. Kolesov, V. Mohan, G. Sharp and A. Tannenbaum. Coupled Segmentation for Anatomical Structures by Combining Shape and Relational Spatial Information. MTNS 2010.

|-

| | [[Image:Circle seg.PNG|200px|]]
| |

== [[Projects:KPCASegmentation|Kernel PCA for Segmentation]] ==

Segmentation performances using active contours can be drastically improved if the possible shapes of the object of interest are learnt. The goal of this work is to use Kernel PCA to learn shape priors. Kernel PCA allows for learning non linear dependencies in data sets, leading to more robust shape priors. [[Projects:KPCASegmentation|More...]]

<font color="red">'''New: '''</font> S. Dambreville, Y. Rathi, and A. Tannenbaum. A Framework for Image Segmentation using Image Shape Models and Kernel PCA Shape Priors. IEEE Trans Pattern Anal Mach Intell. 2008 Aug;30(8):1385-99

|-
| | [[Image:ZoomedResultWithModel.png|200px]]
| |

== [[Projects:GeodesicTractographySegmentation|Geodesic Tractography Segmentation]] ==

In this work, we provide an energy minimization framework which allows one to find fiber tracts and volumetric fiber bundles in brain diffusion-weighted MRI (DW-MRI). [[Projects:GeodesicTractographySegmentation|More...]]

<font color="red">'''New: '''</font> J. Melonakos, E. Pichon, S. Angenet, and A. Tannenbaum. Finsler Active Contours. IEEE Transactions on Pattern Analysis and Machine Intelligence, March 2008, Vol 30, Num 3.

|-

| | [[Image:P1_small.png|200px|]]
| |

== [[Projects:LabelSpace|Label Space: A Coupled Multi-Shape Representation]] ==

Many techniques for multi-shape representation may often develop inaccuracies stemming from either approximations or inherent variation. Label space is an implicit representation that offers unbiased algebraic manipulation and natural expression of label uncertainty. We demonstrate smoothing and registration on multi-label brain MRI. [[Projects:LabelSpace|More...]]

<font color="red">'''New: '''</font> J. Malcolm, Y. Rathi, A. Tannenbaum. "Label Space: A Multi-Object Shape Representation." In Combinatorial Image Analysis, 2008.

|-

| | [[Image:BasePair3DModel.JPG|200px|]]
| |

== [[Projects:NonParametricClustering|Non Parametric Clustering for Biomolecular Structural Analysis]] ==

High accuracy imaging and image processing techniques allow for collecting structural information of biomolecules with atomistic accuracy. Direct interpretation of the dynamics and the functionality of these structures with physical models, is yet to be developed. Clustering of molecular conformations into classes seems to be the first stage in recovering the formation and the functionality of these molecules. [[Projects:NonParametricClustering|More...]]

<font color="red">'''New: '''</font> E. Hershkovits, A. Tannenbaum, and R. Tannenbaum. Adsorption of Block Copolymers from Selective Solvents on Curved Surfaces. Macromolecules. 2008.

|-

| | [[Image:TruckInitialization.png|200px|]]
| |

== [[Projects:PointSetRigidRegistration|Point Set Rigid Registration]] ==

In this work, we propose a particle filtering approach for the problem of registering two point sets that differ by
a rigid body transformation. Experimental results are provided that demonstrate the robustness of the algorithm to initialization, noise, missing structures or differing point densities in each sets, on challenging 2D and 3D registration tasks. [[Projects:PointSetRigidRegistration|More...]]

<font color="red">'''New: '''</font> R. Sandhu, S. Dambreville, A. Tannenbaum. Particle Filtering for Registration of 2D and 3D Point Sets with Stochastic Dynamics. In CVPR, 2008.

|-

| | [[Image:Results brain sag.JPG|200px]]
| |

== [[Projects:OptimalMassTransportRegistration|Optimal Mass Transport Registration]] ==

The goal of this project is to implement a computationaly efficient Elastic/Non-rigid Registration algorithm based on the Monge-Kantorovich theory of optimal mass transport for 3D Medical Imagery. Our technique is based on Multigrid and Multiresolution techniques. This method is particularly useful because it is parameter free and utilizes all of the grayscale data in the image pairs in a symmetric fashion and no landmarks need to be specified for correspondence. [[Projects:OptimalMassTransportRegistration|More...]]

<font color="red">'''New: '''</font> Eldad Haber, Tauseef Rehman, and Allen Tannenbaum. An Efficient Numerical Method for the Solution of the L2 Optimal Mass Transfer Problem. In submission - SIAM Journal of Scientific Computing, 2009.

<font color="red">'''New: '''</font> Tauseef Rehman, Eldad Haber, Gallagher Pryor, and Allen Tannenbaum. Fast Optimal Mass Transport for 2D Image Registration and Morphing. Accepted for - Elsevier Journal of Image and Vision Computing, 2009.

|-

| | [[Image:Gatech caudateBands.PNG|200px]]
| |

== [[Projects:MultiscaleShapeSegmentation|Multiscale Shape Segmentation Techniques]] ==

To represent multiscale variations in a shape population in order to drive the segmentation of deep brain structures, such as the caudate nucleus or the hippocampus. [[Projects:MultiscaleShapeSegmentation|More...]]

|-

| | [[Image:Caudate Nucleus Denoising.JPG|200px|]]
| |

== [[Projects:WaveletShrinkage|Wavelet Shrinkage for Shape Analysis]] ==

Shape analysis has become a topic of interest in medical imaging since local variations of a shape could carry relevant information about a disease that may affect only a portion of an organ. We developed a novel wavelet-based denoising and compression statistical model for 3D shapes. [[Projects:WaveletShrinkage|More...]]

|-

| | [[Image:Basis membership.png|200px]]
| |

== [[Projects:MultiscaleShapeAnalysis|Multiscale Shape Analysis]] ==

We present a novel method of statistical surface-based morphometry based on the use of non-parametric permutation tests and a spherical wavelet (SWC) shape representation. [[Projects:MultiscaleShapeAnalysis|More...]]

|-

| | [[Image:Dlpfc1.jpg|200px|]]
| |

== [[Projects:RuleBasedDLPFCSegmentation|Rule-Based DLPFC Segmentation]] ==

In this work, we provide software to semi-automate the implementation of segmentation procedures based on expert neuroanatomist rules for the dorsolateral prefrontal cortex. [[Projects:RuleBasedDLPFCSegmentation|More...]]

|-

| | [[Image:Striatum1.png|200px|]]
| |

== [[Projects:RuleBasedStriatumSegmentation|Rule-Based Striatum Segmentation]] ==

In this work, we provide software to semi-automate the implementation of segmentation procedures based on expert neuroanatomist rules for the striatum. [[Projects:RuleBasedStriatumSegmentation|More...]]

|-

| | [[Image:Brain-flat.PNG|200px]]
| |

== [[Projects:ConformalFlatteningRegistration|Conformal Flattening (inactive)]] ==

The goal of this project is for better visualizing and computation of neural activity from fMRI brain imagery. Also, with this technique, shapes can be mapped to shperes for shape analysis, registration or other purposes. Our technique is based on conformal mappings which map genus-zero surface: in fmri case cortical or other surfaces, onto a sphere in an angle preserving manner. [[Projects:ConformalFlatteningRegistration|More...]]

|-

| | [[Image:Fig1yan.PNG|200px|]]
| |

== [[Projects:BloodVesselSegmentation|Blood Vessel Segmentation]] ==

The goal of this work is to develop blood vessel segmentation techniques for 3D MRI and CT data. The methods have been applied to coronary arteries and portal veins, with promising results. [[Projects:BloodVesselSegmentation|More...]]

<font color="red">'''New: '''</font> V.Mohan, G. Sundaramoorthi, A. Stillman and A. Tannenbaum. Vessel Segmentation with Automatic Centerline Extraction Using Tubular Tree Segmentation. CI2BM at MICCAI 2009, September 2009.

|-

| | [[Image:Fig67.png|200px|]]
| |

== [[Projects:KnowledgeBasedBayesianSegmentation|Knowledge-Based Bayesian Segmentation]] ==

This ITK filter is a segmentation algorithm that utilizes Bayes's Rule along with an affine-invariant anisotropic smoothing filter. [[Projects:KnowledgeBasedBayesianSegmentation|More...]]

|-

| | [[Image:Stochastic-snake.png|200px|]]
| |

== [[Projects:StochasticMethodsSegmentation|Stochastic Methods for Segmentation]] ==

New stochastic methods for implementing curvature driven flows for various medical tasks such as segmentation. [[Projects:StochasticMethodsSegmentation|More...]]

|-

| | [[Image:GT-SulciOutlining1.jpg|200px]]
| |

== [[Projects:SulciOutlining|Automatic Outlining of sulci on the brain surface]] ==

We present a method to automatically extract certain key features on a surface. We apply this technique to outline sulci on the cortical surface of a brain. [[Projects:SulciOutlining|More...]]

|-

| | [[Image:Table1.png|200px|]]
| |

== [[Projects:KPCA_LLE_KLLE_ShapeAnalysis|KPCA, LLE, KLLE Shape Analysis]] ==

The goal of this work is to study and compare shape learning techniques. The techniques considered are Linear Principal Components Analysis (PCA), Kernel PCA, Locally Linear Embedding (LLE) and Kernel LLE. [[Projects:KPCA_LLE_KLLE_ShapeAnalysis|More...]]

|-

| | [[Image:Gatech SlicerModel2.jpg|200px]]
| |

== [[Projects:StatisticalSegmentationSlicer2|Statistical/PDE Methods using Fast Marching for Segmentation]] ==

This Fast Marching based flow was added to Slicer 2. [[Projects:StatisticalSegmentationSlicer2|More...]]

|}

Algorithm:BU

2011-10-17T14:56:29Z

Yflou: /* Boston University Projects */

Back to [[Algorithm:Main|NA-MIC Algorithms]]
__NOTOC__
= Overview of Boston University Algorithms (PI: Allen Tannenbaum) =

At Boston University, we are broadly interested in a range of mathematical image analysis algorithms for segmentation, registration, diffusion-weighted MRI analysis, and statistical analysis. For many applications, we cast the problem in an energy minimization framework wherein we define a partial differential equation whose numeric solution corresponds to the desired algorithmic outcome. The following are many examples of PDE techniques applied to medical image analysis.

= Boston University Projects =

{| cellpadding="10" style="text-align:left;"

| | [[Image:GT-SPD-img1.png|200px|]]
| |

== [[Projects:RegistrationTBI|Multimodal Deformable Registration of Traumatic Brain Injury MR Volumes using Graphics Processing Units]] ==

Time-efficient processing and analysis of magnetic resonance imaging (MRI) volumes can be critical for both medical diagnosis as well as for the formulation of acute treatment strategies. One context where such efficiency is desirable is for the neurocritical care and monitoring of traumatic brain injury (TBI) patients. An important problem of TBI neuroimaging data analysis is the task of co-registering MR volumes acquired using distinct sequences in the presence of widely variable pixel intensities that are due to the presence of pathology. Here we address this important and challenging problems using an implementation of multimodal deformable registration on graphics processing units (GPU). We follow a viscous fluid model framework and replace mutual information with the Bhattacharyya distance as the measure of similarity between image volumes. The proposed algorithm is implemented on a GPU and its robustness is illustrated using a longitudinal multimodal TBI dataset. [[Projects:SoftPlaqueDetection|More...]]

|-

| | [[Image:MultiScaleHippoSegmentationHausdorf.png|200px]]
| |

== [[Projects:MultiScaleShapeSegmentation|Multi-scale Shape Representation and Segmentation With Applications to Radiotherapy]] ==

We present in this work a multiscale representation for shapes with arbitrary topology, and a method to segment the target organ/tissue from medical images having very low contrast with respect to surrounding regions using multiscale shape information and local image features. In a number of previous papers, shape knowledge was incorporated by first constructing a shape space from training data, and then constraining the segmentation process to be within the resulting shape space. However, such an approach has certain limitations including the fact that small scale shape variances may be overwhelmed by those on larger scale, and therefore the local shape information is lost. In this work, first we handle this problem by providing a multiscale shape representation using the wavelet transform. Consequently, the shape variances captured by the statistical learning step are also represented at various scales. In doing so, not only is the diversity of shape enriched, but also small scale changes are nicely captured. [[Projects:MultiScaleShapeSegmentation|More...]]

|-

| | [[Image:GT-SPD-img1.png|200px|]]
| |

== [[Projects:SoftPlaqueDetection|Soft Plaque Detection in CTA Imagery]] ==

The ability to detect and measure non-calciﬁed plaques (also known as soft plaques) may improve physicians’ ability to predict cardiac events. This work automatically detects soft plaques in CTA imagery using active contours driven by spatially localized probabilistic models. Plaques are identified by simultaneously segmenting the vessel from the inside-out and the outside-in using carefully chosen localized energies [[Projects:SoftPlaqueDetection|More...]]

