AN EFFICIENT BRAIN TUMOR DETECTION USING EXPECTATION MAXIMIZATION ALGORITHM

Abstract

Brain tumor is a deadly disease. The detection of brain tumor from Magnetic Resonance Imaging (MRI) is a challenging one. The accuracy in the detection of tumor growth in different regions of brain depends upon the selection of various segmentation and feature extraction techniques. Although multimodal MRI images can provide complementary information in the tumor area, brain tumor segmentation is still a challenging and difficult task. Varying intensity of tumors in MRI makes the automatic segmentation of such tumors extremely challenging. In this paper, we propose a novel method for the detection of brain tumor growth. For preprocessing and segmentation of MRI images, K-means clustering and Expectation-Maximization (EM) algorithms are used. The features are extracted and the proposed techniques provide better performance for tumor detection.