Difference between revisions of "NA-MIC Internal Collaborations:StructuralImageAnalysis"

From NAMIC Wiki
Jump to: navigation, search
 
(9 intermediate revisions by one other user not shown)
Line 6: Line 6:
  
 
{| cellpadding="10" style="text-align:left;"
 
{| cellpadding="10" style="text-align:left;"
| style="width:15%" | [[Image:Circle seg.PNG|200px]]
+
| style="width:15%" | [[Image:MITHippocampalSubfieldSegmentation.png|200px]]
 
| style="width:85%" |
 
| style="width:85%" |
  
== [[Projects:KPCASegmentation|Kernel PCA for Segmentation]] ==
+
== [[Projects:BayesianMRSegmentation| Bayesian Segmentation of MRI Images]] ==
  
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...]]
+
In this project we develop and validate a method for fully automated segmentation of the subfields of the hippocampus in ultra-high resolution in vivo MRI. [[Projects:HippocampalSubfieldSegmentation|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
+
<font color="red">'''New: '''</font> van Leemput K., Bakkour A., Benner T., Wiggins G., Wald L.L., Augustinack J., Dickerson B.C., Golland P., Fischl B. Automated segmentation of hippocampal subfields from ultra-high resolution in vivo MRI. Hippocampus. 2009 Jun;19(6):549-57.
  
 +
van Leemput K. Encoding probabilistic brain atlases using Bayesian inference. IEEE Trans Med Imaging. 2009 Jun;28(6):822-37.
 
|}
 
|}
  
Line 27: Line 28:
 
In this project, we want to compute cortical correspondence on populations, using various features such as cortical structure, DTI connectivity, vascular structure, and functional data (fMRI). This presents a challenge because of the highly convoluted surface of the cortex, as well as because of the different properties of the data features we want to incorporate together. [[Projects:CorticalCorrespondenceWithParticleSystem|More...]]
 
In this project, we want to compute cortical correspondence on populations, using various features such as cortical structure, DTI connectivity, vascular structure, and functional data (fMRI). This presents a challenge because of the highly convoluted surface of the cortex, as well as because of the different properties of the data features we want to incorporate together. [[Projects:CorticalCorrespondenceWithParticleSystem|More...]]
  
<font color="red">'''New: '''</font> Oguz I, Niethammer M, Cates J, Whitaker R, Fletcher T, Vachet C, Styner M. “Cortical Correspondence with Probabilistic Fiber Connectivity”. Proc. Information Processing in Medical Imaging, 2009.  
+
<font color="red">'''New: '''</font> Oguz I., Niethammer M., Cates J., Whitaker R., Fletcher T., Vachet C., Styner M. Cortical Correspondence with Probabilistic Fiber Connectivity. Inf Process Med Imaging. 2009;21:651-63.  
  
 
|-
 
|-
  
| | [[Image:Cbg-dtiatlas-tracts.png|200px]]
+
| | [[Image:ICluster_templates.gif|200px]]
 +
| |
 +
 
 +
== [[Projects:MultimodalAtlas|Multimodal Atlas]] ==
 +
 
 +
In this work, we propose and investigate an algorithm that jointly co-registers a collection of images while computing multiple templates. The algorithm, called '''iCluster''', is used to compute multiple atlases for a given population.
 +
[[Projects:MultimodalAtlas|More...]]
 +
 
 +
<font color="red">'''New: '''</font> Yeo B.T.T., Sabuncu M.R., Golland P., Fischl B. Task-Optimal Registration Cost Functions. Int Conf Med Image Comput Comput Assist Interv. 2009;12(Pt 1):1009-1017.
 +
|-
 +
 
 +
| | [[Image:CoordinateChart.png|200px]]
 
| |
 
| |
  
== [[Projects:DTIPopulationAnalysis|Population Analysis from Deformable Registration]] ==
+
== [[Projects:SphericalDemons|Spherical Demons: Fast Surface Registration]] ==
 +
 
