Brain tumor segmentation using wavelet Multi-resolution expectation maximization algorithm

Abstract

Magnetic Resonance Imaging is one of the most important tools for diagnosing brain cancer. The variation in shape, size, location and structure of brain tumors makes it challenging for segmentation. Accurate brain tumor segmentation helps in taking accurate treatment decisions. In this paper, the Wavelet Multiresolution Expectation Maximization (WMEM) algorithm is explained and applied on brain MRI for tumor segmentation. The performance of the algorithm is evaluated using real Magnetic Resonance Imaging (MRI) images with segmented ground truth.