Background/Objectives:Liver cancer is an exceedingly heterogeneous malignancy with high mortality rates, and despite extensive research, there have been no significant improvements in treatment outcomes. In the process of navigating the complex landscape of liver cancer, AI has arisen as the “knight in shining armour”, sparking hope and offering invaluable insight into early detection, diagnosis, staging, treatment selection, and post-treatment surveillance. By integrating imaging, clinical, pathological, and molecular data, AI emerges as a transformative tool that offers unique opportunities to enhance patient care.Methods:A comprehensive literature search of PubMed and Scopus, was conducted using the terms “artificial intelligence,” “machine learning,” “deep learning,” “radiomics,” and “liver cancer.” Eligible studies included peer-reviewed original research applying AI to detection, diagnosis, prognosis, treatment planning, or surveillance of liver cancer. Key findings are organized along the clinical continuum.Results:Imaging-based AI models for tumor detection were the most advanced, with several achieving diagnostic accuracy above 90% in retrospective studies. Applications for treatment decision-making are emerging, but most remain at proof-of-concept stages. Generally, few of these innovations have progressed to large-scale clinical trials or received regulatory approval, slowing their integration into clinical practice.Conclusions:This narrative review highlights AI’s potential to transform liver cancer management and addresses the ethical, regulatory, and logistical barriers to its clinical adoption, serving as a call to action for integrating AI into practice to improve patient outcomes.
背景/目的：肝癌是一种具有高度异质性的恶性肿瘤，死亡率居高不下，尽管已有大量研究，但治疗效果并未取得显著改善。在探索肝癌复杂诊疗格局的过程中，人工智能犹如"身披闪亮盔甲的骑士"般崛起，为早期检测、诊断、分期、治疗方案选择及治疗后监测带来了新的希望与宝贵洞见。通过整合影像学、临床、病理及分子数据，人工智能正成为一种变革性工具，为提升患者诊疗水平提供了独特机遇。 方法：本研究系统检索了PubMed和Scopus数据库，使用"人工智能"、"机器学习"、"深度学习"、"影像组学"及"肝癌"等关键词进行文献筛选。纳入标准为经同行评议、应用人工智能技术于肝癌检测、诊断、预后评估、治疗规划或监测领域的原创研究。关键发现按临床诊疗流程进行系统性梳理。 结果：基于影像学的肿瘤检测人工智能模型发展最为成熟，多项回顾性研究显示其诊断准确率超过90%。用于治疗决策的人工智能应用正在兴起，但多数仍处于概念验证阶段。总体而言，这些创新技术中仅有少数进入大规模临床试验或获得监管批准，这延缓了其在临床实践中的整合进程。 结论：本综述系统阐述了人工智能变革肝癌诊疗模式的潜力，同时剖析了其临床转化面临的伦理、监管及实施层面的障碍，旨在呼吁推动人工智能与临床实践的深度融合，以最终改善患者预后。
Turning the Tide—Artificial Intelligence in the Evolving Landscape of Liver Cancer
肿瘤(癌症)患者之家