Brain Tissue Segmentation by FCM and Dempster-Shafer Theory

As a result of noise and intensity non-uniformity, automatic segmentation of brain tissue in magnetic resonance image (MRI) is a complicated concern. In this study a novel brain MRI segmentation approach is presented which employs Dempster-Shafer Theory (DST) for information fusion. In the proposed method, Fuzzy C-mean (FCM) is applied to separate features and then the outputs of FCM are interpreted to basic belief structures. The salient aspect of this work is the interpretation of each FCM outputs to the belief structures with particular focal elements. The Results of the proposed method are evaluated using Dice´s similarity index. Qualitative and quantitative comparisons demonstrate that our method has better results and is more robust than other algorithm.