Computer-Aided Diagnosis of Malign and Benign Brain Tumors on MR Images

Abstract

Determination of the most suitable type of treatment for brain cancer depends on the accurate detection of the type, location, size and borders of the tumor. Computer-aided diagnosis(CAD) systems help to physician in order to facilitate realizing of these aims. In this study, a CAD system was designed to detect brain tumors with computer assistance using T1 and T2 weighted MR images. The designed system segments brain tumor region of MR image using spatial-Fuzzy C-Means(FCM) method. Also, features of tumor region are extracted with image processing methods. Subsequently, support vector machine(SVM) is used for classification of benign and malign tumors in the CAD system. According to detailed test results, the proposed CAD system recognizes brain tumors with 91.49% accuracy, 90.79% sensitivity and 94.74% specificity. © Springer International Publishing Switzerland 2015.