2008 Winter Project Week:MRISC - Revision history

Pohl: /* Jan 2008 Project Half Week */

2008-02-07T18:07:48Z

Jan 2008 Project Half Week

Taox: /* Key Investigators */

2008-01-03T21:00:28Z

Key Investigators

Msabuncu at 19:43, 14 December 2007

2007-12-14T19:43:38Z

Msabuncu at 19:40, 14 December 2007

2007-12-14T19:40:49Z

Msabuncu at 19:38, 14 December 2007

2007-12-14T19:38:58Z

Tkapur at 19:42, 13 December 2007

2007-12-13T19:42:51Z

Msabuncu: New page: This study will explore an approach that utilizes an atlas-based joint registration segmentation framework to automatically classify magnetic resonance images into healthy and disease subj...

2007-12-12T16:07:57Z

New page: This study will explore an approach that utilizes an atlas-based joint registration segmentation framework to automatically classify magnetic resonance images into healthy and disease subj...

New page

This study will explore an approach that utilizes an atlas-based joint
registration segmentation framework to automatically classify
magnetic resonance images into healthy and disease subjects. We
extend an Expectation Maximization framework (Pohl et al. 2006) that
unifies atlas-based segmentation and registration. The geometric
transformation (i.e., registration with the atlas) is defined using
structure-specific affine parameters that yield a global, one-to-one
non-linear deformation. The modes of variation of the transformation
parameters are generated using principal component analysis. This
provides a robust way to learn the global deformation space that
aligns a new brain with the atlas. With this parametrization, the
algorithm then performs a deformation-based classification of the
new brain using a Support Vector Machine. We demonstrate the
algorithm with a data set that consists of 16 first episode
schizophrenics and 17 healthy subjects. The data set
included manual labels for the (left and right) Superior Temporal
Gyrus (STG), Hippocampus (HIPP), Amygdala (AMY) and Parahippocampal
Gyrus (PHG).

@@ Line 30: / Line 30: @@
 ====Jan 2008 Project Half Week====
+We discussed the next mile stones and hope to have them completed after the summer AHM.
 </div>
@@ Line 37: / Line 37: @@
 </div>
 ===Reference===
 K. M. Pohl, J. Fisher, W.E.L. Grimson, R. Kikinis, and W.M. Wells. A bayesian model for joint segmentation and registration. NeuroImage, 31(1), pp. 228-239, 2006

@@ Line 7: / Line 7: @@
 * MIT CSAIL: Mert R Sabuncu
 * BWH: Kilian Pohl
 <div style="margin: 20px;">

@@ Line 21: / Line 21: @@
 <h1>Approach, Plan </h1>
-Our approach is builds on the technology described in the reference below.
+Our plan is to build on the technology described in the reference below.
 </div>

@@ Line 1: / Line 1: @@
 {|
 |[[Image:NAMIC-SLC.jpg|thumb|320px|Return to [[2008_Winter_Project_Week]] ]]
 |}

← Older revision		Revision as of 19:42, 13 December 2007
Line 1:		Line 1:
		+
		+	Please redo this page using this [[2008_Winter_Project_Week_Template\|'''Template''']]
		+
	This study will explore an approach that utilizes an atlas-based joint		This study will explore an approach that utilizes an atlas-based joint
	registration segmentation framework to automatically classify		registration segmentation framework to automatically classify

@@ Line 1: / Line 1: @@
-Please redo this page using this [[2008_Winter_Project_Week_Template|'''Template''']]
+__NOTOC__
-This study will explore an approach that utilizes an atlas-based joint
+<div style="margin: 20px;">
 registration segmentation framework to automatically classify
-magnetic resonance images into healthy and disease subjects. We
+<div style="width: 27%; float: left; padding-right: 3%;">
 extend an Expectation Maximization framework (Pohl et al. 2006) that
-unifies atlas-based segmentation and registration. The geometric
+<h1>Objective</h1>
-transformation (i.e., registration with the atlas) is defined using
+This study will explore an approach that utilizes an atlas-based joint registration segmentation framework to automatically classify
-structure-specific affine parameters that yield a global, one-to-one
+magnetic resonance images into healthy and disease subjects. We extend an Expectation Maximization framework (Pohl et al. 2006) that unifies atlas-based segmentation and registration. The geometric transformation (i.e., registration with the atlas) is defined using structure-specific affine parameters that yield a global, one-to-one non-linear deformation. The modes of variation of the transformation parameters are generated using principal component analysis. This provides a robust way to learn the global deformation space that aligns a new brain with the atlas. With  this parametrization, the algorithm then performs a deformation-based classification of the new brain using a Support Vector Machine. We demonstrate the algorithm with a data set that consists of 16 first episode schizophrenics and 17 healthy subjects. The data set included manual labels for the (left and right) Superior Temporal Gyrus (STG),  Hippocampus (HIPP), Amygdala (AMY) and Parahippocampal Gyrus (PHG).
 non-linear deformation. The modes of variation of the transformation
-parameters are generated using principal component analysis. This
+</div>
 provides a robust way to learn the global deformation space that
-aligns a new brain with the atlas. With  this parametrization, the
+<div style="width: 27%; float: left; padding-right: 3%;">
 algorithm then performs a deformation-based classification of the
-new brain using a Support Vector Machine. We demonstrate the
+<h1>Approach, Plan </h1>
-algorithm with a data set that consists of 16 first episode
+Our approach is builds on the technology described in the reference below.
-schizophrenics and 17 healthy subjects. The data set
+</div>
 included manual labels for the (left and right) Superior Temporal
-Gyrus (STG), Hippocampus (HIPP), Amygdala (AMY) and Parahippocampal
+<div style="width: 40%; float: left;">
 Gyrus (PHG).