arXiv 2509.126002025-09-16cs.LGcs.AIq-bio.QM

增强泛化能力和数据效率用于泛癌症预后预测的多模态基础模型

A Multimodal Foundation Model to Enhance Generalizability and Data Efficiency for Pan-cancer Prognosis Prediction

Department of Computer Science and Engineering（计算机科学与工程系）；Hong Kong University of Science and Technology（香港科学与技术大学）；Department of Pathology（病理学系）；School of Medicine（医学院）；Zhejiang University（浙江大学）；Nanfang Hospital and School of Basic Medical Sciences（南方医科大学基础医学系）；Southern Medical University（南方医学院）；Guangdong Provincial Key Laboratory of Molecular Tumor Pathology（广东省分子肿瘤病理重点实验室）；Jinfeng Laboratory（金凤实验室）；Department of Radiology（放射科）；Division of Life Science（生命科学系）；HKUST Shenzhen-Hong Kong Collaborative Innovation Research Institute（香港科技大学深圳-香港协同创新研究院）；State Key Laboratory of Nervous System Disorders（神经系统疾病国家重点实验室）

Huajun Zhou, Fengtao Zhou, Jiabo Ma, Yingxue Xu, Xi Wang, Xiuming Zhang, Li Liang, Zhenhui Li, Hao Chen

备注：: 27 pages, 7 figures

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

提出多模态基础模型MICE，通过协作专家整合病理、临床和基因数据进行泛癌症预后预测，结合对比与监督学习提升泛化性和数据效率，在多队列中显著超越现有模型。

摘要：

多模态数据为全面理解肿瘤微环境提供了异构信息。然而，现有的AI模型往往难以利用多模态数据中的丰富信息，且提取的表示泛化能力较差。在此我们提出MICE（Multimodal data Integration via Collaborative Experts，基于协作专家的多模态数据集成），这是一个多模态基础模型，能有效整合病理图像、临床报告和基因组数据，以进行精确的泛癌症预后预测。MICE没有使用传统的多专家模块，而是采用多个功能多样的专家来全面捕获跨癌症和癌症特异性的见解。利用来自30种癌症类型11,799名患者的数据，我们通过结合对比学习和监督学习增强了MICE的泛化能力。MICE的表现优于单模态和基于多专家的最先进多模态模型，在内部队列中C-index提升了3.8%至11.2%，在独立队列中提升了5.8%至8.8%。此外，它在各种临床场景中展现出卓越的数据效率。凭借其增强的泛化能力和数据效率，MICE为泛癌症预后预测建立了一个有效且可扩展的基础，在个性化定制治疗和改善治疗结果方面具有巨大潜力。

英文摘要：

Multimodal data provides heterogeneous information for a holistic understanding of the tumor microenvironment. However, existing AI models often struggle to harness the rich information within multimodal data and extract poorly generalizable representations. Here we present MICE (Multimodal data Integration via Collaborative Experts), a multimodal foundation model that effectively integrates pathology images, clinical reports, and genomics data for precise pan-cancer prognosis prediction. Instead of conventional multi-expert modules, MICE employs multiple functionally diverse experts to comprehensively capture both cross-cancer and cancer-specific insights. Leveraging data from 11,799 patients across 30 cancer types, we enhanced MICE's generalizability by coupling contrastive and supervised learning. MICE outperformed both unimodal and state-of-the-art multi-expert-based multimodal models, demonstrating substantial improvements in C-index ranging from 3.8% to 11.2% on internal cohorts and 5.8% to 8.8% on independent cohorts, respectively. Moreover, it exhibited remarkable data efficiency across diverse clinical scenarios. With its enhanced generalizability and data efficiency, MICE establishes an effective and scalable foundation for pan-cancer prognosis prediction, holding strong potential to personalize tailored therapies and improve treatment outcomes.

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。