解决病理模型在不同医院间的偏差问题，提升跨机构泛化能力。
Hospital-Specific Bias in Patch-Based Pathology Models
- 用轻量对抗适配器从特征中剥离医院特有信息。
- 保持疾病分类准确率的同时显著降低医院偏差。
- 适合关注临床模型泛化的研究人员使用。
病理学基础模型（PFMs）在多种组织病理学任务中表现优异，但其对医院特异性领域偏移的敏感性仍缺乏系统研究。本研究在TCGA的切片级数据集上系统评估了最先进的PFMs，提出一种轻量级对抗适配器，用于从潜在表示中消除医院相关域信息。实验表明，尽管疾病分类准确率基本保持不变，该适配器能有效降低医院特异性偏差，t-SNE可视化结果进一步验证了这一点。本研究建立了评估PFMs跨医院鲁棒性的基准，并提供了在异质临床环境下提升泛化能力的实际策略。代码已公开于https://github.com/MengRes/pfm_domain_bias。
原文摘要 · Abstract (English)
Pathology foundation models (PFMs) achieve strong performance on diverse histopathology tasks, but their sensitivity to hospital-specific domain shifts remains underexplored. We systematically evaluate state-of-the-art PFMs on TCGA patch-level datasets and introduce a lightweight adversarial adaptor to remove hospital-related domain information from latent representations. Experiments show that, while disease classification accuracy is largely maintained, the adaptor effectively reduces hospital-specific bias, as confirmed by t-SNE visualizations. Our study establishes a benchmark for assessing cross-hospital robustness in PFMs and provides a practical strategy for enhancing generalization under heterogeneous clinical settings. Our code is available at https://github.com/MengRes/pfm_domain_bias.
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。