A fuzzy C-means model based on the spatial structural information for brain MRI segmentation

被引：7

作者：

Wang, Shunfeng ^{[1
]}

Geng, Zhiyuan ^{[1
]}

Zhang, Jianwei ^{[1
]}

Chen, Yunjie ^{[1
]}

Wang, Jin ^{[2
]}

机构：

[1] School of Mathematics and Statistics, Nanjing University of Information Science and Technology, Nanjing 210044, China

[2] School of Computer and Software, Nanjing University of Information, Science and Technology, Nanjing 210044, China

来源：

International Journal of Signal Processing, Image Processing and Pattern Recognition | 2014年 / 7卷 / 01期

关键词：

Magnetic resonance imaging - Fuzzy clustering - Clustering algorithms;

D O I：

10.14257/ijsip.2014.7.1.29

中图分类号：

学科分类号：

摘要：

Due to the effect of noise in brain MR images, it is difficult for the traditional fuzzy c-means (FCM) clustering algorithm to obtain desirable segmentation results. Combining the information of patch to reduce the effect of noise has been a focus of current research. However, the traditional patch model is isotropic, so that it would lose the structural information easily. In this paper, a novel fuzzy c-means model based on the spatial similarity information is proposed. To be anisotropy and preserve more structural information, this model takes both the non-local information and spatial structural similarity measurement (SSIM) between the image patches into consideration, and then a new distance function is established between every pixels and category centers for image segmentation. The efficiency of the proposed algorithm is demonstrated by extensive segmentation experiments using both synthetic and real brain MR images and by comparison with other state of the art algorithms. © 2014 SERSC.

引用

页码：313 / 322