I. Introduction
A brain tumor is an uncontrolled cell division activity which has become one of the major causes for the increased rate of mortality among adults and children [1]. According to the World Health Organization and American Brain Tumor Association [2], brain tumors can be divided into four grades. Grade I and grade II are slow growing benign tumors, also called low-grade tumors. On the contrary, grade III and grade IV are rapid growing malignant tumors, also known as high-grade tumors shown in Fig. 1. According to National Brain Tumor Foundation (NBTF) for research in the United States, brain tumors cause one-quarter of the total cancer death in children. Also, NBTF statistics shows that in developed countries the number of people who develop brain tumors and die from them has increased perhaps as much as 300% over past three decades [3]. Early detection of brain tumor is very important and in this context, an automated system can be a great tool to interpret the tumor images and analyze tumor area.