发表机构
Helmholtz AI; Helmholtz Munich - German Research Center for Environmental Health; Technical University of Munich; University Hospital Heidelberg; Institute of AI for Health, Helmholtz Munich - German Research Center for Environmental Health; Ludwig-Maximilian-University Hospital; Ludwig-Maximilian-University; German Cancer Consortium（亥姆霍兹人工智能研究所; 亥姆霍兹慕尼黑中心——德国环境健康研究中心; 慕尼黑工业大学; 海德堡大学医院; 亥姆霍兹慕尼黑中心——德国环境健康研究中心健康人工智能研究所; 路德维希-马克西米利安大学医院; 路德维希-马克西米利安大学; 德国癌症研究联盟）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
MorphoOrgaAgent是一个基于基础模型的多智能体系统，通过自然语言实现零样本类器官分割、自动数据分析和报告生成，并引入MorphoOrgaVQA基准验证其有效性。
AI 中文摘要
类器官是三维组织模型，其形态为肿瘤发展、疾病进展和药物测试提供了重要见解。提取这些形态特征严重依赖手动分割，这既耗时又费力。此外，进行定量统计分析通常需要定制编码技能和数学背景，这对实验生物学家构成了主要障碍。为应对这些挑战，我们引入了MorphoOrgaAgent，一个多智能体框架，基于自然语言输入实现零样本类器官分割、自动化数据分析和报告生成。该框架主要由三个核心组件构成：一个TaskUnderstandingAgent，用于识别所请求的测量和可视化类型；一个混合分割模块，将源自Cellpose的几何提示与文本提示相结合，以引导SAM3进行零样本类器官实例分割；以及一个ReportAgent，用于计算定量指标并将其与生成的可视化一起汇编成结构化报告。我们进一步引入了MorphoOrgaVQA，一个旨在对类器官形态分析中的智能体系统进行定量评估的基准。实验结果表明，MorphoOrgaAgent能处理明确和描述性的用户请求，产生的测量结果与真实值高度吻合，并在无需手动编程的情况下生成完整的分析报告。完整源代码和MorphoOrgaVQA基准可在该https URL公开获取。
英文摘要
Organoids are three-dimensional tissue models whose morphology provides important insights into tumor development, disease progression, and drug testing. Extracting these morphological features relies heavily on manual segmentation, which is time-consuming and labor-intensive. Furthermore, performing quantitative statistical analysis typically requires custom coding skills and a mathematical background, presenting a major barrier for experimental biologists. To address these challenges, we introduce MorphoOrgaAgent, a multi-agent framework that achieves zero-shot organoid segmentation, automated data analysis, and report generation based on natural language input. The framework consists mainly of three core components: a TaskUnderstandingAgent that identifies requested measurements and visualization types; a hybrid segmentation module that combines Cellpose-derived geometric prompts with text prompts to guide SAM3 for zero-shot organoid instance segmentation; and a ReportAgent that computes quantitative metrics and compiles them alongside generated visualizations into a structured report. We further introduce MorphoOrgaVQA, a benchmark designed for quantitative evaluation of agent systems in organoid morphology analysis. Experimental results demonstrate that MorphoOrgaAgent handles both explicit and descriptive user requests, produces measurements closely matching ground truth, and generates complete analysis reports without requiring manual programming. The complete source code and MorphoOrgaVQA benchmark are publicly available at https://github.com/peng-lab/MorphoOrgaAgent.
CommentsAccepted at the 2nd Agentic AI for Medicine Workshop, MICCAI 2026. 15 pages, 3 figures, 2 tables
