Abstract: The tumor is an undesirable growth of unhealthy tissues which increase intracranial pressure. Magnetic Resonance Imaging is a medical expertise, mainly used by the radiologists for diagnosis of an internal structure of the human body without any surgery. The method proposed in this paper is fuzzy c-means (FCM) and is compared with K-Means segmentation. Followed by tumor detection which will display the presence of a tumor as Abnormal brain whereas the absence of tumor as a normal brain. In the different clusters obtained, it shows different elements of the brain such as white matter, gray matter, edema and CSF (Cerebrospinal fluid) and tumor. A user-friendly environment is created by using GUI in MATLAB which in turn saves the precious time of doctor to diagnose the tumor automatically. Performance analysis using various parameters such as PSNR, Global Consistency error (GCE), Variation of Information (VOI), area, elapsed time, reproducibility, and Rand Index (RI) is done.

Keywords: Fuzzy C-Means, K-MEANS, Brain Tumor, PSNR, Rand Index, Variation of Information, GCE.