A machine learning classification approach based glioma brain tumor detection

Abstract

AbstractThis article develops a computer aided fully automated method for detecting and classifying the glioma brain magnetic resonance imaging (MRI) using machine learning classification approach. The noise contents in source brain MRI image are detected and removed using ridgelet filter and then the edges in noise removed image are detected using fuzzy logic and then contrast adaptive local histogram equalization is applied on the edge detected brain image for enhancing the edge pixels. The Gabor transformation is applied on the enhanced brain image and the features are computed from this transformed image. The computed features are optimized using feature optimization technique genetic algorithm (GA) and the optimized features are classified using adaptive neurofuzzy inference system (ANFIS) classification method, which classifies the source brain MRI image into either glioma or non‐glioma brain image. Finally, fuzzy C means algorithm is applied on the glioma brain image to segment the tumor regions. The segmented tumor regions in glioma brain image is compared with manually tumor segmented brain image in order to evaluate the performance efficiency of the proposed system and the simulation results shows that the proposed works in this article achieves optimum performance with state of the art methods.