Demarcation of Brain Tumor Using Modified Fuzzy C-Means

The Demarcation and prediction of the area of the tumor have an important role in medical treatments of malignant tumors. This paper describes an application of Fuzzy set theory in medical image processing, namely brain tumor demarcation. Fuzzy C-Means is proved to be a good and efficient segmentation method. But the main disadvantage of this method is that it is highly sensitive to noise. In this paper a modified Fuzzy CMeans (MFCM) is proposed which is less sensitive to noise than state-of-the-art Fuzzy C-Means method. MFCM filters the image at the time of the segmentation of noisy Magnetic Resonance Imaging (MRI) images. This methodology is applied to the three MRI images of brain consisting tumors with different areas. The proposed method always`s results in better segmentations of brain tumors than conventional FCM. This method is applied efficiently for detection of contour and dimensions of a brain tumor.