Smart dosing: revolutionizing uveal melanoma treatment with AI.

Abstract

Uveal melanoma, the most common primary intraocular malignancy in adults, presents a significant challenge due to its high metastatic potential and the need to preserve vision during treatment. While conventional therapies such as plaque brachytherapy and proton beam radiation aim to balance tumor control with ocular preservation, recent advances in artificial intelligence (AI) and machine learning (ML) offer transformative potential in personalizing radiation dosing. By integrating radiologic features with genomic markers such as BAP1 mutations, monosomy 3, and chromosome 8q gain, AI models can predict tumor radiosensitivity and guide dose modulation based on individual tumor biology. This precision approach may enhance treatment efficacy while minimizing toxicity to surrounding ocular structures. However, the deployment of AI in clinical oncology also raises ethical concerns, including the risk of algorithmic bias and the need for data diversity, regulatory oversight, and interdisciplinary collaboration. Responsible integration of AI into radiation oncology could redefine treatment strategies for uveal melanoma, ushering in a new era of radiogenomics-driven precision medicine.