<font color="red">'''New: '''</font> Soft Plaque Detection and Automatic Vessel Segmentation. PMMIA Workshop in MICCAI, Sep. 2009.
|-

| | [[Image:3D_Segmentation_LA.png|200px]]
| |

== [[Projects:SegmentationEndocardialWall|Segmentation of the Left Atrial Wall for Atrial Fibrillation Ablation Therapy]] ==

Magnetic resonance imaging (MRI) has been used for both pre- and and post-ablation assessment of the atrial wall. MRI can aid in selecting the right candidate for the ablation procedure and assessing post-ablation scar formations. Image processing techniques can be used for automatic segmentation of the atrial wall, which facilitates an accurate statistical assessment of the region. As a first step towards the general solution to the computer-assisted segmentation of the left atrial wall, in this research we propose a shape-based image segmentation framework to segment the endocardial wall of the left atrium.[[Projects:SegmentationEpicardialWall|More...]]

<font color="red">'''New: '''</font> Y. Gao, B. Gholami, R. S. MacLeod, J, Blauer, W. M. Haddad, and A. R. Tannenbaum, Segmentation of the Endocardial Wall of the Left Atrium using Local Region-Based Active Contours and Statistical Shape Learning, SPIE Medical Imaging, San Diego, CA, 2010.

|-

| | [[Image:Pain1.JPG|200px]]
| |

== [[Projects:PainAssessment|Agitation and Pain Assessment Using Digital Imaging]] ==

Pain assessment in patients who are unable to verbally
communicate with medical staff is a challenging problem
in patient critical care. The fundamental limitations in sedation
and pain assessment in the intensive care unit (ICU) stem
from subjective assessment criteria, rather than quantifiable,
measurable data for ICU sedation and analgesia. This often
results in poor quality and inconsistent treatment of patient
agitation and pain from nurse to nurse. Recent advancements in
pattern recognition techniques using a relevance vector machine
algorithm can assist medical staff in assessing sedation and pain
by constantly monitoring the patient and providing the clinician
with quantifiable data for ICU sedation. In this paper, we show
that the pain intensity assessment given by a computer classifier
has a strong correlation with the pain intensity assessed by
expert and non-expert human examiners.[[Projects:PainAssessment|More...]]

<font color="red">'''New: '''</font> B. Gholami, W. M. Haddad, and A. Tannenbaum, “Relevance Vector Machine Learning for Neonate Pain Intensity Assessment Using Digital Imaging,” IEEE Trans. Biomed. Eng., vol. 57, pp. 1457-1466.

B. Gholami, W. M. Haddad, and A. R. Tannenbaum, “Agitation and Pain Assessment Using Digital Imaging,” Proc. IEEE Eng. Med. Biolog. Conf., Minneapolis, MN, pp. 2176-2179, 2009 (Awarded National Institute of Biomedical Imaging and Bioengineering/National Institute of Health Student Travel Fellowship).

|-

| | [[Image:MultiObjSeg.png|200px|]]
| |

== [[RobustStatisticsSegmentation|Simultaneous Multiple Object Segmentation using Robust Statistics Features ]] ==

Multiple objects are segmented simultaneously using several interactive active contours based on the feature image which utilizes the robust statistics of the image. [[RobustStatisticsSegmentation|More...]]

|-

| | [[Image:ShapeBasePstSegSlicer.png|200px|]]
| |

== [[Projects:ProstateSegmentation|Prostate Segmentation]] ==

The 3D prostate MRI images are collected by collaborators at Queen’s University. With a little manual initialization, the algorithm provided the results give to the left. The method mainly uses Random Walk algorithm. [[Projects:ProstateSegmentation|More...]]

<font color="red">'''New: '''</font> Y. Gao, A. Tannenbaum; Shape based MRI prostate image segmentation using local information driven directional distance Bayesian method. SPIE Medical Imaging 2010.

|-

| | [[Image:ProstateRegSupineToProneInParaview.png|200px|]]
| |

== [[Projects:pfPtSetImgReg|Particle Filter Registration of Medical Imagery]] ==

3D volumetric image registration is performed. The method is based on registering the images through point sets, which is able to handle long distance between as well as registration between Supine and Prone pose prostate. [[Projects:pfPtSetImgReg|More...]]

<font color="red">'''New: '''</font> Y. Gao, R. Sandhu, G. Fichtinger, A. Tannenbaum; A coupled global registration and segmentation framework with application to magnetic resonance prostate imagery. IEEE TMI vol.29, pp1781, 2010
.

|-

| | [[Image:GT-DWI-Reorientation-1.jpg|200px]]
| |

== [[Projects:DWIReorientation|Re-Orientation Approach for Segmentation of DW-MRI]] ==

This work proposes a methodology to segment tubular fiber bundles from diffusion weighted magnetic resonance images (DW-MRI). Segmentation is simplified by locally reorienting diffusion information based on large-scale fiber bundle geometry. [[Projects:DWIReorientation|More...]]

<font color="red">'''New: '''</font> Near-tubular fiber bundle segmentation for diffusion weighted imaging: segmentation through frame reorientation. Neuroimage, Mar 2009.

|-

| | [[Image:GTTubSurfaceSeg-Img1.png|200px]]
| |

== [[Projects:TubularSurfaceSegmentation|Tubular Surface Segmentation Framework]] ==

We have proposed a new model for tubular surfaces that transforms the problem of detecting a surface in 3D space, to detecting a curve in 4D space. Besides allowing us to impose a "soft" tubular shape prior, this also leads to computational efficiency over conventional surface segmentation approaches. [[Projects:TubularSurfaceSegmentation|More...]]

<font color="red">'''New: '''</font> V. Mohan, G. Sundaramoorthi, M. Kubicki and A. Tannenbaum. Tubular Surface Evolution for Segmentation of the Cingulum Bundle From DW-MRI. September 2008. Proceedings of the Second Workshop on Mathematical Foundations of Computational Anatomy (MFCA'08), Int Conf Med Image Comput Comput Assist Interv. 2008.

<font color="red">'''New: '''</font> V. Mohan, G. Sundaramoorthi, A. Stillman and A. Tannenbaum. Vessel Segmentation with Automatic Centerline Extraction using Tubular Surface Segmentation. September 2009. Proceedings of the Workshop on Cardiac Interventional Imaging and Biophysical Modelling (CI2BM'09), Int Conf Med Image Comput Comput Assist Interv. 2009.

<font color="red">'''New: '''</font> V. Mohan, G. Sundaramoorthi and A. Tannenbaum. Tubular Surface Segmentation for Extracting Anatomical Structures from Medical Imagery (in submission). IEEE Transactions on Medical Imaging.

|-

| | [[Image:GT-PopStudyVis OnCBs Case19-View2.jpg|200px]]
| |

== [[Projects:TubularSurfaceSegmentationPopStudy|Group Study on DW-MRI using the Tubular Surface Model]] ==

We have proposed a new framework for performing group studies on DW-MRI data sets using the Tubular Surface Model of Mohan et al. We successfully apply this framework to discriminating schizophrenic cases from normal controls, as well as towards visualizing the regions of the Cingulum Bundle that are affected by Schizophrenia. [[Projects:TubularSurfaceSegmentationPopStudy|More...]]

<font color="red">'''New: '''</font> V. Mohan, G. Sundaramoorthi, M. Kubicki, D. Terry and A. Tannenbaum. Population Analysis of the Cingulum Bundle using the Tubular Surface Model for Schizophrenia Detection. SPIE Medical Imaging 2010.

<font color="red">'''New: '''</font> V. Mohan, G. Sundaramoorthi, M. Kubicki and A. Tannenbaum. Population Analysis of neural fiber bundles towards schizophrenia detection and characterization, using the Tubular Surface model. Neuroimage (in preparation)

|-

| | [[Image:Model3D_upTrans.png|200px]]
| |

== [[Projects:MGH-HeadAndNeck-RT|Adaptive Radiotherapy for head, neck and thorax]] ==

We proposed an algorithm to include prior knowledge in previously segmented anatomical structures to help in the segmentation of the next structure. This will add enough prior information to allow the Graph Cuts algorithm to segment structures with fuzzy boundaries. [[Projects:MGH-HeadAndNeck-RT|More...]]

<font color="red">'''New: '''</font> I. Kolesov, V. Mohan, G. Sharp and A. Tannenbaum. Coupled Segmentation for Anatomical Structures by Combining Shape and Relational Spatial Information. MTNS 2010.

|-

| | [[Image:Circle seg.PNG|200px|]]
| |

== [[Projects:KPCASegmentation|Kernel PCA for Segmentation]] ==

Segmentation performances using active contours can be drastically improved if the possible shapes of the object of interest are learnt. The goal of this work is to use Kernel PCA to learn shape priors. Kernel PCA allows for learning non linear dependencies in data sets, leading to more robust shape priors. [[Projects:KPCASegmentation|More...]]

<font color="red">'''New: '''</font> S. Dambreville, Y. Rathi, and A. Tannenbaum. A Framework for Image Segmentation using Image Shape Models and Kernel PCA Shape Priors. IEEE Trans Pattern Anal Mach Intell. 2008 Aug;30(8):1385-99

|-
| | [[Image:ZoomedResultWithModel.png|200px]]
| |

== [[Projects:GeodesicTractographySegmentation|Geodesic Tractography Segmentation]] ==

In this work, we provide an energy minimization framework which allows one to find fiber tracts and volumetric fiber bundles in brain diffusion-weighted MRI (DW-MRI). [[Projects:GeodesicTractographySegmentation|More...]]

<font color="red">'''New: '''</font> J. Melonakos, E. Pichon, S. Angenet, and A. Tannenbaum. Finsler Active Contours. IEEE Transactions on Pattern Analysis and Machine Intelligence, March 2008, Vol 30, Num 3.

|-

| | [[Image:P1_small.png|200px|]]
| |

== [[Projects:LabelSpace|Label Space: A Coupled Multi-Shape Representation]] ==

Many techniques for multi-shape representation may often develop inaccuracies stemming from either approximations or inherent variation. Label space is an implicit representation that offers unbiased algebraic manipulation and natural expression of label uncertainty. We demonstrate smoothing and registration on multi-label brain MRI. [[Projects:LabelSpace|More...]]

<font color="red">'''New: '''</font> J. Malcolm, Y. Rathi, A. Tannenbaum. "Label Space: A Multi-Object Shape Representation." In Combinatorial Image Analysis, 2008.

|-

| | [[Image:BasePair3DModel.JPG|200px|]]
| |

== [[Projects:NonParametricClustering|Non Parametric Clustering for Biomolecular Structural Analysis]] ==

High accuracy imaging and image processing techniques allow for collecting structural information of biomolecules with atomistic accuracy. Direct interpretation of the dynamics and the functionality of these structures with physical models, is yet to be developed. Clustering of molecular conformations into classes seems to be the first stage in recovering the formation and the functionality of these molecules. [[Projects:NonParametricClustering|More...]]

<font color="red">'''New: '''</font> E. Hershkovits, A. Tannenbaum, and R. Tannenbaum. Adsorption of Block Copolymers from Selective Solvents on Curved Surfaces. Macromolecules. 2008.

|-

| | [[Image:TruckInitialization.png|200px|]]
| |

== [[Projects:PointSetRigidRegistration|Point Set Rigid Registration]] ==

In this work, we propose a particle filtering approach for the problem of registering two point sets that differ by
a rigid body transformation. Experimental results are provided that demonstrate the robustness of the algorithm to initialization, noise, missing structures or differing point densities in each sets, on challenging 2D and 3D registration tasks. [[Projects:PointSetRigidRegistration|More...]]

<font color="red">'''New: '''</font> R. Sandhu, S. Dambreville, A. Tannenbaum. Particle Filtering for Registration of 2D and 3D Point Sets with Stochastic Dynamics. In CVPR, 2008.

|-

| | [[Image:Results brain sag.JPG|200px]]
| |

== [[Projects:OptimalMassTransportRegistration|Optimal Mass Transport Registration]] ==

The goal of this project is to implement a computationaly efficient Elastic/Non-rigid Registration algorithm based on the Monge-Kantorovich theory of optimal mass transport for 3D Medical Imagery. Our technique is based on Multigrid and Multiresolution techniques. This method is particularly useful because it is parameter free and utilizes all of the grayscale data in the image pairs in a symmetric fashion and no landmarks need to be specified for correspondence. [[Projects:OptimalMassTransportRegistration|More...]]

<font color="red">'''New: '''</font> Eldad Haber, Tauseef Rehman, and Allen Tannenbaum. An Efficient Numerical Method for the Solution of the L2 Optimal Mass Transfer Problem. In submission - SIAM Journal of Scientific Computing, 2009.

