[Insight-users] question regarding GeodesicActiveContourShapePriorLevelSetImageFilter

[Siddharth Vikal]

-------- Original Message --------
Subject: 	question regarding
"GeodesicActiveContourShapePriorLevelSetImageFilter"
Date: 	Wed, 23 Apr 2008 15:00:38 -0400
From: 	Amir M. Tahmasebi <tahmaseb at cs.queensu.ca>
To: 	insight-users at itk.org



Hi all,

I am using "GeodesicActiveContourShapePriorLevelSetImageFilter" to
segment a structure from 3D MR images of the brain. I used
"ImagePCAShapeModelEstimator" for generating meanshape model as well
as variation modes. I have modified the provided example for 3D.
Instead
 of "FastMarchingImageFilter", which requires seed points, I provide
the distance map of the meanshape as the initial contour (generated
using
"SignedDanielssonDistanceMapImageFilter").

My question is regarding the the initial coordinate (x,y,z) for
meanshape to start with which are a part of parameters being updated.
No matter what position I select, I get the same final result. I was
wondering how can I check if this initial position is actually
involved
in the process of segmentation.

Thanks in advance,

________________________________
Amir M. Tahmasebi
Ph.D. Student,
Medical Image Analysis Lab.
School of Computing,
Queen's University,
Kingston, Ontario
CANADA
K7L 3N6
________________________________
Tel: (613) 533-2797
Web: www.cs.queensu.ca/~tahmaseb <http://www.cs.queensu.ca/%7Etahmaseb>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://www.itk.org/pipermail/insight-users/attachments/20080424/d08d8ec6/attachment.htm>