An Advanced Approach for Extraction of Brain Tumor from Digital MR Images Using Morphology Gradient & ART

Abstract

In this work, An Advanced Approach has been proposed for the detection and extraction of brain tumor from magnetic resonance images (MRIs). Magnetic resonance images are visualized and examined using the high order of Angular Radial Transform (ART) and morphological gradient. The Angular Radial Transform (ART) is one of the region-based shape descriptors have many desirable properties such as rotation invariance, robustness to noise, and scale changes. This approach is based on the three steps. Before the segmentation process, the pre-processing of the original image is done by median filter to remove the noise. Then, the morphological gradient is computed and added to the filtered image, and the local statistics values obtained from the high order angular radial transform which are used to calculate the appropriate threshold value. After thresholding, the features of 36 ART of high order are used to extract tumor. These features are then used as input to a support vector machine (SVM) to classify images between normal and abnormal. The experimental results show that the proposed approach is successful to analyze the tumor of the image on testing with different MRIs.