arXiv 2508.072922026-09-23cs.AIcs.CLcs.CV

EndoCogniAgent: 闭环代理推理与自我一致性验证用于内窥镜诊断

EndoCogniAgent: Closed-Loop Agentic Reasoning with Self-Consistency Validation for Endoscopic Diagnosis

School of Biological Science and Medical Engineering, Southeast University（东南大学生物科学与医学工程学院）；Jiangsu Key Laboratory of Biomaterials and Devices, Southeast University（江苏省生物材料与器件重点实验室）；State Key Laboratory of Digital Medical Engineering, Southeast University（国家数字医学工程重点实验室）；The First Affiliated Hospital of Nanjing Medical University（南京医科大学第一附属医院）；Department of Computer Science and Engineering, The Chinese University of Hong Kong（香港中文大学计算机科学与工程系）；Jiangsu Provincial Joint International Research Laboratory of Medical Information Processing（江苏省联合国际医学信息处理联合实验室）；Laboratory of Image Science and Technology, the School of Computer Science and Engineering, Southeast University（图像科学与技术实验室，东南大学计算机科学与工程学院）

Yi Tang, Kai-Ni Wang, Liang-Peng Pu, Hui Tang, Xiaopu He, Guang-Quan Zhou

备注：: 21 pages, 24 figures, 9 tables. Revised version: adds a blinded clinician evaluation, paired statistical significance testing, and extended ablation and generalization analyses. Code and data are available at https://github.com/Tyyds-ai/EndoCogniAgent

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

该研究提出EndoCogniAgent框架，通过闭环代理推理和自我一致性验证提升内窥镜诊断的准确性与可靠性，其核心方法是将诊断过程建模为受控状态更新过程，并引入EndoAgentBench基准进行评估。

摘要：

内窥镜诊断是一个迭代过程，临床医生逐步获取、比较和验证局部视觉证据以得出结论。当前AI系统未能充分支持此过程，因为细粒度证据获取和多步推理仍弱相关，导致两种失败模式：幻觉证据和未纠正的误差累积，影响诊断可靠性。我们提出EndoCogniAgent，一种闭环代理框架，将内窥镜诊断建模为受控状态更新过程。在每次推理轮次中，中央计划器选择下一步证据获取动作，专用专家工具提取相应观察，自我一致性验证机制沿两个维度检查观察：知识一致性与输入图像以及时间一致性与先前验证的发现，然后更新诊断状态。验证的观察被纳入演进状态以指导后续计划，而缺乏充分支持的发现则保留并带有纠正反馈，引导计划器进行进一步验证。我们进一步引入EndoAgentBench，一个以工作流程为导向的基准，包含来自11个内窥镜数据集的6132个问题-答案对，旨在评估诊断代理在全面诊断链中的表现，从细粒度视觉感知到高水平诊断推理。实验显示，EndoCogniAgent在感知任务上达到85.23%的平均准确率，在推理任务上达到71.13%的临床接受率，消融分析确认自我一致性验证和事件状态维护对这些提升至关重要。

英文摘要：

Endoscopic diagnosis is an iterative process in which clinicians acquire, compare, and verify local visual evidence before reaching a conclusion. Current AI systems do not adequately support this process because fine-grained evidence acquisition and multi-step reasoning remain weakly coupled, complicating reconciliation of image-derived findings with their textual interpretations. This gives rise to two failure modes, hallucinated evidence and uncorrected error accumulation, that undermine diagnostic reliability. We propose EndoCogniAgent, a closed-loop agentic framework that formulates endoscopic diagnosis as a controlled state update process for integrating complementary visual and textual evidence. At each reasoning round, a central planner selects an evidence acquisition action, specialized expert tools extract spatial and semantic observations as structured textual evidence, and a self-consistency validation mechanism examines this evidence along two dimensions, knowledge consistency against the input image and temporal consistency with prior validated findings, before updating the diagnostic state. Validated observations are admitted into the evolving state to condition subsequent planning, while insufficiently supported or conflicting findings are retained with corrective feedback that redirects the planner toward additional verification. We further introduce EndoAgentBench, a workflow-oriented benchmark comprising 6,132 question-answer pairs from 11 endoscopic datasets, to evaluate diagnostic agents across a comprehensive diagnostic chain, from fine-grained visual perception to high-level diagnostic reasoning. EndoCogniAgent achieves 85.23% overall accuracy on perception tasks and 71.13% clinical acceptance rate on reasoning tasks. Blinded clinician evaluation further shows consistent improvements in diagnostic response quality over the evaluated baselines.

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。