 +
We present the fast Spherical Demons algorithm for registering two spherical images. By exploiting spherical vector spline interpolation theory, we show that a large class of regularizers for the modified demons objective function can be efficiently approximated on the sphere using convolution. Based on the one parameter subgroups of diffeomorphisms, [[Projects:SphericalDemons|More...]]
 +
 
 +
 
 +
<font color="red">'''New: '''</font> Yeo B.T.T., Sabuncu M.R., Vercauteren T., Ayache N., Fischl B., Golland P. Spherical Demons: Fast Surface Registration. Int Conf Med Image Comput Comput Assist Interv. 2008;11(Pt 1):745-753.
  
Analysis of populations of diffusion images typically requires time-consuming manual segmentation of structures of interest to obtain correspondance for statistics. This project uses non-rigid registration of DTI images to produce a common coordinate system for hypothesis testing of diffusion properties. [[Projects:DTIPopulationAnalysis|More...]]
+
<font color="red">'''New: '''</font> Yeo B.T.T., Sabuncu M.R., Vercauteren T., Ayache N., Fischl B., Golland P. Spherical Demons: Fast Surface Registration. IEEE TMI, In Press.
  
<font color="red">'''New: '''</font> Casey B. Goodlett, P. Thomas Fletcher, John H. Gilmore, Guido Gerig. Group Analysis of DTI Fiber Tract Statistics with Application to Neurodevelopment. NeuroImage 45 (1) Supp. 1, 2009. p. S133-S142.
 
  
 
|-
 
|-
  
| | [[Image:ICluster_templates.gif|200px]]
+
| | [[Image:JointRegSeg.png|200px]]
 
| |
 
| |
  
== [[Projects:MultimodalAtlas|Multimodal Atlas]] ==
+
== [[Projects:RegistrationRegularization|Optimal Atlas Regularization in Image Segmentation]] ==
 +
 
 +
We propose a unified framework for computing atlases from manually labeled data sets at various degrees of “sharpness” and the joint registration and segmentation of a new brain with these atlases. Using this framework, we investigate the tradeoff between warp regularization and image fidelity, i.e. the smoothness of the new subject warp and the sharpness of the atlas in a segmentation application.
 +
[[Projects:RegistrationRegularization|More...]]
  
In this work, we propose and investigate an algorithm that jointly co-registers a collection of images while computing multiple templates. The algorithm, called '''iCluster''', is used to compute multiple atlases for a given population.
+
<font color="red">'''New:'''</font> Yeo B.T.T., Sabuncu M.R., Desikan R., Fischl B., Golland P. Effects of Registration Regularization and Atlas Sharpness on Segmentation Accuracy. Med Image Anal. 2008 Oct;12(5):603-15.  
[[Projects:MultimodalAtlas|More...]]
+
 
 +
|-
  
<font color="red">'''NEW: '''</font> Image-driven Population Analysis through Mixture-Modeling, M.R. Sabuncu, S.K. Balci, M.E. Shenton and P. Golland. IEEE Transactions on Medical Imaging. Accepted for Publication, 2009.
+
| | [[Image:Cbg-dtiatlas-tracts.png|200px]]
 +
| |
  
|-
+
== [[Projects:DTIPopulationAnalysis|Population Analysis from Deformable Registration]] ==
  
 +
Analysis of populations of diffusion images typically requires time-consuming manual segmentation of structures of interest to obtain correspondance for statistics.  This project uses non-rigid registration of DTI images to produce a common coordinate system for hypothesis testing of diffusion properties. [[Projects:DTIPopulationAnalysis|More...]]
  
 +
<font color="red">'''New: '''</font> Goodlett C., Fletcher P.T., Gilmore J.H., Gerig G. Group Analysis of DTI Fiber Tract Statistics with Application to Neurodevelopment. Neuroimage. 2009 Mar;45(1 Suppl):S133-42.
 
|}
 
|}
  
Line 67: Line 90:
 
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...]]
 
