Robust segmentation of brain MRI images using a novel fuzzy c-means clustering method

Segmentation of brain magnetic resonance imaging (MRI) images is greatly significant in neuroscience field. We propose a novel FCM method for segmentation of brain MRI images that makes full use of both the image intensity and spatial feature information. The proposed method can handle images having intensity inhomogeneity and noises by using the regularization that does not only consider the bias field but also takes neighborhood influence into account. Experiment indicates that the novel FCM method achieves more accurate and robust results in segmentation of brain MRI images compared to the expectation-maximization (EM) method and the conventional FCM method.