arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2507.03460cs.AI
收藏

心血管影像表型分析的多智能体推理

Multi-Agent Reasoning for Cardiovascular Imaging Phenotype Analysis

Department of Computing, Imperial College London, London, UK(帝国理工学院计算机系);Department of Mechanical Engineering, University College London, London, UK(伦敦大学学院机械工程系);Department of Brain Sciences, Imperial College London, London, UK(帝国理工学院脑科学系);Data Science Institute, Imperial College London, London, UK(帝国理工学院数据科学研究所);University of Tokyo, Tokyo, JP(东京大学);National Heart and Lung Institute, Imperial College London, London, UK(帝国理工学院国家心脏和肺研究所);FAU Erlangen-Nürnberg, Erlangen, DE(埃朗根-纽伦堡大学);UK Dementia Research Institute, Imperial College London, London, UK(英国痴呆研究所在伦敦帝国理工学院);Rosalind Franklin Institute, Harwell Science and Innovation Campus, Didcot, UK(罗莎琳德·弗兰克林研究所)

Weitong Zhang, Mengyun Qiao, Chengqi Zang, Steven Niederer, Paul M Matthews, Wenjia Bai, Bernhard Kainz

AI总结:

提出MESHAgents框架,利用多智能体大语言模型自动发现心血管影像表型与风险因素的关联,性能媲美专家选择,并提升多数疾病召回率。

摘要:

识别影像表型、疾病风险因素与临床结局之间的关联对于理解疾病机制至关重要。然而,传统方法依赖于人工驱动的假设检验和关联因素选择,往往忽视了影像表型与其他多模态数据之间复杂的非线性依赖关系。为解决这一问题,我们引入了心脏多智能体探索协同框架(MESHAgents):该框架利用大语言模型作为智能体,在关联研究中动态地引出、呈现并决定混杂因素和表型。具体而言,我们编排了一个多学科AI智能体团队,通过迭代、自组织的推理过程自发地生成并汇聚见解。该框架将统计相关性与多专家共识动态结合,为表型组关联研究(PheWAS)提供了自动化流程。我们通过一项基于人群的心脏和主动脉影像表型研究展示了该系统的能力。MESHAgents自主发现了影像表型与多种非影像因素之间的相关性,识别出超出标准人口统计学因素的额外混杂变量。在诊断任务上的验证表明,MESHAgents发现的表型在疾病分类任务中达到了与专家选择的表型相当的性能,平均AUC差异小至$-0.004_{\pm0.010}$。值得注意的是,在9种疾病类型中,有6种的召回率得分有所提高。我们的框架提供了具有临床相关性的影像表型,并具备透明的推理过程,为专家驱动的方法提供了一种可扩展的替代方案。

英文摘要:

Identifying associations between imaging phenotypes, disease risk factors, and clinical outcomes is essential for understanding disease mechanisms. However, traditional approaches rely on human-driven hypothesis testing and selection of association factors, often overlooking complex, non-linear dependencies among imaging phenotypes and other multi-modal data. To address this, we introduce Multi-agent Exploratory Synergy for the Heart (MESHAgents): a framework that leverages large language models as agents to dynamically elicit, surface, and decide confounders and phenotypes in association studies. Specifically, we orchestrate a multi-disciplinary team of AI agents, which spontaneously generate and converge on insights through iterative, self-organizing reasoning. The framework dynamically synthesizes statistical correlations with multi-expert consensus, providing an automated pipeline for phenome-wide association studies (PheWAS). We demonstrate the system's capabilities through a population-based study of imaging phenotypes of the heart and aorta. MESHAgents autonomously uncovered correlations between imaging phenotypes and a wide range of non-imaging factors, identifying additional confounder variables beyond standard demographic factors. Validation on diagnosis tasks reveals that MESHAgents-discovered phenotypes achieve performance comparable to expert-selected phenotypes, with mean AUC differences as small as $-0.004_{\pm0.010}$ on disease classification tasks. Notably, the recall score improves for 6 out of 9 disease types. Our framework provides clinically relevant imaging phenotypes with transparent reasoning, offering a scalable alternative to expert-driven methods.

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。

↑