<font color="red">'''New: '''</font> Tauseef Rehman, Eldad Haber, Gallagher Pryor, and Allen Tannenbaum. Fast Optimal Mass Transport for 2D Image Registration and Morphing. Accepted for - Elsevier Journal of Image and Vision Computing, 2009.

|-

| | [[Image:Gatech caudateBands.PNG|200px]]
| |

== [[Projects:MultiscaleShapeSegmentation|Multiscale Shape Segmentation Techniques]] ==

To represent multiscale variations in a shape population in order to drive the segmentation of deep brain structures, such as the caudate nucleus or the hippocampus. [[Projects:MultiscaleShapeSegmentation|More...]]

|-

| | [[Image:Caudate Nucleus Denoising.JPG|200px|]]
| |

== [[Projects:WaveletShrinkage|Wavelet Shrinkage for Shape Analysis]] ==

Shape analysis has become a topic of interest in medical imaging since local variations of a shape could carry relevant information about a disease that may affect only a portion of an organ. We developed a novel wavelet-based denoising and compression statistical model for 3D shapes. [[Projects:WaveletShrinkage|More...]]

|-

| | [[Image:Basis membership.png|200px]]
| |

== [[Projects:MultiscaleShapeAnalysis|Multiscale Shape Analysis]] ==

We present a novel method of statistical surface-based morphometry based on the use of non-parametric permutation tests and a spherical wavelet (SWC) shape representation. [[Projects:MultiscaleShapeAnalysis|More...]]

|-

| | [[Image:Dlpfc1.jpg|200px|]]
| |

== [[Projects:RuleBasedDLPFCSegmentation|Rule-Based DLPFC Segmentation]] ==

In this work, we provide software to semi-automate the implementation of segmentation procedures based on expert neuroanatomist rules for the dorsolateral prefrontal cortex. [[Projects:RuleBasedDLPFCSegmentation|More...]]

|-

| | [[Image:Striatum1.png|200px|]]
| |

== [[Projects:RuleBasedStriatumSegmentation|Rule-Based Striatum Segmentation]] ==

In this work, we provide software to semi-automate the implementation of segmentation procedures based on expert neuroanatomist rules for the striatum. [[Projects:RuleBasedStriatumSegmentation|More...]]

|-

| | [[Image:Brain-flat.PNG|200px]]
| |

== [[Projects:ConformalFlatteningRegistration|Conformal Flattening (inactive)]] ==

The goal of this project is for better visualizing and computation of neural activity from fMRI brain imagery. Also, with this technique, shapes can be mapped to shperes for shape analysis, registration or other purposes. Our technique is based on conformal mappings which map genus-zero surface: in fmri case cortical or other surfaces, onto a sphere in an angle preserving manner. [[Projects:ConformalFlatteningRegistration|More...]]

|-

| | [[Image:Fig1yan.PNG|200px|]]
| |

== [[Projects:BloodVesselSegmentation|Blood Vessel Segmentation]] ==

The goal of this work is to develop blood vessel segmentation techniques for 3D MRI and CT data. The methods have been applied to coronary arteries and portal veins, with promising results. [[Projects:BloodVesselSegmentation|More...]]

<font color="red">'''New: '''</font> V.Mohan, G. Sundaramoorthi, A. Stillman and A. Tannenbaum. Vessel Segmentation with Automatic Centerline Extraction Using Tubular Tree Segmentation. CI2BM at MICCAI 2009, September 2009.

|-

| | [[Image:Fig67.png|200px|]]
| |

== [[Projects:KnowledgeBasedBayesianSegmentation|Knowledge-Based Bayesian Segmentation]] ==

This ITK filter is a segmentation algorithm that utilizes Bayes's Rule along with an affine-invariant anisotropic smoothing filter. [[Projects:KnowledgeBasedBayesianSegmentation|More...]]

|-

| | [[Image:Stochastic-snake.png|200px|]]
| |

== [[Projects:StochasticMethodsSegmentation|Stochastic Methods for Segmentation]] ==

New stochastic methods for implementing curvature driven flows for various medical tasks such as segmentation. [[Projects:StochasticMethodsSegmentation|More...]]

|-

| | [[Image:GT-SulciOutlining1.jpg|200px]]
| |

== [[Projects:SulciOutlining|Automatic Outlining of sulci on the brain surface]] ==

We present a method to automatically extract certain key features on a surface. We apply this technique to outline sulci on the cortical surface of a brain. [[Projects:SulciOutlining|More...]]

|-

| | [[Image:Table1.png|200px|]]
| |

== [[Projects:KPCA_LLE_KLLE_ShapeAnalysis|KPCA, LLE, KLLE Shape Analysis]] ==

The goal of this work is to study and compare shape learning techniques. The techniques considered are Linear Principal Components Analysis (PCA), Kernel PCA, Locally Linear Embedding (LLE) and Kernel LLE. [[Projects:KPCA_LLE_KLLE_ShapeAnalysis|More...]]

|-

| | [[Image:Gatech SlicerModel2.jpg|200px]]
| |

== [[Projects:StatisticalSegmentationSlicer2|Statistical/PDE Methods using Fast Marching for Segmentation]] ==

This Fast Marching based flow was added to Slicer 2. [[Projects:StatisticalSegmentationSlicer2|More...]]

|}

Algorithm:BU

2011-10-17T14:51:15Z

Yflou: /* Boston University Projects */

Back to [[Algorithm:Main|NA-MIC Algorithms]]
__NOTOC__
= Overview of Boston University Algorithms (PI: Allen Tannenbaum) =

At Boston University, we are broadly interested in a range of mathematical image analysis algorithms for segmentation, registration, diffusion-weighted MRI analysis, and statistical analysis. For many applications, we cast the problem in an energy minimization framework wherein we define a partial differential equation whose numeric solution corresponds to the desired algorithmic outcome. The following are many examples of PDE techniques applied to medical image analysis.

= Boston University Projects =

{| cellpadding="10" style="text-align:left;"

| | [[Image:GT-SPD-img1.png|200px|]]
| |

== [[Projects:Multimodal Deformable Registration of Traumatic Brain Injury MR Volumes using Graphics Processing Units]] ==
Time-efficient processing and analysis of magnetic resonance imaging (MRI) volumes can be critical for both medical diagnosis as well as for the formulation of acute treatment
strategies whenever such strategies rely heavily upon information provided by neuroimaging data. One context where such efficiency is desirable is for the neurocritical care and monitoring of traumatic brain injury (TBI) patients. An important problem of TBI neuroimaging data analysis is the task of co-registering MR volumes acquired using distinct sequences in the presence of widely variable pixel intensities that are due to the presence of pathology. Here we address this important and challenging problems using an implementation of multimodal deformable registration on graphics processing units (GPU). We follow a viscous fluid model framework and replace mutual information with the Bhattacharyya distance as the measure of similarity between image volumes. The proposed algorithm is implemented on a GPU and its robustness is illustrated using a longitudinal multimodal TBI dataset, where we find that 6 seconds are required to register a pair of volumes with matrix sizes of $256\times256\times60$ using our method. In addition to exceptional time efficiency via its GPU implementation, this methodology provides a clinically informative method for the mapping and evaluation of anatomical changes in TBI. [[Projects:SoftPlaqueDetection|More...]]

<font color="red">'''New: '''</font> Soft Plaque Detection and Automatic Vessel Segmentation. PMMIA Workshop in MICCAI, Sep. 2009.
|-

| | [[Image:MultiScaleHippoSegmentationHausdorf.png|200px]]
| |

== [[Projects:MultiScaleShapeSegmentation|Multi-scale Shape Representation and Segmentation With Applications to Radiotherapy]] ==

We present in this work a multiscale representation for shapes with arbitrary topology, and a method to segment the target organ/tissue from medical images having very low contrast with respect to surrounding regions using multiscale shape information and local image features. In a number of previous papers, shape knowledge was incorporated by first constructing a shape space from training data, and then constraining the segmentation process to be within the resulting shape space. However, such an approach has certain limitations including the fact that small scale shape variances may be overwhelmed by those on larger scale, and therefore the local shape information is lost. In this work, first we handle this problem by providing a multiscale shape representation using the wavelet transform. Consequently, the shape variances captured by the statistical learning step are also represented at various scales. In doing so, not only is the diversity of shape enriched, but also small scale changes are nicely captured. [[Projects:MultiScaleShapeSegmentation|More...]]

|-

| | [[Image:GT-SPD-img1.png|200px|]]
| |

== [[Projects:SoftPlaqueDetection|Soft Plaque Detection in CTA Imagery]] ==

The ability to detect and measure non-calciﬁed plaques (also known as soft plaques) may improve physicians’ ability to predict cardiac events. This work automatically detects soft plaques in CTA imagery using active contours driven by spatially localized probabilistic models. Plaques are identified by simultaneously segmenting the vessel from the inside-out and the outside-in using carefully chosen localized energies [[Projects:SoftPlaqueDetection|More...]]

<font color="red">'''New: '''</font> Soft Plaque Detection and Automatic Vessel Segmentation. PMMIA Workshop in MICCAI, Sep. 2009.
|-

| | [[Image:3D_Segmentation_LA.png|200px]]
| |

== [[Projects:SegmentationEndocardialWall|Segmentation of the Left Atrial Wall for Atrial Fibrillation Ablation Therapy]] ==

Magnetic resonance imaging (MRI) has been used for both pre- and and post-ablation assessment of the atrial wall. MRI can aid in selecting the right candidate for the ablation procedure and assessing post-ablation scar formations. Image processing techniques can be used for automatic segmentation of the atrial wall, which facilitates an accurate statistical assessment of the region. As a first step towards the general solution to the computer-assisted segmentation of the left atrial wall, in this research we propose a shape-based image segmentation framework to segment the endocardial wall of the left atrium.[[Projects:SegmentationEpicardialWall|More...]]

<font color="red">'''New: '''</font> Y. Gao, B. Gholami, R. S. MacLeod, J, Blauer, W. M. Haddad, and A. R. Tannenbaum, Segmentation of the Endocardial Wall of the Left Atrium using Local Region-Based Active Contours and Statistical Shape Learning, SPIE Medical Imaging, San Diego, CA, 2010.

|-

| | [[Image:Pain1.JPG|200px]]
| |

== [[Projects:PainAssessment|Agitation and Pain Assessment Using Digital Imaging]] ==

Pain assessment in patients who are unable to verbally
communicate with medical staff is a challenging problem
in patient critical care. The fundamental limitations in sedation
and pain assessment in the intensive care unit (ICU) stem
from subjective assessment criteria, rather than quantifiable,
measurable data for ICU sedation and analgesia. This often
results in poor quality and inconsistent treatment of patient
agitation and pain from nurse to nurse. Recent advancements in
pattern recognition techniques using a relevance vector machine
algorithm can assist medical staff in assessing sedation and pain
by constantly monitoring the patient and providing the clinician
with quantifiable data for ICU sedation. In this paper, we show
that the pain intensity assessment given by a computer classifier
has a strong correlation with the pain intensity assessed by
expert and non-expert human examiners.[[Projects:PainAssessment|More...]]

<font color="red">'''New: '''</font> B. Gholami, W. M. Haddad, and A. Tannenbaum, “Relevance Vector Machine Learning for Neonate Pain Intensity Assessment Using Digital Imaging,” IEEE Trans. Biomed. Eng., vol. 57, pp. 1457-1466.

B. Gholami, W. M. Haddad, and A. R. Tannenbaum, “Agitation and Pain Assessment Using Digital Imaging,” Proc. IEEE Eng. Med. Biolog. Conf., Minneapolis, MN, pp. 2176-2179, 2009 (Awarded National Institute of Biomedical Imaging and Bioengineering/National Institute of Health Student Travel Fellowship).

|-

| | [[Image:MultiObjSeg.png|200px|]]
| |

== [[RobustStatisticsSegmentation|Simultaneous Multiple Object Segmentation using Robust Statistics Features ]] ==

Multiple objects are segmented simultaneously using several interactive active contours based on the feature image which utilizes the robust statistics of the image. [[RobustStatisticsSegmentation|More...]]

|-

| | [[Image:ShapeBasePstSegSlicer.png|200px|]]
| |

== [[Projects:ProstateSegmentation|Prostate Segmentation]] ==

The 3D prostate MRI images are collected by collaborators at Queen’s University. With a little manual initialization, the algorithm provided the results give to the left. The method mainly uses Random Walk algorithm. [[Projects:ProstateSegmentation|More...]]

<font color="red">'''New: '''</font> Y. Gao, A. Tannenbaum; Shape based MRI prostate image segmentation using local information driven directional distance Bayesian method. SPIE Medical Imaging 2010.

|-

| | [[Image:ProstateRegSupineToProneInParaview.png|200px|]]
| |

== [[Projects:pfPtSetImgReg|Particle Filter Registration of Medical Imagery]] ==

3D volumetric image registration is performed. The method is based on registering the images through point sets, which is able to handle long distance between as well as registration between Supine and Prone pose prostate. [[Projects:pfPtSetImgReg|More...]]

