Projects:fMRIStatisticsSoftwareInfrastructure - Revision history

Melonakos at 18:04, 28 November 2007

2007-11-28T18:04:28Z

Melonakos at 17:37, 28 November 2007

2007-11-28T17:37:38Z

Melonakos at 13:59, 4 September 2007

2007-09-04T13:59:01Z

Melonakos at 13:23, 4 September 2007

2007-09-04T13:23:18Z

Melonakos at 02:16, 4 September 2007

2007-09-04T02:16:59Z

Melonakos: NA-MIC/Projects/fMRI Analysis/fMRI Statistics Software Infrastructure moved to Projects:fMRIStatisticsSoftwareInfrastructure

2007-08-21T16:22:02Z

NA-MIC/Projects/fMRI Analysis/fMRI Statistics Software Infrastructure moved to Projects:fMRIStatisticsSoftwareInfrastructure

Zohara: update to link to Insight Journal article

2007-01-12T18:02:51Z

update to link to Insight Journal article

Andy: Update from Wiki

2006-12-18T19:38:47Z

Update from Wiki

New page

Back to [[NA-MIC_Collaborations|NA-MIC_Collaborations]]

'''Objective:''' To provide ITK and Slicer based tools for processing fMRI data. Currently, the scope of this effort focuses on the data processing that occurs ''after'' the alignment of the time sequence acquisition. As such, the effort is centered on the statistical analysis of fMRI and includes infrastructure for:

* Data representation
* Massively univariate processing
* Hypothesis testing
* Segmentation

'''Progress:''' A new image class, itk::VectorImage, has been developed to represent fMRI data. A VectorImage is an N-dimensional image where each voxel stores a vector of values. Conceptually, VectorImage is similar to a standard itk::Image of itk::VariableLengthVectors (in fact, VectorImage provides a fascade of an Image of VariableLengthVectors). However, VectorImage uses an efficient memory structure which avoids the memory fragmentation that results from storing a VariableLengthVector instance at each voxel.

The massively univariate processing of fMRI data involves solving a generalized linear model (GLM) at every voxel under consideration. Previously, Slicer used the GNU Scientific Library (GSL) for solving GLM problems. However, the GNU Scientific Library license is incompatible with the spirit of NA-MIC. The GLM code in Slicer has been ported to use existing components of ITK for solving standard linear algebra problems.

Hypothesis testing is used as a model selection tool in fMRI processing. A new library of probability distributions to support hypothesis testing has been developed and is scheduled to be included in ITK. The new library provides access to the probability density function, cumulative distribution function, and inverse cumulative distribution function for Gaussian, Student-t, and Chi-square distributions. The library can be extended to include other parametric and non-parametric distributions. The probability distribution library has been integrated into Slicer and supplants the use of the GNU Scientific Library. A paper describing the library is available on the [https://caddlab.rad.unc.edu/MIDAS/bitstream/1926/159/5/Distributions.pdf Insight Journal].

To combat the massively univariate nature of the above processing, where each voxel is classified independent of its neighbors, neighborhood constraints are employed to refine the initial estimated activation maps. These neighborhood constraints can be posed as a Markov Random Field (MRF) and solved using a variety of methods (iterated conditional modes, mean field annealing, belief propagation, graph cuts). Currently, ITK only provides an iterated conditional modes solver for a Markov Random Field. In our ongoing work, we will be extending ITK to have a broader suite of MRF solvers.

'''Key Investigators:'''

* GE Research (probability distributions, generalized linear model, segmentation): Jim Miller
* Isomics (Slicer integration): Steve Pieper, H Liu
* Kitware (VectorImage): Karthik Krishnan
* MIT (segmentation): Polina Golland

'''Links:'''

* [http://insightsoftwareconsortium.org/InsightJournal/view_publication.php?back=view_reviews.php%3Fback%3Dpublications.php%3Fjournalid%3D4%26pubid%3D68&pubid=68 Probability Distributions Insight Journal Article (pdf and code)], [https://caddlab.rad.unc.edu/MIDAS/bitstream/1926/159/5/Distributions.pdf pdf]

