RadAgent用工具逐步解析胸部CT，让AI诊断过程可查可验。
RadAgent: A tool-using AI agent for stepwise interpretation of chest computed tomography
- 构建工具增强的迭代推理流程，每步决策可追溯。
- 临床准确率提升5.8点（宏平均F1），对抗攻击下鲁棒性提升24.7点。
- 首次实现37.0%的忠实度，适合需要透明解释的放射科医生使用。
视觉语言模型（VLM）显著推进了复杂医学影像如计算机断层扫描（CT）的AI辅助解读与报告生成。然而，现有方法多将临床医生置于被动观察者地位，无法提供可检查、验证或修正的可解释推理路径。为此，我们提出RadAgent——一种使用工具的AI代理，通过分步可解释流程生成胸部CT报告。每个报告均附带完整的中间决策与工具交互追踪，使临床医生能审查发现的推导过程。实验显示，相较于其3D VLM基线模型CT-Chat，RadAgent在三个维度上均有提升：临床准确率在宏平均F1上提高5.8点（相对提升35.4%），微平均F1提高5.1点（相对提升18.6%）；对抗条件下鲁棒性提升24.7点（相对提升41.9%）。此外，RadAgent首次实现37.0%的忠实度，而原3D VLM模型完全缺失此能力。通过将胸部CT解读构造成显式的、工具增强的迭代推理路径，RadAgent推动了放射学中透明且可靠的AI发展。
原文摘要 · Abstract (English)
Vision-language models (VLM) have markedly advanced AI-driven interpretation and reporting of complex medical imaging, such as computed tomography (CT). Yet, existing methods largely relegate clinicians to passive observers of final outputs, offering no interpretable reasoning trace for them to inspect, validate, or refine. To address this, we introduce RadAgent, a tool-using AI agent that generates CT reports through a stepwise and interpretable process. Each resulting report is accompanied by a fully inspectable trace of intermediate decisions and tool interactions, allowing clinicians to examine how the reported findings are derived. In our experiments, we observe that RadAgent improves chest CT report generation over its 3D VLM counterpart, CT-Chat, across three dimensions. Clinical accuracy improves by 5.8 points (35.4% relative) in macro-F1 and 5.1 points (18.6% relative) in micro-F1. Robustness under adversarial conditions improves by 24.7 points (41.9% relative). Furthermore, RadAgent achieves 37.0% in faithfulness, a new capability entirely absent in its 3D VLM counterpart. By structuring the interpretation of chest CT as an explicit, tool-augmented and iterative reasoning trace, RadAgent brings us closer toward transparent and reliable AI for radiology.
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。