Spatial continuity incorporated multi-attribute fuzzy clustering algorithm for blood vessels segmentation

作     者：HAO JuTao1*, ZHAO JingJing2 & LI MingLu3 1School of Optical-Electrical and Computer Engineering, University of Shanghai for Science and Technology, Shanghai 200093, China 2Department of Electrical Engineering, Shanghai University of Electric Power, Shanghai 200090, China 3Department of Computer Science and Engineering, Shanghai Jiaotong University, Shanghai 200240, China 

作者机构：School of Optical-Electrical and Computer Engineering University of Shanghai for Science and Technology Shanghai China Department of Electrical Engineering Shanghai University of Electric Power Shanghai China Department of Computer Science and Engineering Shanghai Jiaotong University Shanghai China 

出 版 物：《Science China(Information Sciences)》 (中国科学:信息科学(英文版))

年 卷 期：2010年第53卷第4期

页      面：752-759页

核心收录：

学科分类：12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 081104[工学-模式识别与智能系统] 08[工学] 0835[工学-软件工程] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：supported by the National Basic Research Program of China (Grant No. 2006CB303000) the Innovation Program of Shanghai Municipal Education Commission (Grant No. 10YZ102) the Science Foundation for the Excellent Youth Scholars of Shanghai of China (Grant No. slg08014) 

主　　题：fuzzy c-means clustering scale space analysis spatial continuity blood vessel segmentation multi-attribute fuzzy clustering 

摘      要：A three-dimensional representation of vasculature can be extremely important in image-guided neurosurgery, pre-surgical planning. In this paper, a spatial continuity incorporated multi-attribute fuzzy clustering algorithm (MAFCM S) is proposed to segment entire blood vessels from TOF MRA images. This clustering method takes both the intensity information and the geometrical information into account, while most of the cur- rent clustering methods only deal with the former. In this method, a new dissimilarity measure, which integrates the intensity and the geometry shape dissimilarity, is introduced. Because of the presence of the geometrical information, the new measure is able to differentiate the pixels with similar intensity values within different geometrical shape structures. Experimental results show that the new algorithm can get better segmentation.