Opportunities and Advances in Radiomics and Radiogenomics in Neuro-Oncology

摘要

Neuro-oncology broadly encompasses life threatening malignancies of the brain and spinal cord including both primary as well as lesions metastasizing to the central nervous system. The biggest clinical challenge in the field currently is to be able to design personalized treatment management solutions in patients based on apriori knowledge of their survival outcome or response to conventional or experimental treatments. Radiomics or the quantitative extraction of subvisual data from conventional radiographic imaging and radiogenomics, statistically correlating radiomic features with point-mutations and next generation sequencing data, have recently emerged as unique mechanisms to offer insights into answering some of these clinically relevant questions related to diagnosis, classification, prognosis as well as assessing treatment response. In this review, we provide an overview of the framework for radiomic and radiogenomic approaches in neuro-oncology, including a brief description of the techniques commonly employed. Further, we will provide a review of some of the existing applications of radiomics and radiogenomics in neuro-oncology for tumor classification, survival prognosis, predicting response to therapies, as well as distinguishing benign post-treatment changes from tumor recurrence, using routine MRI scans. While highly promising, the clinical acceptance of radiomics and radiogenomics techniques will largely hinge on their resilience to non-standardization across imaging protocols, as well as in their ability to demonstrate reproducibility across large multi-institutional cohorts.