<font color="red">'''New: '''</font> Y. Gao, R. Sandhu, G. Fichtinger, A. Tannenbaum; A coupled global registration and segmentation framework with application to magnetic resonance prostate imagery. IEEE TMI vol.29, pp1781, 2010
.

|-

| | [[Image:GT-DWI-Reorientation-1.jpg|200px]]
| |

== [[Projects:DWIReorientation|Re-Orientation Approach for Segmentation of DW-MRI]] ==

This work proposes a methodology to segment tubular fiber bundles from diffusion weighted magnetic resonance images (DW-MRI). Segmentation is simplified by locally reorienting diffusion information based on large-scale fiber bundle geometry. [[Projects:DWIReorientation|More...]]

<font color="red">'''New: '''</font> Near-tubular fiber bundle segmentation for diffusion weighted imaging: segmentation through frame reorientation. Neuroimage, Mar 2009.

|-

| | [[Image:GTTubSurfaceSeg-Img1.png|200px]]
| |

== [[Projects:TubularSurfaceSegmentation|Tubular Surface Segmentation Framework]] ==

We have proposed a new model for tubular surfaces that transforms the problem of detecting a surface in 3D space, to detecting a curve in 4D space. Besides allowing us to impose a "soft" tubular shape prior, this also leads to computational efficiency over conventional surface segmentation approaches. [[Projects:TubularSurfaceSegmentation|More...]]

<font color="red">'''New: '''</font> V. Mohan, G. Sundaramoorthi, M. Kubicki and A. Tannenbaum. Tubular Surface Evolution for Segmentation of the Cingulum Bundle From DW-MRI. September 2008. Proceedings of the Second Workshop on Mathematical Foundations of Computational Anatomy (MFCA'08), Int Conf Med Image Comput Comput Assist Interv. 2008.

<font color="red">'''New: '''</font> V. Mohan, G. Sundaramoorthi, A. Stillman and A. Tannenbaum. Vessel Segmentation with Automatic Centerline Extraction using Tubular Surface Segmentation. September 2009. Proceedings of the Workshop on Cardiac Interventional Imaging and Biophysical Modelling (CI2BM'09), Int Conf Med Image Comput Comput Assist Interv. 2009.

<font color="red">'''New: '''</font> V. Mohan, G. Sundaramoorthi and A. Tannenbaum. Tubular Surface Segmentation for Extracting Anatomical Structures from Medical Imagery (in submission). IEEE Transactions on Medical Imaging.

|-

| | [[Image:GT-PopStudyVis OnCBs Case19-View2.jpg|200px]]
| |

== [[Projects:TubularSurfaceSegmentationPopStudy|Group Study on DW-MRI using the Tubular Surface Model]] ==

We have proposed a new framework for performing group studies on DW-MRI data sets using the Tubular Surface Model of Mohan et al. We successfully apply this framework to discriminating schizophrenic cases from normal controls, as well as towards visualizing the regions of the Cingulum Bundle that are affected by Schizophrenia. [[Projects:TubularSurfaceSegmentationPopStudy|More...]]

<font color="red">'''New: '''</font> V. Mohan, G. Sundaramoorthi, M. Kubicki, D. Terry and A. Tannenbaum. Population Analysis of the Cingulum Bundle using the Tubular Surface Model for Schizophrenia Detection. SPIE Medical Imaging 2010.

<font color="red">'''New: '''</font> V. Mohan, G. Sundaramoorthi, M. Kubicki and A. Tannenbaum. Population Analysis of neural fiber bundles towards schizophrenia detection and characterization, using the Tubular Surface model. Neuroimage (in preparation)

|-

| | [[Image:Model3D_upTrans.png|200px]]
| |

== [[Projects:MGH-HeadAndNeck-RT|Adaptive Radiotherapy for head, neck and thorax]] ==

We proposed an algorithm to include prior knowledge in previously segmented anatomical structures to help in the segmentation of the next structure. This will add enough prior information to allow the Graph Cuts algorithm to segment structures with fuzzy boundaries. [[Projects:MGH-HeadAndNeck-RT|More...]]

<font color="red">'''New: '''</font> I. Kolesov, V. Mohan, G. Sharp and A. Tannenbaum. Coupled Segmentation for Anatomical Structures by Combining Shape and Relational Spatial Information. MTNS 2010.

|-

| | [[Image:Circle seg.PNG|200px|]]
| |

== [[Projects:KPCASegmentation|Kernel PCA for Segmentation]] ==

Segmentation performances using active contours can be drastically improved if the possible shapes of the object of interest are learnt. The goal of this work is to use Kernel PCA to learn shape priors. Kernel PCA allows for learning non linear dependencies in data sets, leading to more robust shape priors. [[Projects:KPCASegmentation|More...]]

<font color="red">'''New: '''</font> S. Dambreville, Y. Rathi, and A. Tannenbaum. A Framework for Image Segmentation using Image Shape Models and Kernel PCA Shape Priors. IEEE Trans Pattern Anal Mach Intell. 2008 Aug;30(8):1385-99

|-
| | [[Image:ZoomedResultWithModel.png|200px]]
| |

== [[Projects:GeodesicTractographySegmentation|Geodesic Tractography Segmentation]] ==

In this work, we provide an energy minimization framework which allows one to find fiber tracts and volumetric fiber bundles in brain diffusion-weighted MRI (DW-MRI). [[Projects:GeodesicTractographySegmentation|More...]]

<font color="red">'''New: '''</font> J. Melonakos, E. Pichon, S. Angenet, and A. Tannenbaum. Finsler Active Contours. IEEE Transactions on Pattern Analysis and Machine Intelligence, March 2008, Vol 30, Num 3.

|-

| | [[Image:P1_small.png|200px|]]
| |

== [[Projects:LabelSpace|Label Space: A Coupled Multi-Shape Representation]] ==

Many techniques for multi-shape representation may often develop inaccuracies stemming from either approximations or inherent variation. Label space is an implicit representation that offers unbiased algebraic manipulation and natural expression of label uncertainty. We demonstrate smoothing and registration on multi-label brain MRI. [[Projects:LabelSpace|More...]]

<font color="red">'''New: '''</font> J. Malcolm, Y. Rathi, A. Tannenbaum. "Label Space: A Multi-Object Shape Representation." In Combinatorial Image Analysis, 2008.

|-

| | [[Image:BasePair3DModel.JPG|200px|]]
| |

== [[Projects:NonParametricClustering|Non Parametric Clustering for Biomolecular Structural Analysis]] ==

High accuracy imaging and image processing techniques allow for collecting structural information of biomolecules with atomistic accuracy. Direct interpretation of the dynamics and the functionality of these structures with physical models, is yet to be developed. Clustering of molecular conformations into classes seems to be the first stage in recovering the formation and the functionality of these molecules. [[Projects:NonParametricClustering|More...]]

<font color="red">'''New: '''</font> E. Hershkovits, A. Tannenbaum, and R. Tannenbaum. Adsorption of Block Copolymers from Selective Solvents on Curved Surfaces. Macromolecules. 2008.

|-

| | [[Image:TruckInitialization.png|200px|]]
| |

== [[Projects:PointSetRigidRegistration|Point Set Rigid Registration]] ==

In this work, we propose a particle filtering approach for the problem of registering two point sets that differ by
a rigid body transformation. Experimental results are provided that demonstrate the robustness of the algorithm to initialization, noise, missing structures or differing point densities in each sets, on challenging 2D and 3D registration tasks. [[Projects:PointSetRigidRegistration|More...]]

<font color="red">'''New: '''</font> R. Sandhu, S. Dambreville, A. Tannenbaum. Particle Filtering for Registration of 2D and 3D Point Sets with Stochastic Dynamics. In CVPR, 2008.

|-

| | [[Image:Results brain sag.JPG|200px]]
| |

== [[Projects:OptimalMassTransportRegistration|Optimal Mass Transport Registration]] ==

The goal of this project is to implement a computationaly efficient Elastic/Non-rigid Registration algorithm based on the Monge-Kantorovich theory of optimal mass transport for 3D Medical Imagery. Our technique is based on Multigrid and Multiresolution techniques. This method is particularly useful because it is parameter free and utilizes all of the grayscale data in the image pairs in a symmetric fashion and no landmarks need to be specified for correspondence. [[Projects:OptimalMassTransportRegistration|More...]]

<font color="red">'''New: '''</font> Eldad Haber, Tauseef Rehman, and Allen Tannenbaum. An Efficient Numerical Method for the Solution of the L2 Optimal Mass Transfer Problem. In submission - SIAM Journal of Scientific Computing, 2009.

<font color="red">'''New: '''</font> Tauseef Rehman, Eldad Haber, Gallagher Pryor, and Allen Tannenbaum. Fast Optimal Mass Transport for 2D Image Registration and Morphing. Accepted for - Elsevier Journal of Image and Vision Computing, 2009.

|-

| | [[Image:Gatech caudateBands.PNG|200px]]
| |

== [[Projects:MultiscaleShapeSegmentation|Multiscale Shape Segmentation Techniques]] ==

To represent multiscale variations in a shape population in order to drive the segmentation of deep brain structures, such as the caudate nucleus or the hippocampus. [[Projects:MultiscaleShapeSegmentation|More...]]

|-

| | [[Image:Caudate Nucleus Denoising.JPG|200px|]]
| |

== [[Projects:WaveletShrinkage|Wavelet Shrinkage for Shape Analysis]] ==

Shape analysis has become a topic of interest in medical imaging since local variations of a shape could carry relevant information about a disease that may affect only a portion of an organ. We developed a novel wavelet-based denoising and compression statistical model for 3D shapes. [[Projects:WaveletShrinkage|More...]]

|-

| | [[Image:Basis membership.png|200px]]
| |

== [[Projects:MultiscaleShapeAnalysis|Multiscale Shape Analysis]] ==

We present a novel method of statistical surface-based morphometry based on the use of non-parametric permutation tests and a spherical wavelet (SWC) shape representation. [[Projects:MultiscaleShapeAnalysis|More...]]

|-

| | [[Image:Dlpfc1.jpg|200px|]]
| |

== [[Projects:RuleBasedDLPFCSegmentation|Rule-Based DLPFC Segmentation]] ==

In this work, we provide software to semi-automate the implementation of segmentation procedures based on expert neuroanatomist rules for the dorsolateral prefrontal cortex. [[Projects:RuleBasedDLPFCSegmentation|More...]]

|-

| | [[Image:Striatum1.png|200px|]]
| |

== [[Projects:RuleBasedStriatumSegmentation|Rule-Based Striatum Segmentation]] ==

In this work, we provide software to semi-automate the implementation of segmentation procedures based on expert neuroanatomist rules for the striatum. [[Projects:RuleBasedStriatumSegmentation|More...]]

|-

| | [[Image:Brain-flat.PNG|200px]]
| |

== [[Projects:ConformalFlatteningRegistration|Conformal Flattening (inactive)]] ==

The goal of this project is for better visualizing and computation of neural activity from fMRI brain imagery. Also, with this technique, shapes can be mapped to shperes for shape analysis, registration or other purposes. Our technique is based on conformal mappings which map genus-zero surface: in fmri case cortical or other surfaces, onto a sphere in an angle preserving manner. [[Projects:ConformalFlatteningRegistration|More...]]

|-

| | [[Image:Fig1yan.PNG|200px|]]
| |

== [[Projects:BloodVesselSegmentation|Blood Vessel Segmentation]] ==

The goal of this work is to develop blood vessel segmentation techniques for 3D MRI and CT data. The methods have been applied to coronary arteries and portal veins, with promising results. [[Projects:BloodVesselSegmentation|More...]]

