AI 无需训练即可根据指南自动勾画放疗靶区，准确率媲美人工标注模型。
A Guideline-Aware AI Agent for Zero-Shot Target Volume Auto-Delineation
- 将文本指南转化为三维靶区轮廓，不依赖标注数据训练。
- 食管癌案例中靶区分割Dice达0.842，计划靶区达0.880。
- 可零样本适配新指南和不同器官，医生更认可其合规性与实用性。
放疗中临床靶区（CTV）的勾画涉及复杂边界，受肿瘤位置和解剖结构限制。现有深度学习模型虽可自动化，但依赖专家标注数据，一旦临床指南更新即需昂贵重训。为此，我们提出OncoAgent——一种无需训练即可将文本指南转换为三维靶区轮廓的智能代理框架。在食管癌病例评估中，该框架实现零样本下CTV的Dice系数为0.842，计划靶区为0.880，性能接近全监督nnU-Net基线。盲法临床评估显示，医生更偏好OncoAgent，认为其在指南遵循度、修改工作量和临床可接受性上更优。此外，该框架可零样本推广至其他食管癌指南及前列腺等部位，无需重训。该代理范式不仅实现高精度分割，更提供对指南快速响应的能力，为放疗规划中的可解释性提供可扩展、透明的路径。
原文摘要 · Abstract (English)
Delineating the clinical target volume (CTV) in radiotherapy involves complex margins constrained by tumor location and anatomical barriers. While deep learning models automate this process, their rigid reliance on expert-annotated data requires costly retraining whenever clinical guidelines update. To overcome this limitation, we introduce OncoAgent, a novel guideline-aware AI agent framework that seamlessly converts textual clinical guidelines into three-dimensional target contours in a training-free manner. Evaluated on esophageal cancer cases, the agent achieves a zero-shot Dice similarity coefficient of 0.842 for the CTV and 0.880 for the planning target volume, demonstrating performance highly comparable to a fully supervised nnU-Net baseline. Notably, in a blinded clinical evaluation, physicians strongly preferred OncoAgent over the supervised baseline, rating it higher in guideline compliance, modification effort, and clinical acceptability. Furthermore, the framework generalizes zero-shot to alternative esophageal guidelines and other anatomical sites (e.g., prostate) without any retraining. Beyond mere volumetric overlap, our agent-based paradigm offers near-instantaneous adaptability to alternative guidelines, providing a scalable and transparent pathway toward interpretability in radiotherapy treatment planning.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。