Novel segmentation algorithm in segmenting medical images |
| |
Authors: | SR Kannan [Author Vitae] A Sathya [Author Vitae] [Author Vitae] R Devi [Author Vitae] |
| |
Affiliation: | a Department of Electrical Engineering, National Cheng Kung University, Tainan 70701, Taiwan b Department of Mathematics, Gandhigram Rural University, Gandhigram 624 302, India c Department of Engineering Science, National Cheng Kung University, Tainan 70701, Taiwan d Department of Mathematics, MVM Govt. College, Dindigul, India |
| |
Abstract: | The aim of this paper is to develop an effective fuzzy c-means (FCM) technique for segmentation of Magnetic Resonance Images (MRI) which is seriously affected by intensity inhomogeneities that are created by radio-frequency coils. The weighted bias field information is employed in this work to deal the intensity inhomogeneities during the segmentation of MRI. In order to segment the general shaped MRI dataset which is corrupted by intensity inhomogeneities and other artifacts, the effective objective function of fuzzy c-means is constructed by replacing the Euclidean distance with kernel-induced distance. In this paper, the initial cluster centers are assigned using the proposed center initialization algorithm for executing the effective FCM iteratively. To assess the performance of proposed method in comparison with other existed methods, experiments are performed on synthetic image, real breast and brain MRIs. The clustering results are validated using Silhouette accuracy index. The experimental results demonstrate that our proposed method is a promising technique for effective segmentation of medical images. |
| |
Keywords: | Fuzzy c-means Clustering Kernel function Gaussian function Image segmentation |
本文献已被 ScienceDirect 等数据库收录! |
|