用医学知识图谱增强病理图像理解，提升癌症诊断精度。
Knowledge-enhanced Pretraining for Vision-language Pathology Foundation Model on Cancer Diagnosis
- 构建包含1.1万种疾病的知识图谱，重排百万级图文对为14.3万组语义结构
- 在18个公开数据集和4个罕见癌种数据集上显著超越现有模型
- 特别擅长识别罕见癌症亚型，适合临床辅助诊断场景
视觉-语言基础模型在计算病理学中展现出巨大潜力，但主要依赖数据驱动，缺乏显式医学知识整合。我们提出KEEP（KnowledgE-Enhanced Pathology），一个系统性将疾病知识融入预训练过程的癌症诊断基础模型。KEEP利用涵盖11,454种疾病和139,143个属性的综合疾病知识图谱，将数百万张病理图像-文本对重新组织为143,000个与疾病本体层级一致的语义结构组。这种知识增强的预训练在层次化语义空间中对齐视觉与文本表征，促进对疾病关系和形态模式的深层理解。在18个公共基准（超14,000张全切片图像）和4个机构罕见癌种数据集（926例）上，KEEP持续优于现有基础模型，在罕见亚型上表现尤为突出。这些结果确立了知识增强型视觉-语言建模作为推动计算病理学发展的强大范式。
原文摘要 · Abstract (English)
Vision-language foundation models have shown great promise in computational pathology but remain primarily data-driven, lacking explicit integration of medical knowledge. We introduce KEEP (KnowledgE-Enhanced Pathology), a foundation model that systematically incorporates disease knowledge into pretraining for cancer diagnosis. KEEP leverages a comprehensive disease knowledge graph encompassing 11,454 diseases and 139,143 attributes to reorganize millions of pathology image-text pairs into 143,000 semantically structured groups aligned with disease ontology hierarchies. This knowledge-enhanced pretraining aligns visual and textual representations within hierarchical semantic spaces, enabling deeper understanding of disease relationships and morphological patterns. Across 18 public benchmarks (over 14,000 whole-slide images) and 4 institutional rare cancer datasets (926 cases), KEEP consistently outperformed existing foundation models, showing substantial gains for rare subtypes. These results establish knowledge-enhanced vision-language modeling as a powerful paradigm for advancing computational pathology.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。