<font color="red">'''New: '''</font> V.Mohan, G. Sundaramoorthi, A. Stillman and A. Tannenbaum. Vessel Segmentation with Automatic Centerline Extraction Using Tubular Tree Segmentation. CI2BM at MICCAI 2009, September 2009.

|-

| | [[Image:Fig67.png|200px|]]
| |

== [[Projects:KnowledgeBasedBayesianSegmentation|Knowledge-Based Bayesian Segmentation]] ==

This ITK filter is a segmentation algorithm that utilizes Bayes's Rule along with an affine-invariant anisotropic smoothing filter. [[Projects:KnowledgeBasedBayesianSegmentation|More...]]

|-

| | [[Image:Stochastic-snake.png|200px|]]
| |

== [[Projects:StochasticMethodsSegmentation|Stochastic Methods for Segmentation]] ==

New stochastic methods for implementing curvature driven flows for various medical tasks such as segmentation. [[Projects:StochasticMethodsSegmentation|More...]]

|-

| | [[Image:GT-SulciOutlining1.jpg|200px]]
| |

== [[Projects:SulciOutlining|Automatic Outlining of sulci on the brain surface]] ==

We present a method to automatically extract certain key features on a surface. We apply this technique to outline sulci on the cortical surface of a brain. [[Projects:SulciOutlining|More...]]

|-

| | [[Image:Table1.png|200px|]]
| |

== [[Projects:KPCA_LLE_KLLE_ShapeAnalysis|KPCA, LLE, KLLE Shape Analysis]] ==

The goal of this work is to study and compare shape learning techniques. The techniques considered are Linear Principal Components Analysis (PCA), Kernel PCA, Locally Linear Embedding (LLE) and Kernel LLE. [[Projects:KPCA_LLE_KLLE_ShapeAnalysis|More...]]

|-

| | [[Image:Gatech SlicerModel2.jpg|200px]]
| |

== [[Projects:StatisticalSegmentationSlicer2|Statistical/PDE Methods using Fast Marching for Segmentation]] ==

This Fast Marching based flow was added to Slicer 2. [[Projects:StatisticalSegmentationSlicer2|More...]]

|}

Multimodality Image Registration for TBI

2011-06-24T14:28:34Z

Yflou: /* Key Investigators */

__NOTOC__
<gallery>
Image:PW-MIT2011.png|[[2011_Summer_Project_Week#Projects|Projects List]]
Image::BRAINSCutFigure.png|BRAINSCut Result Example
Image:t1e1.png|T1 exam1
Image:t1e2.png|T1 exam2
Image:t1e1deformedM.png|T1 deformed
</gallery>

'''Multimodality Image Registration for Traumatic Brain Injury (TBI)'''

==Key Investigators==
* Georgia Tech: Yifei Lou and Allen Tannenbaum
* UCLA: Micah Chambers, Andrei Irimia

<div style="margin: 20px;">
<div style="width: 27%; float: left; padding-right: 3%;">

<h3>Objective</h3>

* Understanding brain injury using (multimodal) deformable image registration
* Robust registrations inspire of topological changes (enforcing zero flow?)
* The algorithm is based on a viscous fluid model, which can handle larger deformable as compared to the B-spline type of methods
* CUDA-based implementation, which takes 1 min for 256x256x60

</div>

<div style="width: 27%; float: left; padding-right: 3%;">

<h3>Approach, Plan</h3>

* Integration into Slicer3 Module
* Learn more about TBI and our data set from Micah (UCLA NA-MIC TBI DBP team member)
* Validate algorithm on additional TBI datasets from UCLA

</div>

<div style="width: 40%; float: left;">

<h3>Progress</h3>

* Learn more about TBI and ITK/Slicer
* Demonstrate the efficiency of my algorithm on TBI data
* Its failure in one registration case suggests us dividing 12 modalities into 2 subgroups and co-register within group
* plan to write a paper and integrate my algorithm into ITK/Slicer



</div>
</div>

<div style="width: 97%; float: left;">

==References==
'''1''' Yifei Lou and Allen Tannenbaum. Multimodal Deformable Image Registration via the Bhattacharyya Distance. Submitted to IEEE Trans. Image Process. 2011

'''2''' Yifei Lou, Xun Jia, Xuejun Gu and Allen Tannenbaum. A GPU-based Implementation of Multimodal Deformable Image Registration Based on Mutual Information or Bhattacharyya Distance. Insight Journal, 2011. [[http://www.midasjournal.org/browse/publication/803]]
</div>
==Delivery Mechanism==



This work will be delivered to the NAMIC Kit as a

#NITRIC distribution
#Slicer Module
##Built-in: NO
##Extension -- commandline: NO
##Extension -- loadable: NO

Multimodality Image Registration for TBI

2011-06-24T13:37:13Z

Yflou: /* Key Investigators */

__NOTOC__
<gallery>
Image:PW-MIT2011.png|[[2011_Summer_Project_Week#Projects|Projects List]]
Image::BRAINSCutFigure.png|BRAINSCut Result Example
Image:t1e1.png|T1 exam1
Image:t1e2.png|T1 exam2
Image:t1e1deformedM.png|T1 deformed
</gallery>

'''Multimodality Image Registration for Traumatic Brain Injury (TBI)'''

==Key Investigators==
* Georgia Tech: Yifei Lou and Allen Tannenbaum
* Micah Chambers: UCLA

<div style="margin: 20px;">
<div style="width: 27%; float: left; padding-right: 3%;">

<h3>Objective</h3>

* Understanding brain injury using (multimodal) deformable image registration
* Robust registrations inspire of topological changes (enforcing zero flow?)
* The algorithm is based on a viscous fluid model, which can handle larger deformable as compared to the B-spline type of methods
* CUDA-based implementation, which takes 1 min for 256x256x60

</div>

<div style="width: 27%; float: left; padding-right: 3%;">

<h3>Approach, Plan</h3>

* Integration into Slicer3 Module
* Learn more about TBI and our data set from Micah (UCLA NA-MIC TBI DBP team member)
* Validate algorithm on additional TBI datasets from UCLA

</div>

<div style="width: 40%; float: left;">

<h3>Progress</h3>

* Learn more about TBI and ITK/Slicer
* Demonstrate the efficiency of my algorithm on TBI data
* Its failure in one registration case suggests us dividing 12 modalities into 2 subgroups and co-register within group
* plan to write a paper and integrate my algorithm into ITK/Slicer



</div>
</div>

<div style="width: 97%; float: left;">

==References==
'''1''' Yifei Lou and Allen Tannenbaum. Multimodal Deformable Image Registration via the Bhattacharyya Distance. Submitted to IEEE Trans. Image Process. 2011

'''2''' Yifei Lou, Xun Jia, Xuejun Gu and Allen Tannenbaum. A GPU-based Implementation of Multimodal Deformable Image Registration Based on Mutual Information or Bhattacharyya Distance. Insight Journal, 2011. [[http://www.midasjournal.org/browse/publication/803]]
</div>
==Delivery Mechanism==



This work will be delivered to the NAMIC Kit as a

#NITRIC distribution
#Slicer Module
##Built-in: NO
##Extension -- commandline: NO
##Extension -- loadable: NO

Multimodality Image Registration for TBI

2011-06-24T13:33:46Z

Yflou: /* Key Investigators */

__NOTOC__
<gallery>
Image:PW-MIT2011.png|[[2011_Summer_Project_Week#Projects|Projects List]]
Image::BRAINSCutFigure.png|BRAINSCut Result Example
Image:t1e1.png|T1 exam1
Image:t1e2.png|T1 exam2
Image:t1e1deformedM.png|T1 deformed
</gallery>

'''Multimodality Image Registration for Traumatic Brain Injury (TBI)'''

==Key Investigators==
* Georgia Tech: Yifei Lou and Allen Tannenbaum
* Micah Chambers: UCLA

<div style="margin: 20px;">
<div style="width: 27%; float: left; padding-right: 3%;">

<h3>Objective</h3>

* Understanding brain injury using (multimodal) deformable image registration
* Robust registrations inspire of topological changes (enforcing zero flow?)
* The algorithm is based on a viscous fluid model, which can handle larger deformable as compared to the B-spline type of methods
* CUDA-based implementation, which takes 1 min for 256x256x60

</div>

<div style="width: 27%; float: left; padding-right: 3%;">

<h3>Approach, Plan</h3>

* Integration into Slicer3 Module
* Learn more about TBI and our data set from Micah (UCLA NA-MIC TBI DBP team member)
* Validate algorithm on additional TBI datasets from UCLA

</div>

<div style="width: 40%; float: left;">

<h3>Progress</h3>

* Demonstrate the efficiency of my algorithm on TBI data
* Its failure in one registration case suggests us dividing 12 modalities into 2 subgroups and co-register within group
* plan to write a paper



</div>
</div>

<div style="width: 97%; float: left;">

==References==
'''1''' Yifei Lou and Allen Tannenbaum. Multimodal Deformable Image Registration via the Bhattacharyya Distance. Submitted to IEEE Trans. Image Process. 2011

'''2''' Yifei Lou, Xun Jia, Xuejun Gu and Allen Tannenbaum. A GPU-based Implementation of Multimodal Deformable Image Registration Based on Mutual Information or Bhattacharyya Distance. Insight Journal, 2011. [[http://www.midasjournal.org/browse/publication/803]]
</div>
==Delivery Mechanism==



This work will be delivered to the NAMIC Kit as a

#NITRIC distribution
#Slicer Module
##Built-in: NO
##Extension -- commandline: NO
##Extension -- loadable: NO

Multimodality Image Registration for TBI

2011-06-20T17:01:58Z

Yflou: /* Key Investigators */

__NOTOC__
<gallery>
Image:PW-MIT2011.png|[[2011_Summer_Project_Week#Projects|Projects List]]
Image::BRAINSCutFigure.png|BRAINSCut Result Example
Image:t1e1.png|T1 exam1
Image:t1e2.png|T1 exam2
Image:t1e1deformedM.png|T1 deformed
</gallery>

'''Multimodality Image Registration for Traumatic Brain Injury (TBI)'''

==Key Investigators==
* Georgia Tech: Yifei Lou and Allen Tannenbaum
* Micah Chambers: UCLA

<div style="margin: 20px;">
<div style="width: 27%; float: left; padding-right: 3%;">

<h3>Objective</h3>

* Understanding brain injury using (multimodal) deformable image registration
* Robust registrations inspire of topological changes (enforcing zero flow?)
* The algorithm is based on a viscous fluid model, which can handle larger deformable as compared to the B-spline type of methods
* CUDA-based implementation, which takes 1 min for 256x256x60

</div>

<div style="width: 27%; float: left; padding-right: 3%;">

<h3>Approach, Plan</h3>

* Integration into Slicer3 Module
* Validate algorithm on various datasets

</div>

<div style="width: 40%; float: left;">

<h3>Progress</h3>



</div>
</div>

<div style="width: 97%; float: left;">

==References==
'''1''' Yifei Lou and Allen Tannenbaum. Multimodal Deformable Image Registration via the Bhattacharyya Distance. Submitted to IEEE Trans. Image Process. 2011

'''2''' Yifei Lou, Xun Jia, Xuejun Gu and Allen Tannenbaum. A GPU-based Implementation of Multimodal Deformable Image Registration Based on Mutual Information or Bhattacharyya Distance. Insight Journal, 2011. [[http://www.midasjournal.org/browse/publication/803]]
</div>
==Delivery Mechanism==



This work will be delivered to the NAMIC Kit as a

#NITRIC distribution
#Slicer Module
##Built-in: NO
##Extension -- commandline: NO
##Extension -- loadable: NO

File:T1e1deformedM.png

2011-06-20T16:55:56Z

Yflou:

File:T1e2.png

2011-06-20T16:55:43Z

Yflou:

File:T1e1.png

2011-06-20T16:54:59Z

Yflou: uploaded a new version of "File:T1e1.png"

File:T1e1.png

2011-06-20T16:53:32Z

Yflou:

Multimodality Image Registration for TBI

2011-06-20T16:52:56Z

Yflou:

__NOTOC__
<gallery>
Image:PW-MIT2011.png|[[2011_Summer_Project_Week#Projects|Projects List]]
Image::BRAINSCutFigure.png|BRAINSCut Result Example
Image:t1e1.png|T1 exam1
Image:t1e2.png|T1 exam2
Image:t1e1deformedM.png|T1 deformed
</gallery>

'''Multimodality Image Registration for Traumatic Brain Injury (TBI)'''

==Key Investigators==
* Georgia Tech: Yifei Lou and Allen Tannenbaum
* Micah Chambers: UCLA

<div style="margin: 20px;">
<div style="width: 27%; float: left; padding-right: 3%;">

<h3>Objective</h3>

* Understanding brain injury using (multimodal) deformable image registration
* Robust registrations inspire of topological changes (enforcing zero flow?)
* CUDA-based implementation, which takes 1 min for 256x256x60

</div>

<div style="width: 27%; float: left; padding-right: 3%;">

<h3>Approach, Plan</h3>

* Integration into Slicer3 Module
* Consolidate and streamline workflow
* Validate algorithm on various datasets

</div>

<div style="width: 40%; float: left;">

<h3>Progress</h3>



</div>
</div>

<div style="width: 97%; float: left;">

==References==
'''1''' Yifei Lou and Allen Tannenbaum. Multimodal Deformable Image Registration via the Bhattacharyya Distance. Submitted to IEEE Trans. Image Process. 2011

'''2''' Yifei Lou, Xun Jia, Xuejun Gu and Allen Tannenbaum. A GPU-based Implementation of Multimodal Deformable Image Registration Based on Mutual Information or Bhattacharyya Distance. Insight Journal, 2011. [[http://www.midasjournal.org/browse/publication/803]]
</div>
==Delivery Mechanism==



