“…Many studies have indicated that radiomics can be a valuable tool to facilitate precision diagnosis, treatment planning, and predicting outcomes [ 22 ]. In recent years, it has been shown that integrating quantitative medical imaging biomarkers into clinical and dosimetric data has improved the prediction of radiation-induced toxicities in the treatment of various cancers [ 19 , [23] , [24] , [25] , [26] ]. Moreover, the advances in AI, principally machine learning models, have boosted the potential of the typically high-dimensional quantitative radiomics features (RFs) in predicting RT-induced toxicity [ [26] , [27] , [28] ].…”