Unsupervised Segmentation of Overlapped Nuclei Using Bayesian Classification

作     者：Jung, Chanho Kim, Changick Chae, Seoung Wan Oh, Sukjoong 

作者机构：Korea Adv Inst Sci & Technol Dept Elect Engn Taejon 305732 South Korea Sungkyunkwan Univ Dept Pathol Kangbuk Samsung Hosp Sch Med Seoul 440746 South Korea Sungkyunkwan Univ Dept Internal Med Kangbuk Samsung Hosp Sch Med Seoul 440746 South Korea 

出 版 物：《IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING》 (IEEE Trans. Biomed. Eng.)

年 卷 期：2010年第57卷第12期

页      面：2825-2832页

核心收录：

学科分类：0831[工学-生物医学工程（可授工学、理学、医学学位）] 0808[工学-电气工程] 08[工学] 

基　　金：Ministry of Knowledge Economy (MKE)  Korea  under the Information Technology Research Center (ITRC) [NIPA-2010-(C1090-1011-0003)] 

主　　题：Automatic cell segmentation cluster validation Gaussian mixture model overlapped nuclei segmentation unsupervised Bayesian classifier 

摘      要：In a fully automatic cell extraction process, one of the main issues to overcome is the problem related to extracting overlapped nuclei since such nuclei will often affect the quantitative analysis of cell images. In this paper, we present an unsupervised Bayesian classification scheme for separating overlapped nuclei. The proposed approach first involves applying the distance transform to overlapped nuclei. The topographic surface generated by distance transform is viewed as a mixture of Gaussians in the proposed algorithm. In order to learn the distribution of the topographic surface, the parametric expectation-maximization (EM) algorithm is employed. Cluster validation is performed to determine how many nuclei are overlapped. Our segmentation approach incorporates a priori knowledge about the regular shape of clumped nuclei to yield more accurate segmentation results. Experimental results show that the proposed method yields superior segmentation performance, compared to those produced by conventional schemes.