A Modified Fuzzy C-Means for Bias Field Estimation and Segmentation of Brain MR Image
会议名称：《第25届中国控制与决策会议》
会议届次：25th
主办单位：IEEE;NE Univ;IEEE Ind Elect Chapter;IEEE Harbin Sect Control Syst Soc Chapter;Guizhou Univ;IEEE Control Syst Soc;Syst Engn Soc China;Chinese Assoc Artificial Intelligence;Chinese Assoc Automat;Tech Comm Control Theory;Chinese Assoc Aeronaut;Automat Control Soc;Chinese Assoc Syst Simulat;Simulat Methods & Modeling Soc;Intelligent Control & Management Soc
会议日期：2013年
学科分类：0831[工学-生物医学工程（可授工学、理学、医学学位）] 1002[医学-临床医学] 08[工学] 080203[工学-机械设计及理论] 0805[工学-材料科学与工程（可授工学、理学学位）] 0802[工学-机械工程] 0702[理学-物理学] 0812[工学-计算机科学与技术（可授工学、理学学位）]
基 金：supported by Fundamental Research Funds for the Central Universities under grant N110404003
关 键 词：Bias field Fuzzy C-means clustering mage segmentation Global information MR imaging
摘 要：Fuzzy C-means clustering （FCM） algorithm is good at solving the ambiguities and uncertainties in the image, and the modified FCM has been widely used in solving the intensity inhomogeneity problem. Bias-corrected FCM （BCFCM） is very useful for noise and intensity inhomogeneity image segmentation, but it can’t estimate accurately the pixels on the boundary especially in the regions with heavy level of intensity inhomogeneous. In this paper, we present a novel algorithm for brain magnetic resonance imaging （MRI） Image segmentation and intensity inhomogeneity estimation based on BCFCM. The proposed algorithm introduces the global intensity information into the algorithm BCFCM, for the smooth bias field estimation and more accurate segmentations. The proposed method has been successfully applied to MR brain images, and experiment results show that this method is superior to FCM, BCFCM and some other approaches.