结合非局部信息的脑MR图像分割与偏移场恢复耦合模型  

Brain MR Image Segmentation and Bias Correction Model Based on Non-local Information

作　　者：张建伟[1] 杨红[1] 陈允杰[1] 方林[1] 詹天明[2] 

机构地区：[1]南京信息工程大学数学与统计学院,南京210044 [2]南京理工大学计算机科学与技术学院,南京210094

出　　处：《计算机辅助设计与图形学学报》2013年第4期526-532,540,共8页Journal of Computer-Aided Design & Computer Graphics

基　　金：国家自然科学基金(61173072);国家自然科学青年基金(61003209);江苏省自然科学基金(BK2011824);江苏省高校自然科学研究项目(10KJB520012)

摘　　要：磁共振图像由于成像机制的影响往往导致图像中含有噪声和偏移场,使得传统方法很难得到较好的分割结果.为此,在模糊C均值模型的基础上提出一种分割与偏移场恢复耦合模型.首先构建基于非局部信息的邻域正则项,使得在降低噪声影响的同时能有效地保留图像结构信息;其次在模型求解时引入人工蜂群算法,使得模型能快速逼近凸优解.实验结果表明,该模型对噪声和偏移场均具有较好的鲁棒性,可得到较准确的分割和偏移场矫正结果.Due to the intensity inhomogeneous and noise in brain magnetic resonance （MR） image, it is difficult for the traditional models to obtain desirable segmentation results. In this paper, we first propose a novel model based on fuzzy C means （FCM） which combines segmentation with bias correction, while the non-local method is used as a regularization term to reduce the impact of noise as well as keep the image structure. Then, we introduce the artificial bee colony algorithm to gain the convex optimal solution. Experiments of the brain MR images show that the proposed method can obtain better segmentation results as well as the bias estimation in an accurate way.

关 键 词：磁共振图像 模糊C均值 图像分割 非局部信息 偏移场 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]