This work will be delivered to the NAMIC Kit as a

#NITRIC distribution
#Slicer Module
##Built-in: NO
##Extension -- commandline: NO
##Extension -- loadable: NO

Multimodality Image Registration for TBI

2011-06-20T16:51:56Z

Yflou:

__NOTOC__
<gallery>
Image:PW-MIT2011.png|[[2011_Summer_Project_Week#Projects|Projects List]]
Image::BRAINSCutFigure.png|BRAINSCut Result Example
Image:t1exam1.png|T1 exam1
Image:t1exam2.png|T1 exam2
Image:t1deformed.png|T1 deformed
</gallery>

'''Multimodality Image Registration for Traumatic Brain Injury (TBI)'''

==Key Investigators==
* Georgia Tech: Yifei Lou and Allen Tannenbaum
* Micah Chambers: UCLA

<div style="margin: 20px;">
<div style="width: 27%; float: left; padding-right: 3%;">

<h3>Objective</h3>

* Understanding brain injury using (multimodal) deformable image registration
* Robust registrations inspire of topological changes (enforcing zero flow?)
* CUDA-based implementation, which takes 1 min for 256x256x60

</div>

<div style="width: 27%; float: left; padding-right: 3%;">

<h3>Approach, Plan</h3>

* Integration into Slicer3 Module
* Consolidate and streamline workflow
* Validate algorithm on various datasets

</div>

<div style="width: 40%; float: left;">

<h3>Progress</h3>



</div>
</div>

<div style="width: 97%; float: left;">

==References==
'''1''' Yifei Lou and Allen Tannenbaum. Multimodal Deformable Image Registration via the Bhattacharyya Distance. Submitted to IEEE Trans. Image Process. 2011

'''2''' Yifei Lou, Xun Jia, Xuejun Gu and Allen Tannenbaum. A GPU-based Implementation of Multimodal Deformable Image Registration Based on Mutual Information or Bhattacharyya Distance. Insight Journal, 2011. [[http://www.midasjournal.org/browse/publication/803]]
</div>
==Delivery Mechanism==



This work will be delivered to the NAMIC Kit as a

#NITRIC distribution
#Slicer Module
##Built-in: NO
##Extension -- commandline: NO
##Extension -- loadable: NO

Multimodality Image Registration for TBI

2011-06-20T16:47:31Z

Yflou: /* Key Investigators */

__NOTOC__
<gallery>
Image:PW-MIT2011.png|[[2011_Summer_Project_Week#Projects|Projects List]]
Image::BRAINSCutFigure.png|BRAINSCut Result Example
</gallery>

'''Multimodality Image Registration for Traumatic Brain Injury (TBI)'''

==Key Investigators==
* Georgia Tech: Yifei Lou and Allen Tannenbaum
* Micah Chambers: UCLA

<div style="margin: 20px;">
<div style="width: 27%; float: left; padding-right: 3%;">

<h3>Objective</h3>

* Understanding brain injury using (multimodal) deformable image registration
* Robust registrations inspire of topological changes (enforcing zero flow?)
* CUDA-based implementation, which takes 1 min for 256x256x60

</div>

<div style="width: 27%; float: left; padding-right: 3%;">

<h3>Approach, Plan</h3>

* Integration into Slicer3 Module
* Consolidate and streamline workflow
* Validate algorithm on various datasets

</div>

<div style="width: 40%; float: left;">

<h3>Progress</h3>



</div>
</div>

<div style="width: 97%; float: left;">

==References==
'''1''' Yifei Lou and Allen Tannenbaum. Multimodal Deformable Image Registration via the Bhattacharyya Distance. Submitted to IEEE Trans. Image Process. 2011

'''2''' Yifei Lou, Xun Jia, Xuejun Gu and Allen Tannenbaum. A GPU-based Implementation of Multimodal Deformable Image Registration Based on Mutual Information or Bhattacharyya Distance. Insight Journal, 2011. [[http://www.midasjournal.org/browse/publication/803]]
</div>
==Delivery Mechanism==



This work will be delivered to the NAMIC Kit as a

#NITRIC distribution
#Slicer Module
##Built-in: NO
##Extension -- commandline: NO
##Extension -- loadable: NO

Multimodality Image Registration for TBI

2011-06-20T16:42:47Z

Yflou: /* Key Investigators */

__NOTOC__
<gallery>
Image:PW-MIT2011.png|[[2011_Summer_Project_Week#Projects|Projects List]]
Image::BRAINSCutFigure.png|BRAINSCut Result Example
</gallery>

'''Multimodality Image Registration for Traumatic Brain Injury (TBI)'''

==Key Investigators==
* Georgia Tech: Yifei Lou and Allen Tannenbaum
* Micah Chambers: UCLA

<div style="margin: 20px;">
<div style="width: 27%; float: left; padding-right: 3%;">

<h3>Objective</h3>

* Understanding brain injury using (multimodal) deformable image registration
* Robust registrations inspirit of topological changes (enforcing zero flow?)
* CUDA-based implementation, which takes 1 min for 256x256x60

</div>

<div style="width: 27%; float: left; padding-right: 3%;">

<h3>Approach, Plan</h3>

* Integration into Slicer3 Module
* Consolidate and streamline workflow
* Validate algorithm on various datasets

</div>

<div style="width: 40%; float: left;">

<h3>Progress</h3>



</div>
</div>

<div style="width: 97%; float: left;">

==References==
'''1''' Yifei Lou and Allen Tannenbaum. Multimodal Deformable Image Registration via the Bhattacharyya Distance. Submitted to IEEE Trans. Image Process. 2011

'''2''' Yifei Lou, Xun Jia, Xuejun Gu and Allen Tannenbaum. A GPU-based Implementation of Multimodal Deformable Image Registration Based on Mutual Information or Bhattacharyya Distance. Insight Journal, 2011. [[http://www.midasjournal.org/browse/publication/803]]
</div>
==Delivery Mechanism==



This work will be delivered to the NAMIC Kit as a

#NITRIC distribution
#Slicer Module
##Built-in: NO
##Extension -- commandline: NO
##Extension -- loadable: NO

Multimodality Image Registration for TBI

2011-06-20T16:27:08Z

Yflou: /* Key Investigators */

__NOTOC__
<gallery>
Image:PW-MIT2011.png|[[2011_Summer_Project_Week#Projects|Projects List]]
Image::BRAINSCutFigure.png|BRAINSCut Result Example
</gallery>

'''Multimodality Image Registration for Traumatic Brain Injury (TBI)'''

==Key Investigators==
* Georgia Tech: Yifei Lou and Allen Tannenbaum

<div style="margin: 20px;">
<div style="width: 27%; float: left; padding-right: 3%;">

<h3>Objective</h3>

Understanding brain injury using (multimodal) image registration.

</div>

<div style="width: 27%; float: left; padding-right: 3%;">

<h3>Approach, Plan</h3>

* Integration into Slicer3 Module
* Consolidate and streamline workflow
* Validate algorithm on various datasets

</div>

<div style="width: 40%; float: left;">

<h3>Progress</h3>



</div>
</div>

<div style="width: 97%; float: left;">

==References==
'''1''' Yifei Lou and Allen Tannenbaum. Multimodal Deformable Image Registration via the Bhattacharyya Distance. Submitted to IEEE Trans. Image Process. 2011

'''2''' Yifei Lou, Xun Jia, Xuejun Gu and Allen Tannenbaum. A GPU-based Implementation of Multimodal Deformable Image Registration Based on Mutual Information or Bhattacharyya Distance. Insight Journal, 2011. [[http://www.midasjournal.org/browse/publication/803]]
</div>
==Delivery Mechanism==



This work will be delivered to the NAMIC Kit as a

#NITRIC distribution
#Slicer Module
##Built-in: NO
##Extension -- commandline: NO
##Extension -- loadable: NO

Multimodality Image Registration for TBI

2011-06-14T18:34:08Z

Yflou:

__NOTOC__
<gallery>
Image:PW-MIT2011.png|[[2011_Summer_Project_Week#Projects|Projects List]]
Image::BRAINSCutFigure.png|BRAINSCut Result Example
</gallery>

'''Multimodality Image Registration for Traumatic Brain Injury (TBI)'''

==Key Investigators==
* Georgia Tech: Yifei Lou and Allen Tannenbaum

<div style="margin: 20px;">
<div style="width: 27%; float: left; padding-right: 3%;">

<h3>Objective</h3>

* Integration into Slicer3 Module
* Consolidate and streamline workflow
* Validate algorithm on various datasets

</div>

<div style="width: 27%; float: left; padding-right: 3%;">

<h3>Approach, Plan</h3>

</div>

<div style="width: 40%; float: left;">

<h3>Progress</h3>



</div>
</div>

<div style="width: 97%; float: left;">

==References==
'''1''' Yifei Lou and Allen Tannenbaum. Multimodal Deformable Image Registration via the Bhattacharyya Distance. Submitted to IEEE Trans. Image Process. 2011

'''2''' Yifei Lou, Xun Jia, Xuejun Gu and Allen Tannenbaum. A GPU-based Implementation of Multimodal Deformable Image Registration Based on Mutual Information or Bhattacharyya Distance. Insight Journal, 2011. [[http://www.midasjournal.org/browse/publication/803]]
</div>
==Delivery Mechanism==



This work will be delivered to the NAMIC Kit as a

#NITRIC distribution
#Slicer Module
##Built-in: NO
##Extension -- commandline: NO
##Extension -- loadable: NO

Multimodality Image Registration for TBI

2011-06-14T18:33:04Z

Yflou:

__NOTOC__
<gallery>
Image:PW-MIT2011.png|[[2011_Summer_Project_Week#Projects|Projects List]]
Image::BRAINSCutFigure.png|BRAINSCut Result Example
</gallery>

'''Multimodality Image Registration for Traumatic Brain Injury (TBI)'''

==Key Investigators==
* Georgia Tech: Yifei Lou and Allen Tannenbaum

<div style="margin: 20px;">
<div style="width: 27%; float: left; padding-right: 3%;">

<h3>Objective</h3>

#:Integration into Slicer3 Module
#:Consolidate and streamline current segmentation workflow
#:Test algorithm

</div>

<div style="width: 27%; float: left; padding-right: 3%;">

<h3>Approach, Plan</h3>
#:Check dependencies of BRAINSCut
#:and integrate into Slicer CLM.
#:

</div>

<div style="width: 40%; float: left;">

<h3>Progress</h3>



</div>
</div>

<div style="width: 97%; float: left;">

==References==
'''1''' Yifei Lou and Allen Tannenbaum. Multimodal Deformable Image Registration via the Bhattacharyya Distance. Submitted to IEEE Trans. Image Process. 2011

'''2''' Yifei Lou, Xun Jia, Xuejun Gu and Allen Tannenbaum. A GPU-based Implementation of Multimodal Deformable Image Registration Based on Mutual Information or Bhattacharyya Distance. Insight Journal, 2011. [[http://www.midasjournal.org/browse/publication/803]]
</div>
==Delivery Mechanism==



This work will be delivered to the NAMIC Kit as a

#NITRIC distribution
#Slicer Module
##Built-in: NO
##Extension -- commandline: NO
##Extension -- loadable: NO

Multimodality Image Registration for TBI

2011-06-14T18:31:03Z

Yflou: Created page with '__NOTOC__ <gallery> Image:PW-MIT2011.png|Projects List Image::BRAINSCutFigure.png|BRAINSCut Result Example </gallery> '''Multimodality Imag…'

__NOTOC__
<gallery>
Image:PW-MIT2011.png|[[2011_Summer_Project_Week#Projects|Projects List]]
Image::BRAINSCutFigure.png|BRAINSCut Result Example
</gallery>

'''Multimodality Image Registration for Traumatic Brain Injury (TBI)'''

==Key Investigators==
* Georgia Tech: Yifei Lou and Allen Tannenbaum

<div style="margin: 20px;">
<div style="width: 27%; float: left; padding-right: 3%;">

<h3>Objective</h3>

#:Integration of BRAINSCut into Slicer3 Module
#:Integration of GMI feature images into BRAINSCut
#:Test BRAINSCut

</div>

<div style="width: 27%; float: left; padding-right: 3%;">

<h3>Approach, Plan</h3>
#:Check dependencies of BRAINSCut
#:and integrate into Slicer CLM.
#:

</div>

<div style="width: 40%; float: left;">

<h3>Progress</h3>



</div>
</div>

<div style="width: 97%; float: left;">

==References==

==Delivery Mechanism==



This work will be delivered to the NAMIC Kit as a

#NITRIC distribution
#Slicer Module
##Built-in: NO
##Extension -- commandline: NO
##Extension -- loadable: NO

==References==
'''1''' Yifei Lou and Allen Tannenbaum. Multimodal Deformable Image Registration via the Bhattacharyya Distance. Submitted to IEEE Trans. Image Process. 2011

