Development of computer aided brain tumor detection methods using machine learning algorithms

Abstract

The fast development of cells in brain may interrupt with nearby newlinecells which lead to the formation of abnormalities in brain. The abnormal newlinecells are clearly viewed in MRI scan. Hence, MRI scanning technique is used newlinein this research work to capture brain regions more effectively than the CT newlinescanning technique. At present, radiologist detects the tumor region or newlineabnormal cells in brain images manually. The developing countries like India, newlinethe manual scanning is not suitable for detecting tumors in brain images, newlinewhich leads to high detection time and more expensive. Hence, there is a newlinerequirement for detecting the tumors in brain images in an automated method. newlineThis research work proposes an automated brain tumor detection system newlineusing image processing techniques. In this research work, Meningioma tumor newlineis detected using GBML classifier. This proposed system consists of newlinepreprocessing, feature extraction and classification stages. In this chapter, newlineGLCM features, Intensity features and Gray Level Run Length Matrix newline(GLRLM) features are derived from the test brain MRI image. These derived newlinefeature set are classified using GBML classification approach. Morphological newlinefunctions are used to segment the tumor region in classified abnormal brain newlineimage. Further, ANFIS classification approach based Glioma brain tumor newlinedetection and segmentation methodology is also proposed in an automated newlinemanner. The main purpose of this research work is to develop an efficient newlinesystem which localizes the tumor boundary with high level of accuracy newline newline