Quantitative Detection of Coronary Plaques Based on MAP-EM Segmentation
(0) Risk assessment of vulnerable plaques plays an important role in preventing cardiovascular disease in clinic. The objective of this work is to segment coronary vulnerable plaques from surroundings in enhanced coronary CT, which is a challenging task due to partial volume (PV) effect and intensity variation. For accurate segmentation, a MAP-EM algorithm that takes both effects into account simultaneously was investigated to provide a theoretical solution to the problem. With an assumption that each tissue type follows a normal distribution and all tissue types are independent from each other, the algorithm estimated tissue mixture percentage within each image voxel and statistical model parameters for the tissue distribution during each update. Ten patient datasets were used to evaluate the proposed algorithm. Comparison with segmentation results outlined manually by three experienced radiologists verifies the performance and fast convergence of the MAP-EM algorithm presented.
coronary plaques partial volume effect tissue mizture MAP-EM segmentation
YANG Jia-Chen XU Jian ZHANG Guo-Peng Jerome Z. Liang LU Hong-Bing
The Department of Computer Science, Xidian University, Xian, Shannxi 710071, China The Department of Computer Application, Fourth Military Medical University, Xian, Shannxi 710032, C The Department of Radiology, State University of New York, Stony Brook, NY 11794, USA The Department of Computer Application, Fourth Military Medical University, Xian, Shannxi 710032 Ch
国际会议
南京
英文
87-94
2009-10-23（万方平台首次上网日期，不代表论文的发表时间）