A Novel Segmentation Method for CT Head Images Using PSFCM-ES

摘要：

With an expert system, a novel fuzzy c-means clustering method based on PSO and expert system (PSFCM-ES) is proposed in this paper. The algorithm is formulated by incorporating the spatial neighborhood information into the standard FCM clustering algorithm. The k-nearest neighbor (k-NN) algorithm is introduced for calculating the weight in the spatially weighted FCM algorithm so as to improve the performance of image clustering. To speed up the FCM algorithm, the iteration is carried out with the gray level histogram of image instead of the conventional whole data of image. PSO algorithm is included to select optimal cluster centers and expert system is also introduced to solve the labeling problems. Experimental results indicate the proposed approach is effective and efficient.

关键词： CT segmentation spatially weighted fuzzy c-means PSO ezpert system

作者: Kaiping Wei Bin He Tao Zhang

作者单位: Department of Computer Science, Huazhong Normal University, 430079 Wuhan, China

会议类型: 国际会议

会议名称: The 2nd International Conference on Bioinformatics and Biomedical Engineering(iCBBE 2008)(第二届生物信息与生物医学工程国际会议)

会议地点: 上海

会议语种:英文

页码: 1971-1974

在线出版日期: 2008-05-16（万方平台首次上网日期，不代表论文的发表时间）