马尔可夫随机场在弥散张量磁共振图像分割方法中的应用  

Research on algorithms based on Markov random models for diffusion tensor-magnetic resonance images

作　　者：彭洁[1] 吕庆文[1] 冯衍秋[1] 高园园[1] 陈武凡[1] 

机构地区：[1]南方医科大学生物医学工程学院,广东广州510515

出　　处：《南方医科大学学报》2010年第7期1562-1564,1572,共4页Journal of Southern Medical University

基　　金：国家重点基础研究发展规划(973)

摘　　要：本文利用弥散张量磁共振成像(DT-MRI)的弥散张量信息,引入Frobenius范数,提出了一种基于马尔可夫随机场(MRF)的DT-MRI图像分割新算法。本文实验分别使用该算法和K均值算法对DT-MRI图像进行分割,并将分割结果与FA图像予以评估比较。结果表明,新算法分割DT-MRI图像的精确度高于K均值算法。另外,新算法分割DT-MRI图像效果优于常规MRI(T2WI)图像。With the utilization of diffusion tensor information of image voxels, a novel MRF （Markov Random Field） segmentation algorithm was proposed for diffusion tensor MRI （DT-MRI） images benefitted from the introduction of Frobenius norm. The comparison of the segmentation effects between the proposed algorithm and K-means segmentation algorithm for DT-MRI image was made, which showed that the new algorithm could segment the DT-MRI images more accurately than the K-means algorithm. Moreover, with the same segmentation algorithm of MRF, better outcomes were achieved in DT-MRI than in conventional MRI （T2WI） image.

关 键 词：弥散张量 磁共振成像 图像分割 马尔可夫随机场 

分 类 号：O482.531[理学—固体物理]