Automatic Unsupervised Segmentation Methods for MRI Based on Modified Fuzzy C-Means

In medical image analysis, segmentation is an indispensable step in the processing of images. MR has become a particularly useful medical diagnostic tool for cases involving soft tissues, such as in brain imaging [1, 2, 3, 4]. Image segmentation is the process of assigning pixels to regions sharing common properties. Despite the numerous segmentation techniques, image segmentation is still a subject requiring intensive exploration due to the diversity within each application [3, 4, 5, 6, 7, 8, 9, 10, 11]. Approaches to image segmentation have two sorts of objectives, either to extract the contours of body structures (edge-based) or to find out regions containing certain body structures (region-based). For edgebased objective, segmentation is conducted by using differential operator such as Sobel and Laplacian operators to detect intensity discontinuity in the image. The problem is to find a set of points, which