Early characterization and prediction of glioblastoma and brain metastases treatment efficacy using medical imaging-based radiomics and artificial intelligence algorithms

In brain tumors, glioblastoma (GBM) is the most common and aggressive’s one and brain metastases (BM) are occurring in 20-40% of cancer patients. Even with intensive treatment involving radiotherapy and surgery, which frequently leads to cognitive decline due to doses on healthy brain tissue, the median survival is 15 months for GBM and about six to nine for BM. Despite these treatments, GBM patients respond heterogeneously as do patient with BM. Following standard of care, some patients will respond and have an overall survival of more than 30 months and others will not respond and will die within a few months. Differentiating non-responders from responders as early as possible in order to tailor treatment in a personalized medicine fashion to optimize tumor control and preserve healthy brain tissue is the most pressing unmet therapeutic challenge. Innovative computer solutions recently emerged and could help for this challenge. This review will focus on fifty published research between 2013 to 2024 on (1) the early characterization of treatment efficacy with biomarkers imaging and radiomic-based solutions, (2) predictive solutions with radiomic and artificial intelligence-based solutions, (3) interest of other biomarkers and (4) the importance of the prediction of new treatment modalities efficacy.