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.
+
<font color="red">'''New: '''</font> Malcolm J.G., Rathi Y., Shenton M.E., Tannenbaum A. Label Space: A Coupled Multi-shape Representation. Int Conf Med Image Comput Comput Assist Interv. 2008;11(Pt 2):416-424.  
  
 
|-
 
|-
Line 78: Line 101:
 
The UNC shape analysis is based on an analysis framework of objects with spherical topology, described mainly by sampled spherical harmonics SPHARM-PDM. The input of the shape analysis framework is a set of binary segmentations of a single brain structure, such as the hippocampus or caudate. These segmentations are converted into a shape description (SPHARM) with correspondence and analyzed via Hotelling T^2 two sample metric. [[Projects:ShapeAnalysisFrameworkUsingSPHARMPDM|More...]]
 
The UNC shape analysis is based on an analysis framework of objects with spherical topology, described mainly by sampled spherical harmonics SPHARM-PDM. The input of the shape analysis framework is a set of binary segmentations of a single brain structure, such as the hippocampus or caudate. These segmentations are converted into a shape description (SPHARM) with correspondence and analyzed via Hotelling T^2 two sample metric. [[Projects:ShapeAnalysisFrameworkUsingSPHARMPDM|More...]]
  
<font color="red">'''New: '''</font> Zhao Z., Taylor W., Styner M., Steffens D., Krishnan R., Macfall J. , Hippocampus shape analysis and late-life depression. PLoS ONE. 2008 Mar 19;3(3):e1837.
+
<font color="red">'''New: '''</font> Zhu H., Zhou H., Chen J., Li Y., Lieberman J., Styner M. Adjusted exponentially tilted likelihood with applications to brain morphology. Biometrics. 2009 Sep;65(3):919-27.
 +
 
 +
Levitt J.J., Styner M., Niethammer M., Bouix S., Koo M., Voglmaier M.M., Dickey C., Niznikiewicz M.A., Kikinis R., McCarley R.W., Shenton M.E. Shape abnormalities of caudate nucleus in schizotypal personality disorder. Schizophr Res. 2009 May;110(1-3):127-139.
 +
* Shape Analysis Toolkit available as part of UNC Neurolib open source ([http://www.ia.unc.edu/dev/download/shapeAnalysis download]).
 +
* Slicer 3 module for whole shape analysis pipeline in progress (data access via XNAT, processing via BatchMake and distributed computing using Condor)
  
 
|-
 
|-
  
| | [[Image:BasePair3DModel.JPG|200px|]]
+
| | [[Image:UNCShape_CaudatePval_MICCAI06.png|200px]]
 
| |
 
| |
  
== [[Projects:NonParametricClustering|Non Parametric Clustering for Biomolecular Structural Analysis]] ==
+
== [[Projects:LocalStatisticalAnalysisViaPermutationTests|Local Statistical Analysis via Permutation Tests]] ==
  
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...]]
+
We have further developed a set of statistical testing methods that allow the analysis of local shape differences using the Hotelling T 2 two sample metric. Permutatioin tests are employed for the computation of statistical p-values, both raw and corrected for multiple comparisons. Resulting significance maps are easily visualized. Additional visualization of the group tests are provided via mean difference magnitude and vector maps, as well as maps of the group covariance information. Ongoing research focuses on incorporating covariates such as clinical scores into the testing scheme. [[Projects:LocalStatisticalAnalysisViaPermutationTests|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.
+
<font color="red">'''New: '''</font> Paniagua B., Styner M., Macenko M., Pantazis D., Niethammer M. Local Shape Analysis using MANCOVA. Insight Journal, 2009 July-December, http://hdl.handle.net/10380/3124
 +
 
 +
* Available as part of Shape Analysis Toolset in UNC Neurolib open source ([http://www.ia.unc.edu/dev/download/shapeAnalysis download]) with MANCOVA testing.
 +
 
