Radiogenomics of Glioblastoma: Identification of Radiomics associated with Molecular Subtypes

TL;DR

This study explores how radiomics features from MRI images correlate with molecular subtypes of glioblastoma, aiming to improve non-invasive subtype classification and understanding of tumor heterogeneity.

Contribution

It introduces a radiomics-based approach to identify associations with glioblastoma subtypes, achieving high accuracy in subtype prediction.

Findings

Fractal dimensions differ significantly among subtypes.

Radiomics predicts subtypes with 79% accuracy.

Gene expression profiles predict subtypes over 90% accuracy.

Abstract

Glioblastoma is the most malignant type of central nervous system tumor with GBM subtypes cleaved based on molecular level gene alterations. These alterations are also happened to affect the histology. Thus, it can cause visible changes in images, such as enhancement and edema development. In this study, we extract intensity, volume, and texture features from the tumor subregions to identify the correlations with gene expression features and overall survival. Consequently, we utilize the radiomics to find associations with the subtypes of glioblastoma. Accordingly, the fractal dimensions of the whole tumor, tumor core, and necrosis regions show a significant difference between the Proneural, Classical and Mesenchymal subtypes. Additionally, the subtypes of GBM are predicted with an average accuracy of 79% utilizing radiomics and accuracy over 90% utilizing gene expression profiles.