基于高斯马尔科夫随机场模型的脑血管分割算法研究.pdfVIP

36 9 Vol.36No.9 2014 9 Journal of Electronics Information Technology Sept. 2014 - ( 100875) ( 100190) (Stochastic versions of the Expectation Maximization, SEM) 3 TP391; R445.2 A 1009-5896(2014)09-2053-08 DOI: 10.3724/SP.J.1146.2013.01534 A Novel Cerebrovascular Segmentation Algorithm Based on Gauss-Markov Random Field Model Cao Rong-fei Zhang Mei-xia Wang Xing-ce Wu Zhong-ke Zhou Ming-quan Tian Yun Liu Xin-yu (College of Information Science and Technology, Beijing Normal University, Beijing 100875, China) (Institute of Computing Technology, Chinese Academy of Science, Beijing 100190, China) Abstract: In order to solve the thorny cerebrovascular segmentation problems about cerebral vessels of many branches, small shape, special position and complex patterns, this paper presents a novel statistical method to achieve effectively the accurate segmentation of cerebral vessels. Firstly, the Markov random field information is added to the statistical model which makes the full use of the spatial neighborhood information of each pixel and a new Markov statistical model is proposed; then Stochastic versions of the Expectation Maximization (SEM) algorithm is used to estimate parameters of the Markov model and the optimal s