 +
|-
 +
 
 +
| | [[Image:Cbg-dtiatlas-tracts.png|200px]]
 +
| |
 +
 
 +
 
 +
== [[Projects:DTIPopulationAnalysis|Group Analysis of DTI Fiber Tracts]] ==
 +
 
 +
Analysis of populations of diffusion images typically requires time-consuming manual segmentation of structures of interest to obtain correspondance for statistics.  This project uses non-rigid registration of DTI images to produce a common coordinate system for hypothesis testing of diffusion properties. [[Projects:DTIPopulationAnalysis|More...]]
  
 +
<font color="red">'''New: '''</font> Goodlett C., Fletcher P.T., Gilmore J.H., Gerig G. Group Analysis of DTI Fiber Tract Statistics with Application to Neurodevelopment. Neuroimage. 2009 Mar;45(1 Suppl):S133-42.
 
|}
 
|}

Latest revision as of 13:08, 14 May 2010

Home < NA-MIC Internal Collaborations:StructuralImageAnalysis
Back to NA-MIC Internal Collaborations

Structural Image Analysis

Image Segmentation

MITHippocampalSubfieldSegmentation.png

Bayesian Segmentation of MRI Images

In this project we develop and validate a method for fully automated segmentation of the subfields of the hippocampus in ultra-high resolution in vivo MRI. More...

New: van Leemput K., Bakkour A., Benner T., Wiggins G., Wald L.L., Augustinack J., Dickerson B.C., Golland P., Fischl B. Automated segmentation of hippocampal subfields from ultra-high resolution in vivo MRI. Hippocampus. 2009 Jun;19(6):549-57.

van Leemput K. Encoding probabilistic brain atlases using Bayesian inference. IEEE Trans Med Imaging. 2009 Jun;28(6):822-37.

Image Registration

Sulcaldepth.png

Cortical Correspondence using Particle System

In this project, we want to compute cortical correspondence on populations, using various features such as cortical structure, DTI connectivity, vascular structure, and functional data (fMRI). This presents a challenge because of the highly convoluted surface of the cortex, as well as because of the different properties of the data features we want to incorporate together. More...

New: Oguz I., Niethammer M., Cates J., Whitaker R., Fletcher T., Vachet C., Styner M. Cortical Correspondence with Probabilistic Fiber Connectivity. Inf Process Med Imaging. 2009;21:651-63.

ICluster templates.gif

Multimodal Atlas

In this work, we propose and investigate an algorithm that jointly co-registers a collection of images while computing multiple templates. The algorithm, called iCluster, is used to compute multiple atlases for a given population. More...

New: Yeo B.T.T., Sabuncu M.R., Golland P., Fischl B. Task-Optimal Registration Cost Functions. Int Conf Med Image Comput Comput Assist Interv. 2009;12(Pt 1):1009-1017.

CoordinateChart.png

Spherical Demons: Fast Surface Registration

We present the fast Spherical Demons algorithm for registering two spherical images. By exploiting spherical vector spline interpolation theory, we show that a large class of regularizers for the modified demons objective function can be efficiently approximated on the sphere using convolution. Based on the one parameter subgroups of diffeomorphisms, More...


New: Yeo B.T.T., Sabuncu M.R., Vercauteren T., Ayache N., Fischl B., Golland P. Spherical Demons: Fast Surface Registration. Int Conf Med Image Comput Comput Assist Interv. 2008;11(Pt 1):745-753.

New: Yeo B.T.T., Sabuncu M.R., Vercauteren T., Ayache N., Fischl B., Golland P. Spherical Demons: Fast Surface Registration. IEEE TMI, In Press.


JointRegSeg.png

Optimal Atlas Regularization in Image Segmentation

We propose a unified framework for computing atlases from manually labeled data sets at various degrees of “sharpness” and the joint registration and segmentation of a new brain with these atlases. Using this framework, we investigate the tradeoff between warp regularization and image fidelity, i.e. the smoothness of the new subject warp and the sharpness of the atlas in a segmentation application. More...

