From scans to survival: artificial intelligence-driven radiomics in colorectal cancer chemotherapy

Colorectal cancer (CRC) remains the third most common cancer and the second leading cause of cancer-related mortality worldwide, with approximately one-third of patients diagnosed at stage II.1 For this subgroup, the absolute overall-survival gain from fluoropyrimidine-based adjuvant chemotherapy is consistently less than 5%,2 and the current guidelines recommend this treatment only for “high-risk” individuals.3 Unfortunately, conventional risk factors such as poor differentiation, tumor perforation or obstruction, perineural invasion and lymphovascular invasion have limited predictive accuracy in routine practice, resulting in suboptimal patient stratification and potential overtreatment or undertreatment.