摘要
准确的MRI图像分割是脑部定量分析和三维重建的基础,对病变的诊断和治疗具有重要意义。传统的模糊C均值聚类方法针对脑部MRI图像处理存在一定局限性,未能获得满意的分割结果。为此,提出一种改进的模糊C均值聚类分割方法,不但考虑了图像偏移场,而且通过在传统的模糊聚类算法中引入邻域信息约束分割过程。实验结果显示,改进的模糊C均值聚类方法优于传统的模糊C均值聚类方法,有利于从脑部MRI图像中较好的分割出白质、灰质和脑脊液。
Accurate segmentation of MRI images is the basis of brain quantitative analysis and threedimensional reconstruction, which is of great significance in lesion diagnosis and treatment. The conventional FCM algorithm has some limitations in the brain MRI image processing,and it cannot obtain satisfactory segmentation results. Then,this paper proposes an improved FCM method which takes the bias field into account and introduces a term of the pixel＇s neighboring information into the conventional FCM algorithm. The results indicate that the improved FCM is superior to the conventional FCM algorithm and obtains reasonable segmentation of white matter,gray matter and cerebrospinal fluid.
作者
张静
周佐
ZHANG Jing;ZHOU Zuo(School of Information Technology and Communication,Hexi University,Zhangye 734000,Gansu Province,China;School of Physics and Electromechanical Engineering,Hexi University,Zhangye 734000,Gansu Province,China)
出处
《信息技术》
2018年第6期76-80,共5页
Information Technology
基金
河西学院青年教师科研基金资助项目(QN2014-25)
关键词
脑部MRI图像
边缘检测
阈值分割
聚类分割
偏移场
brain MRI image
edge detection
threshold segmentation
clustering segmentation
bias lield
