Paper: | FR-PM-PS1.5 |
Session: | Atlas and Model Based Image Segmentation |
Time: | Friday, April 7, 13:30 - 14:50 |
Presentation: |
Poster
|
Title: |
First Results of an Automated Model-Based Segmentation System for Subcortical Structures in Human Brain MRI Data |
Authors: |
Hendrik Belitz; Research Center Juelich | | |
| Karl Rohr; DKFZ Heidelberg | | |
| Heinrich Müller; University of Dortmund | | |
| Gudrun Wagenknecht; Research Center Juelich | | |
Abstract: |
We propose an automated model-based approach for the segmentation of subcortical structures, especially the basal ganglia, from three-dimensional human brain MRI images. Our hybrid approach combines an automatic tissue classification scheme, a landmark detection algorithm and a discrete active surface model to achieve its goal. A priori knowledge is incoporated into the different stages of the model and is used to retain shape and neighborhood information about the structures of interest throughout the segmentation process. The system is designed for as little user interaction as possible. Exemplary results are given for the BrainWeb simulated brain data set and for a real data set. |