Automated classification of magnetic resonance brain images using bi- dimensional empirical mode decomposition

Abstract

Automated classi cation of brain magnetic resonance (MR) images has been an exten- sively researched topic in biomedical image processing. In this work, we propose a new approach for classifying normal and abnormal brain MR images using bi-dimensional empirical mode decomposition (BEMD) and autoregressive (AR) model. In our ap- proach, brain MR image is decomposed into bi-dimensional intrinsic mode functions (IMFs) using BEMD and AR coe cients from IMFs are used to form a feature vector. Finally, a binary classi er, least square support vector machine (LS-SVM), is employed to discriminate between normal and abnormal brain MR images. The proposed tech- nique achieves 100% classi cation accuracy using second order AR model with linear and radial basis function (RBF) as kernels in LS-SVM clissi er. Experimental results also show that the performance of the proposed method is quite comparable with the existing results.