Imaging signatures of glioblastoma molecular characteristics: A radiogenomics review

Abstract

Over the past few decades, the advent and development of genomic assessment methods and computational approaches have raised the hopes for identifying therapeutic targets that may aid in the treatment of glioblastoma. However, the targeted therapies have barely been successful in their effort to cure glioblastoma patients, leaving them with a grim prognosis. Glioblastoma exhibits high heterogeneity, both spatially and temporally. The existence of different genetic subpopulations in glioblastoma allows this tumor to adapt itself to environmental forces. Therefore, patients with glioblastoma respond poorly to the prescribed therapies, as treatments are directed towards the whole tumor and not to the specific genetic subregions. Genomic alterations within the tumor develop distinct radiographic phenotypes. In this regard, MRI plays a key role in characterizing molecular signatures of glioblastoma, based on regional variations and phenotypic presentation of the tumor. Radiogenomics has emerged as a (relatively) new field of research to explore the connections between genetic alterations and imaging features. Radiogenomics offers numerous advantages, including noninvasive and global assessment of the tumor and its response to therapies. In this review, we summarize the potential role of radiogenomic techniques to stratify patients according to their specific tumor characteristics with the goal of designing patient-specific therapies. Level of Evidence: 5 Technical Efficacy: Stage 2 J. Magn. Reson. Imaging 2020;52:54-69.

Keywords: glioblastoma; machine learning; magnetic resonance imaging; molecular signatures; radiogenomics; radiomics.

Fig. 1.

A representation of the proper workflow of a radiomic study, which includes the following steps: 1) image acquisition, 2) image processing, including noise/artifact reduction, intensity and/or orientation standardization, co-registration of the multi-parametric MRI scans, 3) region-of-interest definition using manual annotation or (semi-)automatic segmentation, 4) feature extraction based on human-engineered (conventional radiomics) or deep learning approaches, and 5) data analysis, involving machine/deep learning methods for feature selection, classification, and cross-validation. Radiogenomics studies should ideally follow the same workflow, with genomics of glioblastoma as their endpoint.

Fig. 2.

An illustration of descriptive characteristics of mutant EGFRvIII (EGFRvIII+) tumors (adopted from ref. (104) with permission from the authors and the publisher (Oxford University Press, License No. 4636511399697)).