Technical Program

Paper Detail

Paper:	FR-PM-PS1.3
Session:	Atlas and Model Based Image Segmentation
Time:	Friday, April 7, 13:30 - 14:50
Presentation:	Poster
Title:	Automatic Mri Brain Tissue Segmentation Using a Hybrid Statistical and Geometric Model
Authors:	Albert Huang; University of British Columbia
	Rafeef Abugharbieh; University of British Columbia
	Roger Tam; University of British Columbia
	Anthony Traboulsee; University of British Columbia
Abstract:	This paper presents a novel hybrid segmentation technique incorporating a statistical as well as a geometric model in a unified segmentation scheme for brain tissue segmentation of magnetic resonance imaging (MRI) scans. We combine both voxel probability and image gradient and curvature information for segmenting gray matter (GM) and white matter (WM) tissues. Both qualitative and quantitative results on synthetic and real brain MRI scans indicate superior and consistent performance when compared with standard techniques such as SPM and FAST.

ISBI 2006 is sponsored by

and organized in cooperation with