ESUR 工作组前列腺 MRI 人工智能检测现状与方向特别报告
本报告由 ESUR 前列腺 MRI 工作组撰写,评估人工智能在前列腺 MRI 癌症检测中的当前作用。报告指出深度学习工具技术准确率高,但研究与临床实际应用之间仍存在显著差距。主要建议包括推行「human-in-the-loop」模式、开展多供应商前瞻性验证及实施上市后监测。
要点
- AI 应支持而非替代放射科医师判断,采用「human-in-the-loop」模式以降低自动化偏倚和法律风险。
- 临床部署前需完成多供应商前瞻性验证,并进行本地验证与用户培训。
- 需实施上市后监测以追踪算法漂移,保障肿瘤学安全性。
核心结论
- 深度学习方法在前列腺 MRI 癌检测中技术准确率高,但研究结果与临床实际应用之间存在显著差距。
- AI 工具应定位为支持放射科专业判断,而非替代放射科医师。
- 需开展多供应商前瞻性验证并实施上市后监测以监测算法漂移。
研究设计与样本
- 制定机构为 ESUR 前列腺 MRI 工作组,属于特别报告性质。
- 报告内容为对 AI 在前列腺 MRI 癌检测中现状评估与未来研究方向建议。
诊断标准与关键数值
- 推行「human-in-the-loop」方法,即 AI 支持而非替代放射科专业判断。
- 需在多供应商条件下开展前瞻性验证。
- 实施上市后监测以监测算法漂移并保障肿瘤学安全性。
临床应用与阅片要点
- AI 工具纳入前列腺诊断 MRI 工作流前应进行本地验证。
- 需对使用者进行充分培训,并建立持续监测机制。
- 阅片中应保持医师主导判断,避免对 AI 输出的自动化偏倚。
局限性
- 缺乏真实世界验证。
- 人机交互动力学复杂,可能影响 AI 实际使用效果。
- 以人群为基础的前列腺癌筛查场景中 AI 部署面临独特挑战。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
英文原文(摘要)· 点击展开
This report from the ESUR Prostate MRI Working Group assesses the current role of artificial intelligence (AI) in MRI-based detection of prostate cancer. While deep learning tools demonstrate high technical accuracy, the report emphasizes a significant gap between research achievements and actual clinical application. Key statements include promoting a "human-in-the-loop" approach, where AI supports rather than replaces radiological expertise, to reduce risks such as automation bias and legal liability. There is an urgent need for prospective validation across multiple vendors and for implementing post-market surveillance to monitor algorithmic drift. Finally, the group identified research priorities focused on cost-effectiveness, transparency via explainable AI, and addressing the unique challenges of deploying these tools in population-based screening programs. KEY POINTS: Question What challenges hinder the clinical adoption of AI-based medical devices for prostate cancer detection? Findings Major obstacles include insufficient real-world validation, complex dynamics of human-AI interactions that require a human-in-the-loop approach, and the need for ongoing post-market surveillance for oncologic safety. Clinical relevance This report highlights the gap between AI's research promise and clinical readiness. It underscores the need for localvalidation, post-market surveillance, and adequate user training as AI tools become incorporated into diagnostic prostate MRI workflows.
引用
- Cuocolo, Ponsiglione, Agrotis, et al. Current status and future directions of AI in prostate cancer detection on MRI: a special report from the ESUR prostate MRI working group authors. Eur Radiol. 2026. PMID: 42760428. doi:10.1007/s00330-026-12836-6
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。