Uveal melanoma (UM) represents the most common primary intraocular malignancy in adults and remains a formidable clinical challenge due to its high metastatic potential and characteristically limited response to conventional systemic therapies. While the combination of radiotherapy and immunotherapy has emerged as a promising multimodal strategy for managing this complex malignancy, its efficacy is significantly constrained by profound individual variations in tumor biology, immune microenvironment composition, and dynamic treatment response patterns. In recent years, artificial intelligence (AI) has fundamentally transformed the landscape of precision oncology by enabling sophisticated image analysis, robust data-driven prediction, and seamless integration of heterogeneous multi-omics information. Within the specific context of uveal melanoma, AI-driven computational models have demonstrated significant potential to accurately predict therapeutic outcomes, quantitatively characterize the tumor immune microenvironment, and optimize radiotherapeutic strategies on a personalized basis. This comprehensive review critically examines and synthesizes recent progress in AI applications for immunoradiotherapy in uveal melanoma, systematically exploring their transformative potential to refine diagnostic accuracy, enhance treatment precision, and ultimately improve long-term patient outcomes through intelligent, data-driven personalized medicine approaches that bridge multiple disciplinary boundaries.
Gu et al. (Thu,) studied this question.