基于片段的病理模型中的医院特异性偏差
Hospital-Specific Bias in Patch-Based Pathology Models
AI总结:
本文提出了一种轻量级对抗适配器,用于减少基于片段的病理模型中的医院特异性偏差,并通过实验验证了其有效性。
摘要:
病理基础模型(PFMs)在多种组织病理学任务上实现了强大的性能,但其对医院特异性域偏移的敏感性仍缺乏深入研究。我们系统地评估了最先进的PFMs在TCGA片段级数据集上的表现,并引入了一个轻量级对抗适配器,用于从潜在表示中去除与医院相关的信息。实验表明,尽管疾病分类准确率基本保持不变,但适配器有效减少了医院特异性偏差,这通过t-SNE可视化得到了验证。我们的研究建立了评估PFMs跨医院鲁棒性的基准,并提供了一种在异质临床环境中增强泛化能力的实用策略。我们的代码可在https://github.com/MengRes/pfm_domain_bias获取。
英文摘要:
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.
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。