Technical Program

Paper Detail

Paper:	TH-PM-PS3.12
Session:	Cardiac and Vascular Imaging
Time:	Thursday, April 6, 15:20 - 16:40
Presentation:	Poster
Title:	Image Segmentation Based on Bayesian Network-Markov Random Field Model and its Application to In Vivo Plaque Composition
Authors:	Fei Liu; University of Washington
	Dongxiang Xu; University of Washington
	Chun Yuan; University of Washington
	William Kerwin; University of Washington
Abstract:	Combining Bayesian network (BN) and Markov Random Field (MRF) models, this paper presents an effective supervised image segmentation algorithm. Representing information from different features, a Bayesian network generates the probability map for each pixel via the conditional PDF (probability density function) learned from a limited training data set. Considering the spatial relation and a priori knowledge of the image, MRF theory is used to generate a reasonable segmentation by minimizing the proposed energy functional. Applying this algorithm to multi-contrast MR image based in vivo plaque composition measurement shows comparable results with expert manual segmentation.

ISBI 2006 is sponsored by

and organized in cooperation with