Implementation and Comparison of Image Segmentation Methods for Detection of Brain Tumors on MR Images

Abstract

Brain tumors grow in the skull and they can be life threatening 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. The most appropriate treatment to be selected for brain cancer depends on precisely identifying of tumor type, location, size and boundaries by the physicians. Thus, it is important using a computer-aided diagnosis / detection system to detect brain tumors successfully for radiologists and physicians. In this study, Fuzzy C-Means (FCM), Otsu's method, Region Growing and Self-Organizing Maps methods is used for the automatic segmentation of brain tumors on the MR images and results are compared with each other. Application software is designed with a user interface for this purpose. Thus, the ease of decision-making by physicians will be provided. Consequently, the application software will prevent errors and may be used as a secondary means for brain tumor segmentation. It has been shown in detailed test experiments on image dataset that designed application can detect brain tumors successfully.