基于D-S证据理论的多发性硬化症病灶分割算法

Segmentation of multiple sclerosis lesions based on D-S evidence theory

多发性硬化症是一种严重威胁中枢神经功能的疾病,对其病灶自动检测方法的研究正受到越来越多的关注。基于D-S证据理论和模糊C-均值(FCM)聚类算法,提出了一种融合T1和T2加权MR图像信息的多发性硬化症自动分割算法。首先运用FCM聚类算法分别分割T1和T2加权MR图像,然后利用根据D-S证据理论得到的融合两种加权图像信息的基本概率分配函数,实现多发性硬化症病灶的分割。通过对多发性硬化症MR脑部图像的分割实验表明,该算法具有很高的多发性硬化症病灶分割精度,对多发性硬化症的临床辅助诊断具有重要作用。

Multiple sclerosis （MS） is an inflammatory demyelinating disease that would damage central nervous system. There was a growing attention to the segmentation algorithms of MS lesions. This paper developed an automatic algorithm for MS le- sions segmentation by utilizing the fusion T1 and T2-weighted MR brain images based on D-S evidence theory and FCM clustering algorithm. First, segmented T1 and T2 -weighted MR brain images by a FCM clustering algorithm. Then fused the resultant images according to the joint mass of T1 and T2-weighted MR brain images to produce the segmentation of MS lesions. The tes- ting experiments on MR brain images show that the proposed algorithm is able to improve the segmentation accuracy, which is important to assist the diagnosis of MS in clinic.