Particle Based Shape Regression - Revision history

Datar at 17:42, 8 June 2010

2010-06-08T17:42:09Z

Datar at 17:41, 8 June 2010

2010-06-08T17:41:00Z

Datar: /* Project */

2010-06-08T17:37:26Z

Project

Datar at 17:36, 8 June 2010

2010-06-08T17:36:17Z

Datar: Created page with 'NOTOC Image:HeadRegressionResult.png|Changes in early head shape with log(age). ==Key Investigators== * Utah: Manasi Datar, Joshua Cates, P. Thomas Flet…'

2010-06-08T17:33:01Z

Created page with '__NOTOC__ <gallery> Image:HeadRegressionResult.png|Changes in early head shape with log(age). </gallery> ==Key Investigators== * Utah: Manasi Datar, Joshua Cates, P. Thomas Flet…'

New page

__NOTOC__
<gallery>
Image:HeadRegressionResult.png|Changes in early head shape with log(age).
</gallery>

==Key Investigators==
* Utah: Manasi Datar, Joshua Cates, P. Thomas Fletcher, Sylvain Gouttard, Guido Gerig, Ross Whitaker

==Project==
<div style="margin: 10px;">
<div style="width: 30%; float: left; padding-right: 2%;">
<h3>Objective</h3>
Shape regression promises to be an important tool to study the relationship between anatomy and underlying clinical or biological parameters, such as age. We propose a new method to
building shape models that incorporates regression analysis in the process of optimizing correspondences on a set of open surfaces. The statistical signiﬁcance of the dependence is evaluated using permutation tests designed to estimate the likelihood of achieving the observed statistics
under numerous rearrangements of the shape parameters with respect to the explanatory variable.
</div>

<div style="width: 30%; float: left; padding-right: 2%;">
<h3>Approach, Plan</h3>
The general strategy of this method is to represent correspondences as point sets that are distributed across an ensemble of similar shapes by a gradient descent optimization of an objective function that quantiﬁes the entropy of the system [1]. Our proposed extension to this method incorporates a linear regression model into the correspondence optimization. We also present a new methodology for correspondence optimization on open surfaces where surface boundaries are deﬁned by arbitrary geometric
constraints.
</div>

<div style="width: 35%; float: left;">
<h3>Progress</h3>
The proposed method has been implemented and integrated with the [http://www.sci.utah.edu/cibc/software/131-shapeworks.html | ShapeWorks] package. The figure above shows results on clinical MRI data related to early development of the human head, described in [2]
</div>

<div style="width: 35%; float: left;">
<h3>References</h3>
1. J Cates, P T Fletcher, M Styner, M Shenton, R Whitaker, "Shape modeling
and analysis with entropy-based particle systems," Information Processing in
Medical Imaging (IPMI 2007), LNCS 4584. (2007) 333–345

2. M Datar, J Cates, P T Fletcher, S Gouttard, G Gerig, R Whitaker, "Particle Based Shape Regression of Open Surfaces with Applications to Developmental Neuroimaging," MICCAI 2009
</div>

@@ Line 1: / Line 1: @@
 __NOTOC__
 [[Image:HeadRegressionResult.png‎|500px|Changes in early head shape with log(age).]]
@@ Line 36: / Line 34: @@
 . M Datar, J Cates, P T Fletcher, S Gouttard, G Gerig, R Whitaker, "Particle Based Shape Regression of Open Surfaces with Applications to Developmental Neuroimaging," MICCAI 2009
 </div>

@@ Line 3: / Line 3: @@
 Back to [[2010_Summer_Project_Week#Projects|Projects List]]
-<gallery>
+[[Image:HeadRegressionResult.png‎|500px|Changes in early head shape with log(age).]]
 ==Key Investigators==