Optimizing Medical Image Classification Using Diverse Feature Extraction Methods for Brain Tumor

Abstract

Detecting brain tumor early and accurately is crucial for effective treatment and better patient outcomes. Three feature extraction methods are used in this study: Gray Level Run Length Matrix (GLRLM), Gray Level Co-occurrence Matrix (GLCM), and Gray Level Histogram Features (GLHF)—to classify MRI images of the brain. GLCM measures the relationship between pixel intensities to capture texture information, while GLRLM finds patterns of pixels with similar gray levels, showing areas of texture. The histogram method summarizes the overall intensity in the image, highlighting differences between normal and abnormal areas. A Support Vector Machine (SVM), a classifier designed to differentiate between brain tissue affected by tumors and normal tissue, processes these retrieved features. Using a typical MRI dataset, the research assesses how well each feature extraction method supports accurate classification by the SVM. By comparing their performance, the study identifies which technique is best for distinguishing between healthy and tumor regions in the brain. This analysis offers valuable insights into improving brain tumor detection, potentially benefiting clinical diagnosis and treatment planning.