MR Image Segmentation Based On Fuzzy C-Means Clustering and the Level Set Method

The purpose of this study was to improve the segmentation performance of the level set method for magnetic resonance images (MRI), such as fuzzy boundary or low contrast. In this paper, a level set method was presented in which fuzzy c-means (FCM) was used to prevent boundary leaking during the curve propagated. Firstly, FCM algorithm was used to compute the fuzzy membership values for each pixel, and the edge indicator function was redefined on the basis of FCM. Then the result of FCM segmentation was introduced to obtain the initial contour of level set method. Finally, with the new edge indicator function, the result of brain MR image segmentation showed that the improved algorithm could exactly extract the corresponding tissues of the brain and improve the evolution of the level set function.