Modi ed Fuzzy C - Mean in Medical Image Segmentation

|This paper describes the application of fuzzy set theory in medical imaging, namely the segmentation of brain images. We propose a fully automatic technique to obtain image clusters. A modi ed fuzzy c-mean (FCM) classi cation algorithm is used to provide a fuzzy partition. Our new method, inspired from the Markov Random Field (MRF), is less sensitive to noise as it lters the image while clustering it, and the lter parameters are enhanced in each iteration by the clustering process. We applied the new method on a noisy CT scan and on a single channel MRI scan. We recommend using a methodology of over segmentation to the textured MRI scan and a user guided-interface to obtain the nal clusters. One of the applications of this technique is TBI recovery prediction in which it is important to consider the partial volume. It is shown that the system stabilizes after a number of iterations with the membership value of the region contours reecting the partial volume value. The nal stage of the process is devoted to decision making or the defuzzi cation process. Keywords|Fuzzy c-mean, Image Segmentation, Fuzzy clustering, Adaptive lter.