An unsupervised modified spatial fuzzy C-mean method for segmentation of brain MR image

摘要

Unsupervised segmentation of Magnetic Resonance Images (MRI) especially brain MRI is an eminent role for medical and scientific research purpose. The recent trend of medical image analysis and segmentation is laid on the super voxel and spatial information within the super voxel of magnetic resonance images. We propose a new local spatial membership function inherent within the unsupervised modified spatial fuzzy c-mean method to compute the optimized cluster centers with a minimum number of iteration. The proposed local spatial membership function deals with the noise sensitivity and uncertainties incumbent by the heterogeneity and bias field. The comparative study shows that the proposed method is significantly improved the cluster validation functions (i.e. partial coefficient and partial entropy etc.) as compared to the recently published FCM based works.