基于全局熵最小化的MRI图像分割算法  

Segmentation algorithm for MRI images based on global entropy minimization

作　　者：朱卫华[1] ZHU Wei - hua(Xinyu University, Xinyu 338004 Chin)

机构地区：[1]新余学院数学与计算机学院,江西新余338004

出　　处：《新余学院学报》2017年第4期1-5,共5页Journal of Xinyu University

基　　金：江西省教育厅科技计划项目"基于模糊C-Means算法的脑部MRI图像分割机理研究"(GJJ161183)

摘　　要：医学图像处理在支持各种疾病的诊断中起着重要的作用。脑磁共振成像(MRI)图像被广泛用于支持医生决定一个大脑是否存在问题。MRI的本质是分割,这是损伤区域选择、定量测量和三维重建的基础。为了有效地识别定位对象,提出了一种全局熵最小化的分割算法。该算法采用基于聚类区域图像模型的二次分割方法以避免移动分割造成的不利影响。从实验数据来看,该算法和FCMA以及LBFC算法相比较,性能更佳,精度更高。Medical image processing plays an important role in supporting the diagnosis of various diseases. Brain magnetic resonance imaging （MRI） image is widely used to support the decisions from doctors who will decide if there is any problem in a brain. The es- sence of the MRI is segmentation which is the basis for damaged area selection, quantitative measurement and 3 - dimensional recon- struction. In order to effectively identify the located objects, this paper introduces a segmentation algorithm using global entropy minimi- zation. This algorithm uses two - time segmentation approach based on the cluster area image model to overcome the negative influences of shifted segmentation. Experiments show that the proposed algorithm gets the better performance and keeps the higher accuracy than LBFC and FCMA.

关 键 词：算法 MRI 图像分割 全局熵 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]