智能体能否在零样本设置中区分视觉上难以分离的疾病？一项初步研究
Can Agents Distinguish Visually Hard-to-Separate Diseases in a Zero-Shot Setting? A Pilot Study
AI总结：
本研究探索多模态大语言模型智能体在零样本下区分视觉混淆疾病（如黑色素瘤与不典型痣、肺水肿与肺炎）的能力，提出基于对比裁决的多智能体框架，在皮肤镜数据上准确率提升11个百分点，但总体性能仍不足临床部署。
摘要：
多模态大语言模型（MLLMs）的快速进展引发了对基于智能体系统的日益关注。尽管大多数医学影像先前工作集中于自动化常规临床工作流程，我们研究了一个未被充分探索但临床意义重大的场景：在零样本设置中区分视觉上难以分离的疾病。我们在两个仅基于影像的代理诊断任务上对代表性智能体进行基准测试：（1）黑色素瘤与不典型痣，以及（2）肺水肿与肺炎，尽管临床管理存在显著差异，但视觉特征高度混淆。我们引入了一种基于对比裁决的多智能体框架。实验结果显示诊断性能提升（在皮肤镜数据上准确率提高11个百分点），并在定性样本上减少了无根据的声明，尽管整体性能仍不足以用于临床部署。我们承认人类注释中固有的不确定性以及临床背景的缺失，这进一步限制了向真实世界场景的转化。在此受控设置中，这项初步研究为视觉混淆场景下的零样本智能体性能提供了初步见解。
英文摘要：
The rapid progress of multimodal large language models (MLLMs) has led to increasing interest in agent-based systems. While most prior work in medical imaging concentrates on automating routine clinical workflows, we study an underexplored yet clinically significant setting: distinguishing visually hard-to-separate diseases in a zero-shot setting. We benchmark representative agents on two imaging-only proxy diagnostic tasks, (1) melanoma vs. atypical nevus and (2) pulmonary edema vs. pneumonia, where visual features are highly confounded despite substantial differences in clinical management. We introduce a multi-agent framework based on contrastive adjudication. Experimental results show improved diagnostic performance (an 11-percentage-point gain in accuracy on dermoscopy data) and reduced unsupported claims on qualitative samples, although overall performance remains insufficient for clinical deployment. We acknowledge the inherent uncertainty in human annotations and the absence of clinical context, which further limit the translation to real-world settings. Within this controlled setting, this pilot study provides preliminary insights into zero-shot agent performance in visually confounded scenarios.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
