A Chan–Vese Model Based on the Markov Chain for Unsupervised Medical Image Segmentation

作     者：Quanwei Huang Yuezhi Zhou Linmi Tao Weikang Yu Yaoxue Zhang Li Huo Zuoxiang He Quanwei Huang;Yuezhi Zhou;Linmi Tao;Weikang Yu;Yaoxue Zhang;Li Huo;Zuoxiang He

作者机构：Key Laboratory of Pervasive Computing(Ministry of Education)and the Department of Computer Science and TechnologyTsinghua UniversityBeijing 100084China School of Electronic and Information EngineeringBeihang UniversityBeijing 100191China Department of Nuclear MedicinePeking Union Medical College HospitalBeijing 100730China School of Clinical MedicineTsinghua Universityand also with Beijing Tsinghua Changgung HospitalBeijing 100084China 

出 版 物：《Tsinghua Science and Technology》 (清华大学学报（自然科学版（英文版）)

年 卷 期：2021年第26卷第6期

页      面：833-844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）] 100207[医学-影像医学与核医学] 1002[医学-临床医学] 08[工学] 080203[工学-机械设计及理论] 1010[医学-医学技术（可授医学、理学学位）] 0802[工学-机械工程] 10[医学] 

基　　金：supported by the National Natural Science Foundation of China (Nos.61672017 and 61272232) the Key-Area Research and Development Program of Guangdong Province (No.2019B010137005) 

主　　题：medical image unsupervised segmentation Markov chain 

摘      要：The accurate segmentation of medical images is crucial to medical care and research;however, many efficient supervised image segmentation methods require sufficient pixel level labels. Such requirement is difficult to meet in practice and even impossible in some cases, e.g., rare Pathoma images. Inspired by traditional unsupervised methods, we propose a novel Chan–Vese model based on the Markov chain for unsupervised medical image segmentation. It combines local information brought by superpixels with the global difference between the target tissue and the background. Based on the Chan–Vese model, we utilize weight maps generated by the Markov chain to model and solve the segmentation problem iteratively using the min-cut algorithm at the superpixel *** method exploits abundant boundary and local region information in segmentation and thus can handle images with intensity inhomogeneity and object sparsity. In our method, users gain the power of fine-tuning parameters to achieve satisfactory results for each segmentation. By contrast, the result from deep learning based methods is *** performance of our method is assessed by using four Computerized Tomography(CT) datasets. Experimental results show that the proposed method outperforms traditional unsupervised segmentation techniques.