Global and local fuzzy clustering with spatial information for medical image segmentation

This paper presents a new fuzzy clustering algorithm for simultaneous segmentation and bias field estimation of medical images. The proposed algorithm, by introducing the standard fuzzy C-means (FCM) objective function into the coherent local intensity clustering (CLIC) criterion function, formulates a global and local fuzzy clustering based objective function to be minimized. The local fuzzy clustering term allows the algorithm to deal with intensity inhomogeneity in images. The global fuzzy clustering term, being endowed with an adaptive weight function, improves the accuracy of segmentation. Besides, to reduce the impact of noise, the proposed algorithm incorporates spatial information into the membership function. Experiment results on clinical and simulated medical images demonstrate the superior performance of the proposed algorithm.