GRGE: Detection of Gliomas Using Radiomics, GA Features and Extremely Randomized Trees

Abstract

Gliomas originates in glial cells and recognized as one of the most malignant and dangerous brain tumors and categories into two major classes i.e., High Grade Glioma (HGG) and Low Grade Glioma (LGG). Out of both, HGG tumors are more aggressive. Classification of grade of glioma is a crucial task for deciding the treatment therapy and estimating survival period of patient. In this work, a computational approach based on Radiomics and machine learning algorithms, namely GRGE, is proposed to discriminate between HGG and LGG. The approach, GRGE, has performed better than several state-of-art methods proposed in the literature for glioma classification.