Computer-Aided Automatic Segmentation of Brain Tumors using s-FCM on MR Images

Abstract

Brain tumors grow in the skull can threat life in later stages because of the pressure exerted on the brain. Malignant brain tumors have become one of the major causes of human death in recent years. If the tumor can be classified correctly at an early stage, the chances of survival of patients can be improved. Therefore, it is important using a computer-aided diagnosis system to detect brain tumors successfully for radiologists and physicians. In this study, spatial-Fuzzy C-Means (s-FCM) method is used for the automatic segmentation of brain tumors on the MR images. The results obtained by aid of s-FCM are compared with conventional FCM. In addition, application software is designed with a user interface for this purpose. Thus, decision-making by physicians will be provided easily. Consequently, the application software will prevent errors in course of segmentation. The software tool might be also used as a secondary tool for brain tumor segmentation. It has been shown in detailed test experiments on image dataset that proposed system can detect brain tumors successfully.