'''2''' Yifei Lou, Xun Jia, Xuejun Gu and Allen Tannenbaum. A GPU-based Implementation of Multimodal Deformable Image Registration Based on Mutual Information or Bhattacharyya Distance. Insight Journal, 2011. [[http://www.midasjournal.org/browse/publication/803]]
</div>

2011 Summer Project Week

2011-06-14T16:14:23Z

Yflou: /* Projects */

Back to [[Events]]

[[image:PW-MIT2011.png|right|200px]]

*'''Dates:''' June 20-24, 2011
*'''Location:''' MIT

==Preliminary Agenda==
==Agenda==

{|border="1"
|-style="background:#b0d5e6;color:#02186f"
!style="width:10%" |Time
!style="width:18%" |Monday, June 20
!style="width:18%" |Tuesday, June 21
!style="width:18%" |Wednesday, June 22
!style="width:18%" |Thursday, June 23
!style="width:18%" |Friday, June 24
|-
|
|bgcolor="#dbdbdb"|'''Project Presentations'''
|bgcolor="#6494ec"|'''NA-MIC Update Day'''
|
|bgcolor="#88aaae"|'''IGT Day'''
|bgcolor="#faedb6"|'''Reporting Day'''
|-
|bgcolor="#ffffdd"|'''8:30am'''
|
|bgcolor="#ffffaa"|Breakfast
|bgcolor="#ffffaa"|Breakfast
|bgcolor="#ffffaa"|Breakfast
|bgcolor="#ffffaa"|Breakfast
|-
|bgcolor="#ffffdd"|'''9am-12pm'''
|
|'''9am-11am:''' [[2011 Project Week Breakout Session: Slicer4|Slicer 4 Core Modules Usability Review]]''' [[MIT_Project_Week_Rooms#Star|Star Room]]
<br>----------------------------------------<br>
'''11-12pm: <font color="#4020ff">Breakout Session:'''</font> [[2011 Summer Project Week Breakout Session Slicer4 Annotation|Slicer4 Annotations]] (Nicole Aucoin)<br>
[[MIT_Project_Week_Rooms#Star|Star Room]]
|'''9am-12pm: <font color="#4020ff">Breakout Session:'''</font><br> [[2011 Project Week Breakout Session: ITK|ITK]] (Luis Ibanez)
<br>[[MIT_Project_Week_Rooms#Grier_34-401_AB|Star Room]]
|'''9am-4pm: <font color="#4020ff">Breakout Session:'''</font><br> [[2011 Summer Project Week Breakout Session:OpenIGTLink|OpenIGTLink]]
<br>[[MIT_Project_Week_Rooms#Grier_34-401_AB|Grier Rooms]]
|'''10am-12pm:''' [[#Projects|Project Progress Updates]]
<br>[[MIT_Project_Week_Rooms#Grier_34-401_AB|Grier Rooms]]
|-
|bgcolor="#ffffdd"|'''12pm-1pm'''
|bgcolor="#ffffaa"|Lunch
|bgcolor="#ffffaa"|Lunch
|bgcolor="#ffffaa"|Lunch
|bgcolor="#ffffaa"|Lunch
|bgcolor="#ffffaa"|Lunch boxes; Adjourn by 1:30pm
|-
|bgcolor="#ffffdd"|'''1pm-5:30pm'''
|'''1-1:05pm: <font color="#503020">Ron Kikinis: Welcome</font>'''
[[MIT_Project_Week_Rooms#Grier_34-401_AB|Grier Rooms]]
<br>----------------------------------------<br>
'''1:05-3:30pm:''' [[#Projects|Project Introductions]] (all Project Leads)
<br>[[MIT_Project_Week_Rooms#Grier_34-401_AB|Grier Rooms]]
<br>----------------------------------------<br>
'''3:30-5:00pm: NA-MIC Kit Update''' Slicer4 Developers Guided Tour (Pieper) ([[media:2011 Summer-Slicer4.ppt|Draft Slides]]), Slicer4 Extension Writing Tutorial (Finet, Fillion-Robin)
<br>[[MIT_Project_Week_Rooms#Grier_34-401_AB|Grier Rooms]]
|'''1-3pm: <font color="#4020ff">Breakout Session:'''</font><br> [http://wiki.slicer.org/slicerWiki/index.php/Slicer4:MultiVolumeContainer#Summer_2011_Project_Week_Breakout_Session Slicer4 MultiVolume Containers] (Nicole Aucoin)
<br>[[MIT_Project_Week_Rooms#Grier_34-401_AB|Star Room]]
<br>----------------------------------------<br>
'''3-4pm:''' [[Summer_2011_Tutorial_Contest|Tutorial Contest Presentations]]
<br>[[MIT_Project_Week_Rooms#Grier_34-401_AB|Grier Rooms]]
<br>----------------------------------------<br>
'''4-5pm:''' [[2011 Summer Project Week Breakout Session VTKCharts|VTK Charts]] (Marcus Hanwell)
<br>[[MIT_Project_Week_Rooms#Grier_34-401_AB|Star Room]]
|'''12:45-1pm:''' [[Events:TutorialContestJune2011|Tutorial Contest Winner Announcement]]
<br>[[MIT_Project_Week_Rooms#Grier_34-401_AB|Grier Rooms]]
<br>----------------------------------------<br>
'''3-4pm: <font color="#4020ff">Breakout Session:'''</font><br>[[2011_Summer_Project_Week_Breakout_Session_EMRegistration|Inter-subject Registration for EM segmenter]]
<br>[[MIT_Project_Week_Rooms#Grier_34-401_AB|Star Room]]
|'''1-4pm: <font color="#4020ff">Breakout Session:'''</font><br> [[2011 Summer Project Week Breakout Session:OpenIGTLink|OpenIGTLink]]
<br>[[MIT_Project_Week_Rooms#Grier_34-401_AB|Grier Rooms]]
|
|-
|bgcolor="#ffffdd"|'''5:30pm'''
|bgcolor="#f0e68b"|Adjourn for the day
|bgcolor="#f0e68b"|Adjourn for the day
|bgcolor="#f0e68b"|Adjourn for the day
|bgcolor="#f0e68b"|Adjourn for the day
|
|}

==Projects==

* Please make a link for your project to a new page based on the [[2011_Summer_Project_Week_Template| 2011 Summer Project Page Template]]

#valuate the applicability of DICOM RT I/O facility in Slicer (via Plastimatch Extension) for Brachytherapy Planning (Tina Kapur, Greg Sharp, Robert Cormack?)
#Visualization of b-spline and vector fields (Steve, Danielle, Dominik)
#[[2011_Summer_Project_Week_Annotation_Module|Annotation Module in Slicer4]] (Nicole Aucoin, Daniel Haehn)
#[[2011_Summer_Project_Week_RECIST|RECIST Slicer4 module]] (Nicole Aucoin)
#DicomToNrrdConverter refactoring ( Xiaodong Tao, Mark Scully)
#[[2011_Summer_Project_Week_normal_consistency_particles|Normal consistency in particle correspondence computation using great circles in principal spheres - Huntington's Disease]], (Beatriz Paniagua, Martin Styner, Sungkyu Jung, Mark Scully)
#Group-wise Automatic Mesh-Based analysis of CortIcal Thickness (GAMBIT) - TBI (Clement Vachet, Martin Styner, Randi Gollub?)
#[[2011_Summer_Project__Week_Shape_Analysis_UNC |SPHARM & particles shape analysis - Huntington's Disease]] - Lucile Bompard, Clement Vachet, Beatriz Paniagua, Martin Styner
#Non-rigid, inter-patient registration of bone masks derived from CT for Head and Neck Cancer Radiation Therapy (Ivan Kolesov, Yi Gao, Gregory Sharp, and Allen Tannenbaum)
#[[2011_Summer_Project_Week_RSS_for_AFib_Ablation|Robust Statistical Segmentation (RSS) for the Atrial Fibrillation Ablation Therapy]] (Yi Gao, Kedar Patwardhan, Wassim Haddad, and Allen Tannenbaum, Rob MacLeod, Josh Blauer, and Josh Cates)
#Mass Spectrometry for Brain Tumor Therapy (Behnood Gholami, Nathalie Agar)
#[[Multimodality Image Registration for TBI]] (Yifei Lou, Danielle Pace, Jack Van Horn?, Marcel Prastawa?)
#[[2011_Summer_Project_Week_Segmentation_TBI|Segmentation of Longitudinal TBI data]] (Bo Wang, Jack Van Horn, Andrei Irimia, Marcel Prastawa, Guido Gerig)
#Longitudinal Shape Regression - Huntington's Disease (James Fishbaugh, Guido Gerig)
#[[2011_Summer_Project__Week_DVH|Dose volume histograms in Slicer]] (Greg Sharp, Nadya Shusharina, Steve Pieper, Csaba Pinter, Tina Kapur)
#[[2011_Summer_Project__Week_DICOM_RT|Synthetic images, vector fields, RT structures and RT doses in Slicer and ITK]]. (Nadya Shusharina, Greg Sharp, Luis Ibanez, Steve Pieper)
#[[2011_Summer_Project_Week_Watersheds|Interactive Watersheds Segmentation Module for Slicer for Atrial Fibrillation and HN Cancer]] (Josh Cates, Ross Whitaker, Steve Pieper, Jim Miller, Nadya)
#Segmentation of Nerve and Nerve Ganglia in the Spine (Adrian Dalca, Giovanna Danagoulian, Ron Kikinis, Ehud Schmidt, Polina Golland)
#Image Manifold Learning with Spectral Embedding and Laplacian Eigenmaps (Ramesh Sridharan, Polina Golland)
#Shapeworks Shape Analysis for Atrial Fibrilliation and HD (Manasi Datar, Beatriz UNC, Mark Scully)
#Explore the applicability of RSS and Shapeworks for Ventricular Segmentation(Chiara Carminati, ?, ?)
#[[2011_Summer_Project_Week_Integrate_BRAINSCut_into_Slicer3]](Regina Kim, ... )
#The Vascular Modeling Toolkit in 3D Slicer 4 (Daniel Haehn, Luca Antiga, Steve Pieper)
#[[2011_Summer_Project_Week__LANDWARP_integration|Integration of LANDWARP into interactive registration module]] (Andrey Fedorov, Greg Sharp, Nadya Shusharina)
#[[2011_Summer_Project_Week_Registration_of_mouse_brains|Registration of mouse brains]] (Francois Budin)
#ShapeWorks Applications (Manasi Datar, Beatriz Paniagua, Martin Styner, Ross Whitaker, ?)
#[[2011_Summer_Project__Week_Wireless_Joystick|Wireless joystick controlling medical devices and software (e.g. Slicer4) in the operating room]] (Szymon Kostrzewski)
#Live Tracked Ultrasound in 3D Slicer 4 (Tamas Heffter)
#[http://wiki.na-mic.org/Wiki/index.php/Survey_stealthlink_openigtlink Surveying research teams interested in Open IGT Link support of Stealth Station (Nobuhiko Hata, Ron Kikinis)]
#DTIPrep - "Study-specific Protocol" based automatic DWI/DTI quality control and preparation - Huntington's Disease (Mashid Farzinfar, Clement Vachet, Joy Matsui, Martin Styner)
#DTIProcessing - Huntington's Disease (Clement Vachet, Joy Matsui, Martin Styner)
#Volumetric DTI into Slicer for HD for Tract based roi segmentation (Steve Callahan, Mark Scully, Jim Miller)
#Nifti Support for Diffusion Tensor Images (Demian)
#Finishing details on the workflows: DICOM->Full brain tractography / peritumoral (Demian)
#Refactoring of the tractography display widget (Isaiah)
#Laterality (Lauren)
#Selection for models and bundles post-clustering (Lauren)
#ROI-based / picking selection of fiber bundles (Maybe one of Sylvain's interns)
#Adding streamlined tractography to the Finsler front propagation tractography toolkit (Antonio)
#Add ODF estimation / visualization (Antonio)
#Workflows and Service Oriented Architecture Modules for Slicer4 as Extensions (Alexander Zaitsev, Wendy Plesniak, Ron Kikinis)
#[[2011_Summer_Project__Week_DICOM_Networking|DICOM Networking interface for Slicer4]] (Steve Pieper, Nicole Aucoin, Noby Hata)
#Stenosis Detector in 3D Slicer 4 (Suares Tamekue, Daniel Haehn, Luca Antiga)
#[[2011_Summer_Project_Week_Spine_Segmentation_And_Osteoporosis_Screening_CT|Spine Segmentation & Osteoporosis Screening In CT Imaging Studies]] (Anthony Blumfield)
#Slicer module for building an average population HARDI Atlas (Ryan Eckbo)
#4D Ultrasound (Laurent Chauvin, Noby Hata, Atsushi Yamada)
#EM Segmentation in 3D Slicer 4 (Daniel Haehn, Dominique Belhachemi, Kilian Pohl)
#[[NonRigidRegistrationThatAccommodatesResection|Demons Based Non-Rigid Registration that Accommodates Resection in 3D Slicer]] (Petter Risholm, Sandy Wells)
#[[2011_Summer_Project_Week_re-parameterize_fiber|Re-parameterize fiber tracts for fiber statistics analysis]]
#[[2011_Summer_Project_Week_Automated_GUI_Testing| Automated GUI Testing (Sonia Pujol, Steve Pieper, Dave Partyka, Jean-Christophe Fillion-Robin, Xiaodong Tao)]]
#[[2011_Summer_Project_Week_Plastimatch_for_EMSegmenter | Integrating Plastimatch into the EMSegmenter]] (Dominique Belhachemi, Kilian Pohl, Greg Sharp)
#[[2011_Summer_Project_Week_Customizing_EMSegmenter_pipelines_for_brain_lesions | Customizing EMSegmenter pipelines for brain lesions]] (Dominique Belhachemi, Alexander Zaitsev, Kilian Pohl)
#[[2011_Summer_Project_Week_Slicer_Extension_for_GLISTR | Slicer extension for GLiome Image SegmenTation and Registration (GLISTR)]] (Andreas Schuh, Daniel Haehn, Kilian Pohl)
#[[2011_Summer_Project_Week_WMGeometry_Slicer4 | White matter geometry measures in Slicer 4]] (Peter Savadjiev)
#Internationalization of Slicer (Luping Fang, Steve Pieper, Daniel Haehn, Suares Tamekue, Jean-Christophe Fillion-Robin, Jean-Christophe, Julien Finet, Yiming Ge, Ping Cao)
#[[2011_Summer_Project_Week__BRAINSFit_new_features_integration|Integrate new features into BRAINSFit]] (Andrey Fedorov, Hans Johnson, Mark Scully)
#[[2011_Summer_Project_Week_FetchMI:_Slicer_integration_with_XNAT |FetchMI: Slicer integration with XNAT 1.5]] (Misha Milchenko, Wendy Plesniak)

