基于模糊连接度的多发性硬化症MR图像自动分割算法

Automated Segmentation of Multiple Sclerosis Lesions Using Fuzzy Connectedness for MR Images

多发性硬化症(MS)是一种严重威胁中枢神经功能的疾病,利用磁共振成像技术能够无损伤地检出其病灶。为了自动地对多发性硬化症病灶进行分割,提出了基于模糊连接度的分割算法,实现了种子点的自动选取。作为多发性硬化症分割的预处理,针对脑部MR FLAIR图像的特征,基于区域增长方法,还提出了脑部组织提取算法。通过对临床患者MR图像的分割实验,表明该分割算法能够比较准确地分割多发性硬化症病灶,其分割效果明显好于模糊C-均值聚类算法和基于马尔可夫场模型的分割算法。该算法还具有无监督、运算速度快、稳健性好等优点,能够应用于多发性硬化症的临床辅助诊断。

Multiple sclerosis （MS） is an inflammatory demyelinating disease that damages central nervous system. Magnetic resonance imaging （MRI） is increasingly being used to assess the progression of the disease. This paper presented an algorithm for fully automated MS lesion segmentation of clinical MR FLAIR brain images. The proposed algorithm was based on fuzzy connectedness and the seed could be selected automatically, A brain tissue extraction algorithm was also presented using region expanding. Experimental results showed that the proposed algorithm displayed more powerful performance than fuzzy c-means （FCM） clustering algorithm and conventional Markov random field （MRF） model-based ones as well. This algorithm is expected to be applied in clinic.