AHM 2006:ProjectsRuleBasedSegmentationInSlicer

Rule Based Segmentation Slicer Modules

File:2006 AHM Programming Half Week Rule Based Segmentation.ppt

Introduction

This Slicer module implements our semi-automatic segmenation algorithms for various brain structures. These algorithms are based on expert neuroanatomist (core 3) rules. Our programs drastically reduce the time it takes to segment various brain structures. We are currently working on the following brain areas: DLPFC, DPFC, Nucleus accumbens, Putamen.

Use Case

I'd like to rapidly segment and visualize a brain area by clicking on a convenient gui.

Current Status

There are 3 major software components to this Slicer module: GUI, ITK Bayesian Filter, VTK Thumb Extraction Filter. At the Programming Half Week, we were able to make progress on each of the components as follows:

• A working first draft GUI has been developed.
• The itkBayesianClassifierImageFilter has been wrapped in VTK for use in Slicer. Still needs to be tested.
• The VTK Thumb Extraction Filter was started and currently being coded.

The following is the current status of each of the major anatomical areas:
DLPFC - Implemented in Matlab, Almost Implemented in Slicer
DPFC - Almost Implemented in Matlab
Nucleus accumbens - Implemented in Matlab
Putamen - Undergoing algorithm development

People

Core 1 Team

(All from Georgia Tech)
Delphine Nain - Slicer Leader
John Melonakos - Bayesian Classification, Sulci Extraction
Ramsey Al-Hakim - DLPFC, Nucleus accumbens
Tauseef Ur Rehman - DPFC
Shawn Lankton - Putamen

Core 2 Team

Alex Yarmakovich (Isomics)

Core 3 Team

Jim Fallon (UCI)
Martha Shenton (Harvard)