A Guideline-Aware AI Agent for Zero-Shot Target Volume Auto-Delineation

TL;DR

This paper presents OncoAgent, a guideline-aware AI system that automatically generates clinical target volumes in radiotherapy without retraining, demonstrating high accuracy, clinical preference, and adaptability across guidelines and anatomical sites.

Contribution

OncoAgent introduces a training-free, guideline-aware framework that converts textual clinical guidelines into target contours, enabling zero-shot adaptation and improved clinical usability.

Findings

Achieves a zero-shot Dice score of 0.842 for CTV in esophageal cancer

Physicians prefer OncoAgent over supervised methods in clinical evaluation

Generalizes to different guidelines and anatomical sites without retraining

Abstract

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.