Brain MRI Medical Image Segmentation Using Fuzzy Based Clustering Algorithms

In this paper, the performance of the various fuzzy based algorithms for medical image segmentation is presented. Fuzzy c-means (FCM) algorithm has proved its effectiveness for image segmentation. However, still it lacks in getting robustness to noise and outliers, especially in the absence of prior knowledge of the noise. To overcome this problem, different types of fuzzy algorithms are introduced with and without spatial information for medical image segmentation. The algorithm utilizes the spatial neighborhood membership values in the standard kernels are used in the kernel FCM (KFCM) algorithm and modifies the membership weighting of each cluster. In this paper, the available various fuzzy algorithms are tested on brain MRI which degraded by Gaussian noise and Salt-Pepper noise. The performance is tested in terms of score for the clustering of images. Keywords-FCM, Image Segmentation, membership functions, fuzzy, multiple-kernal.