The use of artificial intelligence in stereotactic ablative body radiotherapy for hepatocellular carcinoma

The integration of artificial intelligence (AI) into stereotactic ablative body radiotherapy (SABR) for hepatocellular carcinoma (HCC) is transforming the landscape of liver cancer treatment. SABR has emerged as a promising treatment option for patients with localized HCC, offering high local control rates and favorable toxicity profiles. As evidence supporting SABR's clinical efficacy continues to grow, AI technologies are accelerating its adoption by enhancing precision, efficiency, and individualization of care. This review summarizes recent advances in AI applications across the SABR workflow, including automated contouring, knowledge-based planning, fluence prediction via deep learning, respiratory motion modeling, liver function estimation, and prognostic modeling. Clinical studies have demonstrated notable benefits, such as a reduction in contouring time and improved dosimetric quality using machine learning-based optimization algorithms. However, critical limitations persist. Many AI models are trained on limited datasets without external validation, raising concerns about overfitting and generalizability. Future efforts should focus on improving model transparency, confirming their reliability across different institutions, and ensuring ethical use in real-world clinical practice.