An Evidence-Driven Multi-Agent Compound AI System for Head and Neck Proton Radiotherapy Planning
作者: Qingqing Wang, Liqiang Xiao, Chang Chang
分类: cs.AI
发布日期: 2026-10-21
💡 一句话要点
提出基于多智能体复合AI系统的头颈部质子放疗计划优化方法
🎯 匹配领域: 支柱二:RL算法与架构 (RL & Architecture) 支柱九:具身大模型 (Embodied Foundation Models)
关键词: 放射治疗 质子治疗 深度强化学习 大语言模型 多智能体系统 个性化医疗 临床优化
📋 核心要点
- 现有的放射治疗计划方法在满足临床标准与医生偏好之间难以实现有效平衡,导致治疗效果不理想。
- 本研究提出了一种多智能体复合AI系统,结合深度强化学习与大语言模型,通过自然语言交互优化治疗计划。
- 在21名头颈部癌症患者的实验中,后训练的Qwen3-14B在指令遵循和领域推理能力上显著提升,优化效果明显。
📝 摘要(中文)
放射治疗计划需要在满足临床标准与医生偏好之间进行平衡。本研究开发了一种证据驱动的多智能体复合AI系统,结合基于深度强化学习的自动治疗计划与基于大语言模型的对话式计划优化,专注于质子PBS治疗。该系统通过PPO训练的策略网络生成多个计划,并通过自然语言交互进行进一步优化。实验结果表明,后训练的Qwen3-14B在指令遵循、信息检索和领域特定推理能力上均有显著提升,能够更有效地改善用户优先目标,同时限制竞争目标的恶化,提供个性化的治疗计划。
🔬 方法详解
问题定义:本研究旨在解决放射治疗计划中临床标准与医生偏好之间的平衡问题。现有方法往往无法有效整合这些竞争目标,导致治疗计划的临床适用性不足。
核心思路:论文提出的复合AI系统通过深度强化学习生成初步治疗计划,并利用大语言模型进行自然语言交互优化,旨在提高计划的个性化和临床适用性。
技术框架:系统主要包括三个模块:规划代理(生成和推荐计划)、聊天机器人(提供对话接口)、评估代理(检索临床指标和识别约束违规)。初步计划通过PPO训练的策略网络生成,后续优化通过LLM进行。
关键创新:最重要的创新在于将深度强化学习与大语言模型结合,形成一个多智能体系统,能够在复杂情况下进行有效的计划优化,显著提升了计划的个性化和临床适用性。
关键设计:规划代理基于Qwen3-14B模型,经过任务特定数据的后训练,采用SFT和GRPO方法,增强了其推理能力和对证据的支持,优化过程中考虑了用户优先目标与竞争目标的平衡。
🖼️ 关键图片
📊 实验亮点
实验结果显示,后训练的Qwen3-14B在指令遵循、信息检索和领域特定推理能力上均有显著提升,优化后的治疗计划在用户优先目标的改善上表现出更高的有效性,同时限制了竞争目标的恶化,提供了更为合理的临床权衡。
🎯 应用场景
该研究的复合AI系统可广泛应用于放射治疗领域,尤其是在个性化治疗计划的制定中。通过提高治疗计划的质量和适用性,未来可能显著改善患者的治疗效果和生活质量,推动放射治疗的智能化发展。
📄 摘要(原文)
Radiation treatment planning requires balancing competing objectives to satisfy clinical criteria while accommodating physicians' preferences. This study aims to develop an evidence-driven, multi-agent compound AI system that integrates DRL-based automated treatment planning with LLM-based conversational plan refinement for proton PBS therapy. A policy network trained using PPO first generates multiple plans without human intervention, from which one is selected as the target plan and the others serve as references for subsequent refinements. For challenging cases requiring further adjustments, an LLM-based multi-agent system enables plan refinement through natural language interactions. The system comprises a planning agent that recommends evidence-supported adjustments, a chatbot providing a unified conversational interface, and an evaluation agent that retrieves clinical metrics and identifies constraint violations. To enhance domain-specific reasoning, the planning agent based on Qwen3-14B is designed to justify its recommendations using evidence from previously generated plans and post-trained on task-specific data using SFT and GRPO. The framework was trained and evaluated using 21 patients with H&N cancers, with 5 PPO-generated plans per patient. Of these, 50 plans were selected for instruction-guided refinement. Compared with the base LLM, the post-trained Qwen3-14B demonstrated improved instruction-following, information retrieval and domain-specific reasoning capabilities. The resulting adjustments more effectively improved user-prioritized objectives while limiting deterioration in competing objectives, yielding more clinically appropriate trade-offs in patient-specific plan refinement. The proposed compound AI system provides a user-friendly planning platform, offering a promising approach to personalized proton PBS treatment planning.