The Use of Radiomics for Prognosis, Treatment Response Prediction and Risk Stratification in Anal Cancer - A Systematic Review

Introduction Anal cancer is a rare but increasing malignancy affecting the anal canal that requires significant planning and medical management to address. Radiomics holds promise for improving both the improving prognosis, treatment-response prediction and personalised management of this cancer by analyzing quantitative imaging features from radiological assessments. This study aims to examine the most up-to-date literature on the use of radiomics in the prognostication, treatment-response prediction and risk stratification. Methods A systematic search of the literature was performed between 1st January 2006 and 1st January 2026 across five databases: PubMed, Scopus, Embase, Web of Science and Cochrane Central Register of Controlled Trials (CENTRAL). Inclusion criteria required articles to explore the use of radiomics in anal cancer, pre, peri, or post treatment. Each study was assessed for quality using the PROBAST and Radiomics Quality Score tools. Results Fifteen papers encompassing a total of 1,466 reported participants investigated the use of radiomics in anal cancer across four application domains. Prediction of recurrence in anal cancer (7 Studies), prediction of treatment response following CRT (3 Studies), prediction of survival in anal cancer (4 Studies), and prediction of risk factor status for anal cancer (1 Study). Across studies, radiomic models consistently outperformed clinical variables alone, with combined clinical–radiomic models demonstrating improved discrimination (reported AUCs as high as 0.95, externally validated c-indices approximately 0.70). PET-derived volumetric parameters (particularly MTV) and MRI-based texture features were the most reproducible predictors of recurrence and survival. Conclusion Radiomics demonstrates promising potential in risk stratification and managing anal cancer, with the potential to influence clinical decisions. While more research is necessary before it can be widely adopted in medical practice, radiomics will help enable personalized medicine through risk assessment, and optimization of treatment options for improved patient outcomes.