arXiv 2508.160852026-08-11cs.CV

面向精准肿瘤学的病理基础模型集成学习

Ensemble learning of pathology foundation models for precision oncology

Department of Radiation Oncology, Stanford University School of Medicine（放射肿瘤科，斯坦福大学医学院）；Department of Pathology, Stanford University School of Medicine（病理学系，斯坦福大学医学院）；Department of Medicine (Oncology), Stanford University School of Medicine（医学系（肿瘤学），斯坦福大学医学院）；Department of Neurosurgery, Stanford University School of Medicine（神经外科，斯坦福大学医学院）；Stanford Institute for Human-Centered Artificial Intelligence（斯坦福大学人本人工智能研究所）

Xiangde Luo, Xiyue Wang, Feyisope Eweje, Xiaoming Zhang, Juan Luis Gomez Marti, Sarah Cascarino, Sen Yang, Yuchen Li, Ryan Quinton, Jinxi Xiang, Yuanfeng Ji, Zh… 展开作者

Xiangde Luo, Xiyue Wang, Feyisope Eweje, Xiaoming Zhang, Juan Luis Gomez Marti, Sarah Cascarino, Sen Yang, Yuchen Li, Ryan Quinton, Jinxi Xiang, Yuanfeng Ji, Zhe Li, Yijiang Chen, Colin Bergstrom, Ted Kim, Francesca Maria Olguin, Kelley Yuan, Matthew Abikenari, Andrew Heider, Sierra Willens, Sanjeeth Rajaram, Robert West, Joel Neal, Adam Schoenfeld, Maximilian Diehn, Chad Vanderbilt, Ruijiang Li

备注：: In this version, we fixed some issues and updated some results

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

该研究针对现有病理基础模型性能不一致、泛化有限的问题，提出ELF集成学习框架，整合5个预训练病理基础模型，在5万余张WSIs上训练后，在多种肿瘤相关任务中性能优于单模型，为病理应用提供新方案。

摘要：

组织病理学对于癌症诊断和治疗方案选择至关重要，病理基础模型可从全切片图像（WSIs）中学习视觉表征。然而，现有基础模型在不同数据集上采用各异策略训练，导致性能不一致且泛化能力有限。本文提出ELF（基础模型集成学习，Ensemble Learning of Foundation models），将5个预训练病理基础模型整合为统一的切片级表征。ELF在涵盖20个解剖部位的53699张WSIs上训练，利用集成学习捕捉各模型间的互补信息；其切片级架构专为数据高效的下游评估设计，适用于数据有限的场景，如治疗反应预测。我们在多种癌症类型中，针对疾病分类、生物标志物检测及抗癌与免疫治疗反应预测任务评估ELF，结果显示，在所有测试任务中，ELF的性能优于所评估的各组成模型及切片级基础模型，为肿瘤学病理应用中集成学习的进一步评估提供支持。

英文摘要：

Histopathology is essential for cancer diagnosis and treatment selection, and pathology foundation models learn visual representations from whole-slide images (WSIs). However, existing foundation models are trained on disparate datasets using varying strategies, leading to inconsistent performance and limited generalizability. Here, we introduce ELF (Ensemble Learning of Foundation models), which integrates five pretrained pathology foundation models into unified slide-level representations. Trained on 53,699 WSIs spanning 20 anatomical sites, ELF leverages ensemble learning to capture complementary information across models. ELF's slide-level architecture is designed for data-efficient downstream evaluation, including settings with limited data such as therapeutic response prediction. We evaluate ELF for disease classification, biomarker detection, as well as anticancer and immunotherapy response prediction across multiple cancer types. ELF achieves higher performance than the evaluated constituent and slide-level foundation models across the tested tasks, supporting further evaluation of ensemble learning for pathology applications in oncology.

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。