Difference between revisions of "ProstateSegmentationAHM2009"

From NAMIC Wiki
Jump to: navigation, search
Line 1: Line 1:
 
{|
 
{|
 
|[[Image:NAMIC-SLC.jpg|thumb|320px|Return to [[2009_Winter_Project_Week|Project Week Main Page]] ]]
 
|[[Image:NAMIC-SLC.jpg|thumb|320px|Return to [[2009_Winter_Project_Week|Project Week Main Page]] ]]
|[[Image:ShapeBasedProstateSegmentationResult.png|Shape based prostate segmentation|thumb|320px]]
+
|[[Image:ShapeBasedProstateSegmentationResult.png|semi-automatic prostate segmentation|thumb|320px]]
 
|}
 
|}
  

Revision as of 18:17, 7 January 2009

Home < ProstateSegmentationAHM2009
semi-automatic prostate segmentation



Key Investigators

  • Gabor Fichtinger, Purang Abolmaesumi, David Gobbi, Siddharth Vikal; Queen’s University
  • Allen Tannenbaum, Yi Gao; Georgia Tech
  • Katie Hayes, Brigham and Women's Hospital


Objective

For the task of prostate segmentation, we provide two tools: 1. shape based and 2. semi-automatic random walk based. The goal is to put both algorithm into Slicer3 as command line modules.

Approach, Plan

Algorithm 1. is a Bayesian Shape based segmentation. The shape of prostates are learned and then the new image is segmented using the shapes learned. Algorithm 2. is based on the Random Walks segmentation algorithm. It need more human input but the result could be interactively improved arbitrarily close to user's expectation.

Progress

Algorithm 2. is already in the form of command line module. Algorithm 1. is also ready to be ported in.

What we'll work on during the project week are 1. plug both algorithms into Slicer3 without source compiled version of Slicer3; 2. Improve the algorithm for better segmentation performance.