图谱法脑部MRI图像自动分割技术发展及应用  

Development and Application for Atlas-Based Brain MRI Image Segmentation Technology

作　　者：何小海[1] 梁子飞[1] 唐晓颖[2,3] 滕奇志[1] 

机构地区：[1]四川大学电子信息学院,成都610065 [2]中山大学卡内基梅隆大学联合工程学院,广州510006 [3]广东顺德中山大学卡内基梅隆大学国际联合研究院,顺德528300

出　　处：《数据采集与处理》2015年第5期956-964,共9页Journal of Data Acquisition and Processing

基　　金：国家自然科学基金(61372174;81173356)资助项目

摘　　要：脑部MRI图像自动分割是计算机技术运用于医学上的一个典型工作,脑部图像分割技术对于人类研究脑部疾病具有重要意义。虽然有一些非常广泛应用的图像分割方法,如阈值法、区域增长法、聚类法等,但在脑部MRI图像分割中,这些方法都没有图谱法具有更为实际的医学研究与临床价值。本文回顾了脑部图像配准、分割的发展历程,介绍了图谱分割算法的发展及基本原理,以及当前比较前沿的多图谱分割系统的组成和应用。最后本文对图谱法脑部自动分割在实际临床医学中的应用前景作了总结和展望。Automated segmentation of brain MRI image is an important computer-based technology with wide applicability in medicine field,and of great significance in the study of human brain diseases.There exists a variety of segmentation methods,such as the the thresholding method,the region growing method,and the clustering method,which are broadly applied to natural images.However,those methods are not as powerful or practical as atlas-based method when applied to clinical medical image.The development of the atlas-based method for brain image segmentation is reviewed,and representative algorithms are introduced.The basic principles of these parcellation algorithms are described as well as the components of a state-of-the-art segmentation system.On this basis,the segmentation procedures are introduced,and its various applications in clinical medicine are discussed.Finally,the current status and the future potential of the automated segmentation′s applications in clinical medicine are summarized.

关 键 词：脑部磁共振图像 信息处理 图像分割 微分同胚 脑部图像配准 

分 类 号：TP391[自动化与计算机技术—计算机应用技术] Q64[自动化与计算机技术—计算机科学与技术]