Local-based Fuzzy Clustering Algorithm for Magnetic ResonanceBrain Images Corrupted by Intensity Heterogeneity

The segmentation of magnetic resonance imaging (MRI) with intensity heterogeneity is a challenging problem that has received an enormous amount of attention lately. In this paper, we propose a simple and effective segmentation method called local-based fuzzy clustering (LBFC) for MR brain images that corrupted by intensity heterogeneity. Firstly, a two-tissue-based method (TTBM) is proposed to generate the contexts for all pixels. This method is based on the distributing disciplinarian in anatomy that gray matter (GM) is always between white matter (WM) and cerebrospinal fluid (CSF) in brain. Then fuzzy clustering is independently performed in each context to calculate the membership of a pixel to each tissue class. The efficacy of the proposed algorithm is demonstrated by extensive segmentation experiments using both simulated and real MR images and by comparison with other published algorithm.