Segmentation of MR brain image using multi atlas matching technique

Abstract

Detection of brain tumor from Magnetic Resonance Image (MRI) image has become one of the most active researches in the field of medical image processing. Segmentation and Detection of tumor play a major role in biomedical imaging. In this research, tumor segmentation process is done with MR brain image. The proposed method contain image pre processing, image enhancement using Contrast Limited Adaptive Histogram Equalization (CLAHE) and segmentation with multi atlas matching and detection of tumor. The proposed work segment the tumor region precisely from the MR brain image. The experimental result gives an average of 0.85 Dice Similarity Co efficient (DSC), which indicates that the proposed method is efficient in segmentation and detection of the tumor region from the MR brain image.