Clustering of medical image based on Gaussian mixture density model
1. School of Computer Science and Telecommunication Engineering, Jiangsu University, Zhenjiang, Jiangsu 212013, China; 2. School of Computer Science and Engineering, Changshu Institute of Technology, Changshu, Jiangsu 215500, China）
Abstract：Problem of medical image clustering was studied. A kind of K - EM clustering algorithm based on Gaussian mixture density model was proposed. Human abdominal image data was processed with this algorithm, in order to classify liver, kidney, spleen and other major organs. In this algorithm, abdominal image pixel data was randomly selected, the QAIC information criterion was used to determine the best class number of training samples, and K - means clustering algorithm was used to get initial parameters of this mixture model. Multiple iteration of the expection maximum （EM） algorithm was used to set up the mixture density model of abdominal image data. According to Bayes rule, all pixels of the abdominal image were partitioned into the corresponding Gaussian components of the mixture model, and the correct rate and the misjudgement rate of partitioning all pixels of each organ were obtained. Results of experiments show that the average correct rate of the classification of the algorithm is higher than 85% and its misjudgement rate is lower than 10%, which are better than the results of K -means algorithm.
宋余庆, 王春红, 陈健美, 谢从华. 基于高斯混合密度模型的医学图像聚类方法[J]. 江苏大学学报（自然科学版）, 2009, 30(3): 293-296.
Song Yuqing, Wang Chunhong, Chen Jianmei, Xie Conghua. Clustering of medical image based on Gaussian mixture density model[J]. Journal of Jiangsu University(Natural Science Eidtion)
, 2009, 30(3): 293-296.
2009, Vol. 30 