New: Yeo B.T.T., Sabuncu M.R., Desikan R., Fischl B., Golland P. Effects of Registration Regularization and Atlas Sharpness on Segmentation Accuracy. Med Image Anal. 2008 Oct;12(5):603-15.

Cbg-dtiatlas-tracts.png

Population Analysis from Deformable Registration

Analysis of populations of diffusion images typically requires time-consuming manual segmentation of structures of interest to obtain correspondance for statistics. This project uses non-rigid registration of DTI images to produce a common coordinate system for hypothesis testing of diffusion properties. More...

New: Goodlett C., Fletcher P.T., Gilmore J.H., Gerig G. Group Analysis of DTI Fiber Tract Statistics with Application to Neurodevelopment. Neuroimage. 2009 Mar;45(1 Suppl):S133-42.

Morphometric Measures and Shape Analysis

P1 small.png

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. More...

New: Malcolm J.G., Rathi Y., Shenton M.E., Tannenbaum A. Label Space: A Coupled Multi-shape Representation. Int Conf Med Image Comput Comput Assist Interv. 2008;11(Pt 2):416-424.

UNCShape OverviewAnalysis MICCAI06.gif

Shape Analysis Framework using SPHARM-PDM

The UNC shape analysis is based on an analysis framework of objects with spherical topology, described mainly by sampled spherical harmonics SPHARM-PDM. The input of the shape analysis framework is a set of binary segmentations of a single brain structure, such as the hippocampus or caudate. These segmentations are converted into a shape description (SPHARM) with correspondence and analyzed via Hotelling T^2 two sample metric. More...

New: Zhu H., Zhou H., Chen J., Li Y., Lieberman J., Styner M. Adjusted exponentially tilted likelihood with applications to brain morphology. Biometrics. 2009 Sep;65(3):919-27.

Levitt J.J., Styner M., Niethammer M., Bouix S., Koo M., Voglmaier M.M., Dickey C., Niznikiewicz M.A., Kikinis R., McCarley R.W., Shenton M.E. Shape abnormalities of caudate nucleus in schizotypal personality disorder. Schizophr Res. 2009 May;110(1-3):127-139.

  • Shape Analysis Toolkit available as part of UNC Neurolib open source (download).
  • Slicer 3 module for whole shape analysis pipeline in progress (data access via XNAT, processing via BatchMake and distributed computing using Condor)
UNCShape CaudatePval MICCAI06.png

Local Statistical Analysis via Permutation Tests

We have further developed a set of statistical testing methods that allow the analysis of local shape differences using the Hotelling T 2 two sample metric. Permutatioin tests are employed for the computation of statistical p-values, both raw and corrected for multiple comparisons. Resulting significance maps are easily visualized. Additional visualization of the group tests are provided via mean difference magnitude and vector maps, as well as maps of the group covariance information. Ongoing research focuses on incorporating covariates such as clinical scores into the testing scheme. More...

New: Paniagua B., Styner M., Macenko M., Pantazis D., Niethammer M. Local Shape Analysis using MANCOVA. Insight Journal, 2009 July-December, http://hdl.handle.net/10380/3124

  • Available as part of Shape Analysis Toolset in UNC Neurolib open source (download) with MANCOVA testing.
Cbg-dtiatlas-tracts.png


Group Analysis of DTI Fiber Tracts

Analysis of populations of diffusion images typically requires time-consuming manual segmentation of structures of interest to obtain correspondance for statistics. This project uses non-rigid registration of DTI images to produce a common coordinate system for hypothesis testing of diffusion properties. More...

New: Goodlett C., Fletcher P.T., Gilmore J.H., Gerig G. Group Analysis of DTI Fiber Tract Statistics with Application to Neurodevelopment. Neuroimage. 2009 Mar;45(1 Suppl):S133-42.