Integrating fuzzy entropy clustering with an improved PSO for MRI brain image segmentation

Abstract

This article describes a new clustering method for segmentation of Magnetic resonance imaging (MRI) brain images. Currently, when fuzzy clustering is applied to brain image segmentation, there are two main problems to be solved which are: (i) the sensitivity to noise and intensity non-uniformity (INU) artifact; (ii) the trapping into local minima and dependency on initial clustering centroids. For the purpose of obtaining satisfactory segmentation performance and dealing with the problems mentioned above, an effective method is developed within the scope of this paper. Firstly, a new objective function utilizing kernelized fuzzy entropy clustering with local spatial information and bias correction (KFECSB) is designed. We then propose a new algorithm based on an improved particle swarm optimization (PSO) with the new fitness function to better segment MRI brain images. To test its performance, the proposed algorithm has been evaluated on several benchmark images including the simulated MRI brain images from the McConnell Brain Imaging Center (BrainWeb) and the real MRI brain images from the Internet Brain Segmentation Repository (IBSR). In addition, a systematic comparison of the proposed algorithm versus five other state of the art techniques is presented. Experimental results show that the proposed algorithm can achieve satisfactory performance for images with noise and intensity inhomogeneity, and provide better results than its competitors.