==Background==

We are pleased to announce the 13th PROJECT WEEK of hands-on research and development activity for applications in Image-Guided Therapy, Neuroscience, and several additional areas of biomedical research that enable personalized medicine. Participants will engage in open source programming using the [[NA-MIC-Kit|NA-MIC Kit]], algorithm design, medical imaging sequence development, tracking experiments, and clinical application. The main goal of this event is to move forward the translational research deliverables of the sponsoring centers and their collaborators. Active and potential collaborators are encouraged and welcome to attend this event. This event will be set up to maximize informal interaction between participants. If you would like to learn more about this event, please [http://public.kitware.com/cgi-bin/mailman/listinfo/na-mic-project-week click here to join our mailing list].

Active preparation begins on Thursday, April 28th at 3pm ET, with a kick-off teleconference. Invitations to this call will be sent to members of the sponsoring communities, their collaborators, past attendees of the event, as well as any parties who have expressed an interest in working with these centers. The main goal of the kick-off call is to get an idea of which groups/projects will be active at the upcoming event, and to ensure that there is sufficient coverage for all. Subsequent teleconferences will allow for more focused discussions on individual projects and allow the hosts to finalize the project teams, consolidate any common components, and identify topics that should be discussed in breakout sessions. In the final days leading upto the meeting, all project teams will be asked to fill in a template page on this wiki that describes the objectives and plan of their projects.

The event itself will start off with a short presentation by each project team, driven using their previously created description, and will help all participants get acquainted with others who are doing similar work. In the rest of the week, about half the time will be spent in breakout discussions on topics of common interest of subsets of the attendees, and the other half will be spent in project teams, doing hands-on project work. The hands-on activities will be done in 40-50 small teams of size 2-4, each with a mix of multi-disciplinary expertise. To facilitate this work, a large room at MIT will be setup with several tables, with internet and power access, and each computer software development based team will gather on a table with their individual laptops, connect to the internet to download their software and data, and be able to work on their projects. Teams working on projects that require the use of medical devices will proceed to Brigham and Women's Hospital and carry out their experiments there. On the last day of the event, a closing presentation session will be held in which each project team will present a summary of what they accomplished during the week.

This event is part of the translational research efforts of [http://www.na-mic.org NA-MIC], [http://www.ncigt.org NCIGT], [http://nac.spl.harvard.edu/ NAC], [http://catalyst.harvard.edu/home.html Harvard Catalyst], and [http://www.cimit.org CIMIT]. It is an expansion of the NA-MIC Summer Project Week that has been held annually since 2005. It will be held every summer at MIT and Brigham and Womens Hospital in Boston, typically during the last full week of June, and in Salt Lake City in the winter, typically during the second week of January.

A summary of all past NA-MIC Project Events is available [[Project_Events#Past|here]].

== Logistics ==
*'''Dates:''' June 20-24, 2011
*'''Location:''' MIT. [[Meeting_Locations:MIT_Grier_A_%26B|Grier Rooms A & B: 34-401A & 34-401B]].
*'''REGISTRATION:''' Please register [http://guest.cvent.com/d/sdqy0l/4W here]. Payment must be made by credit card.
*'''Registration Fee:''' $260 (covers the cost of breakfast, lunch and coffee breaks for the week).
*'''Hotel:''' Boston Marriott Cambridge, Two Cambridge Center, 50 Broadway, Cambridge, MA 02142. Group rate is $199/night plus tax. Book [http://www.marriott.com/hotels/travel/boscb?groupCode=jrbjrba&app=resvlink&fromDate=6/19/11&toDate=6/24/11 here] or call 1-617-494-6600 and mention that you are booking in the MIT Room Block. '''All reservations must be made by May 29, 2011 to receive the discounted rate.'''

== Preparation ==

# Please make sure that you are on the http://public.kitware.com/cgi-bin/mailman/listinfo/na-mic-project-week mailing list
# The NA-MIC engineering team will be discussing infrastructure projects in a kickoff TCON on April 28, 3pm ET. In the weeks following, new and old participants from the above mailing list will be invited to join to discuss their projects, so please make sure you are on it!
# By 3pm ET on Thursday May 12, all participants to add a one line title of their project to #Projects
#By 3pm ET on Thursday June 9, all project leads to complete [[Project_Week/Template|Complete a templated wiki page for your project]]. Please do not edit the template page itself, but create a new page for your project and cut-and-paste the text from this template page. If you have questions, please send an email to tkapur at bwh.harvard.edu.
# By 3pm on June 16: Create a directory for each project on the [[Engineering:SandBox|NAMIC Sandbox]] (Zack)
## Commit on each sandbox directory the code examples/snippets that represent our first guesses of appropriate methods. (Luis and Steve will help with this, as needed)
## Gather test images in any of the Data sharing resources we have (e.g. XNAT/MIDAS). These ones don't have to be many. At least three different cases, so we can get an idea of the modality-specific characteristics of these images. Put the IDs of these data sets on the wiki page. (the participants must do this.)
## Setup nightly tests on a separate Dashboard, where we will run the methods that we are experimenting with. The test should post result images and computation time. (Zack)
# Please note that by the time we get to the project event, we should be trying to close off a project milestone rather than starting to work on one...
# People doing Slicer related projects should come to project week with slicer built on your laptop.
## Projects to develop extension modules should work with the [http://viewvc.slicer.org/viewcvs.cgi/branches/Slicer-3-6/#dirlist Slicer-3-6 branch] (new code should not be checked into the branch).
## Projects to modify core behavior of slicer should be done on the [http://viewvc.slicer.org/viewcvs.cgi/trunk/ trunk].

==Registrants==

Do not add your name to this list- it is maintaining by the organizers based on your paid registration (see Logistics for link)
# Nicole Aucoin , Brigham and Women's Hospital
# Dominique Belhachemi , University of Pennsylvania
# Anthony Blumfiled , Radnostics
# Lucile Bompard , UNC NIRAL
# Sylvain Bouix , Brigham and Women's Hospital
# Francois Budin , UNC NIRAL
# Steve Callahan , University of Utah
# Joshua Cates , University of Utah
# Laurent Chauvin , Brigham and Women's Hospital
# Adrian Dalca , MIT CSAIL
# Manasi Datar , University of Utah
# Colin Davey ,
# Ryan Eckbo , Brigham and Women's Hospital
# Jan Egger , University Hospital of Marburg
# Luping Fang , Zhejiang University of Technology, China
# mahshid farzinfar , UNC
# Andriy Fedorov , Brigham and Women's Hospital
# Julien Finet , Kitware Inc.
# James Fishbaugh , University of Utah
# Greg Gardner , University of Utah
# Ronen Globinsky , Yale University
# Maged Goubran , Robarts Research Institute
# Daniel Haehn , University of Pennsylvania
# Mike Halle , Brigham and Women's Hospital
# Noby Hata , Brigham and Women's Hospital
# Tamas Heffter , Queen's University
# Andrei Irimia , University of California, Los Angeles
# Hans Johnson , University of Iowa
# Ilknur Kabul , Kitware
# Tina Kapur , Brigham and Women's Hospital
# Ron Kikinis , Brigham and Women's Hospital; Harvard Medical School
# Regina Kim , University of Iowa
# Szymon Kostrzewski , Ecole Polytechnique Federale de Lausanne EPFL
# Dillon Lee , University of Utah
# Yinpeng Li , UNC-NIRAL
# Yifei Lou , Georgia Institute of Technology
# mohsen mahvash , Harvard Medical School (BWH and VA)
# Katie Mastrogiacomo , Brigham and Women's Hospital
# Joy Matsui , University of Iowa
# Dominik Meier , BWH
# Mikhail Milchenko , Washington University in St. Louis
# James Miller , GE Research
# Isaiah Norton , Brigham and Women's Hospital
# Danielle Pace , Kitware
# Beatriz Paniagua , University of North Carolina at Chapel Hill
# Xenophon Papademetris , Yale University
# Kedar Patwardhan , GE Global Research
# Steve Pieper , Isomics, Inc.
# Csaba Pinter , Queen's University
# Wendy Plesniak , Brigham and Women's Hospital
# Kilian Pohl , UPenn
# Marcel Prastawa , University of Utah
# Sonia Pujol , Brigham and Women's Hospital
# Martin Rajchl , Robarts Research Institute
# Petter Risholm , Brigham and Women's Hospital
# Peter Savadjiev , Brigham and Women's Hospital
# Andreas Schuh , University of Pennsylvania
# Mark Scully , University of Iowa
# Gregory Sharp , MGH
# Yundi Shi , UNC-Chapel Hill
# Nadya Shusharina , MGH
# Ramesh Sridharan , MIT CSAIL
# Hao Su , WPI
# Suarez Tamekue , Brigham and Women's Hospital
# Xiaodong Tao , GE Research
# Clement Vachet , UNC Chapel Hill
# Antonio Vega , Brigham and Women's Hospital
# Gopal Veni , University of Utah
# Bo Wang , University of Utah
# Demian Wasserman , Brigham and Women's Hospital
# Sandy Wells , Brigham and Women's Hospital
# Jason White , Brigham and Women's Hospital
# Atsushi Yamada , Brigham and Women's Hospital
# Alexander Yarmarkovich , Isomics
# Alexander Zaitsev , Brigham and Women's Hospital

2011 Summer Project Week

2011-05-12T20:07:16Z

Yflou: /* Projects */

User:Yflou

2011-05-12T19:04:45Z

Yflou:

__NOTOC__

==Key Investigators==
* Gatech: Yifei Lou

<div style="margin: 20px;">
<div style="width: 27%; float: left; padding-right: 3%;">

<h3>Objective</h3>
We are developing methods for multimodal deformable image registration.

</div>

<div style="width: 27%; float: left; padding-right: 3%;">

<h3>Approach, Plan</h3>

Our approach for analyzing diffusion tensors is summarized in the IPMI 2007 reference below. The main challenge to this approach is <foo>.

Our plan for the project week is to first try out <bar>,...

</div>

<div style="width: 40%; float: left;">

<h3>Progress</h3>
Software for the fiber tracking and statistical analysis along the tracts has been implemented. The statistical methods for diffusion tensors are implemented as ITK code as part of the [[NA-MIC/Projects/Diffusion_Image_Analysis/DTI_Software_and_Algorithm_Infrastructure|DTI Software Infrastructure]] project. The methods have been validated on a repeated scan of a healthy individual. This work has been published as a conference paper (MICCAI 2005) and a journal version (MEDIA 2006). Our recent IPMI 2007 paper includes a nonparametric regression method for analyzing data along a fiber tract.

</div>
</div>

<div style="width: 97%; float: left;">

User:Yflou

2011-05-12T19:03:15Z

Yflou: Multimodal image registration