A modified fuzzy C-means for bias field estimation and segmentation of brain MR image

Fuzzy C-means clustering (FCM) algorithm is good at solving the ambiguities and uncertainties in the image, and the modified FCM has been widely used in solving the intensity inhomogeneity problem. Bias-corrected FCM (BCFCM) is very useful for noise and intensity inhomogeneity image segmentation, but it can't estimate accurately the pixels on the boundary especially in the regions with heavy level of intensity inhomogeneous. In this paper, we present a novel algorithm for brain magnetic resonance imaging (MRI) Image segmentation and intensity inhomogeneity estimation based on BCFCM. The proposed algorithm introduces the global intensity information into the algorithm BCFCM, for the smooth bias field estimation and more accurate segmentations. The proposed method has been successfully applied to MR brain images, and experiment results show that this method is superior to FCM, BCFCM and some other approaches.