@@ Line 20: / Line 20: @@
 To combat the massively univariate nature of the above processing, where each voxel is classified independent of its neighbors, neighborhood constraints are employed to refine the initial estimated activation maps. These neighborhood constraints can be posed as a Markov Random Field (MRF) and solved using a variety of methods (iterated conditional modes, mean field annealing, belief propagation, graph cuts). Currently, ITK only provides an iterated conditional modes solver for a Markov Random Field. In our ongoing work, we will be extending ITK to have a broader suite of MRF solvers.
-''References''
+= Publications =
 = Key Investigators =

@@ Line 1: / Line 1: @@
   Back to [[NA-MIC_Collaborations|NA-MIC_Collaborations]], [[Algorithm:MIT|MIT Algorithms]]
-'''Objective'''
+= fMRI Statistics Software Infrastructure =
 To provide ITK and Slicer based tools for processing fMRI data. Currently, the scope of this effort focuses on the data processing that occurs ''after'' the alignment of the time sequence acquisition. As such, the effort is centered on the statistical analysis of fMRI and includes infrastructure for:
@@ Line 12: / Line 10: @@
 * Segmentation
-'''Progress'''
+= Description =
 A new image class, itk::VectorImage, has been developed to represent fMRI data. A VectorImage is an N-dimensional image where each voxel stores a vector of values. Conceptually, VectorImage is similar to a standard itk::Image of itk::VariableLengthVectors (in fact, VectorImage provides a fascade of an Image of VariableLengthVectors). However, VectorImage uses an efficient memory structure which avoids the memory fragmentation that results from storing a VariableLengthVector instance at each voxel.
@@ Line 26: / Line 24: @@
 * [http://hdl.handle.net/1926/159 Probability Distributions Insight Journal Article (pdf and code)], [https://caddlab.rad.unc.edu/MIDAS/bitstream/1926/159/5/Distributions.pdf pdf]
-'''Key Investigators'''
+= Key Investigators =
 * GE (probability distributions, generalized linear model, segmentation): Jim Miller
@@ Line 32: / Line 30: @@
 * Kitware (VectorImage): Karthik Krishnan
 * MIT (segmentation): Polina Golland

@@ Line 1: / Line 1: @@
 = fMRI Statistics Software Infrastructure =
-  Back to [[NA-MIC_Collaborations|NA-MIC_Collaborations]]
+  Back to [[NA-MIC_Collaborations|NA-MIC_Collaborations]], [[Algorithm:MIT|MIT Algorithms]]
 '''Objective'''

@@ Line 21: / Line 21: @@
 To combat the massively univariate nature of the above processing, where each voxel is classified independent of its neighbors, neighborhood constraints are employed to refine the initial estimated activation maps. These neighborhood constraints can be posed as a Markov Random Field (MRF) and solved using a variety of methods (iterated conditional modes, mean field annealing, belief propagation, graph cuts). Currently, ITK only provides an iterated conditional modes solver for a Markov Random Field. In our ongoing work, we will be extending ITK to have a broader suite of MRF solvers.
 '''Key Investigators'''
-* GE(probability distributions, generalized linear model, segmentation): Jim Miller
+* GE (probability distributions, generalized linear model, segmentation): Jim Miller
 * Isomics (Slicer integration): Steve Pieper, H Liu
 * Kitware (VectorImage): Karthik Krishnan
@@ Line 30: / Line 34: @@
 '''Links'''

← Older revision		Revision as of 18:02, 12 January 2007
Line 25:		Line 25:
	'''Links:'''		'''Links:'''

−	* [http://~~insightsoftwareconsortium~~.~~org~~/~~InsightJournal~~/~~view_publication.php?back=view_reviews.php%3Fback%3Dpublications.php%3Fjournalid%3D4%26pubid%3D68&pubid=68~~ Probability Distributions Insight Journal Article (pdf and code)], [https://caddlab.rad.unc.edu/MIDAS/bitstream/1926/159/5/Distributions.pdf pdf]	+	* [http://hdl.handle.net/1926/159 Probability Distributions Insight Journal Article (pdf and code)], [https://caddlab.rad.unc.edu/MIDAS/bitstream/1926/159/5/Distributions.pdf pdf]

← Older revision	Revision as of 16:22, 21 August 2007
(No difference)