基于物理模型的染色增强方法,提升跨中心病理模型泛化能力
Physics-Grounded Adversarial Stain Augmentation with Calibrated Coverage Guarantees
- 在Macenko染色参数空间中进行对抗性增强,预算由多中心统计与DKW不等式校准
- 在Camelyon17-WILDS上达到93.9%准确率,最差组准确率达84.9%,优于10种对比方法
- 适合关注跨医院病理图像泛化、需可解释增强的医学影像研究者
不同医院间的染色差异会降低病理模型在实际部署中的性能。现有增强方法在色彩空间中随意扰动,缺乏合理的预算约束和对未见中心的覆盖保证。本文提出校准对抗性染色增强(CASA),在Macenko染色参数空间中执行对抗性增强,并通过DKW不等式从多中心统计数据中校准预算。在Camelyon17-WILDS数据集上(5次随机种子测试),CASA实现93.9% ± 1.6%的切片级准确率,显著优于HED-strong(88.4% ± 7.3%)、RandStainNA(85.2% ± 6.7%)和ERM(63.9% ± 11.3%),且在所有10种对比方法中取得最高最差组准确率(84.9% ± 0.9%)。
原文摘要 · Abstract (English)
Stain variation across hospitals degrades histopathology models at deployment. Existing augmentation methods perturb color spaces with arbitrary hyperparameters, lacking both a principled budget and coverage guarantees for unseen centers. We propose \textbf{C}alibrated \textbf{A}dversarial \textbf{S}tain \textbf{A}ugmentation (\textbf{CASA}), which performs adversarial augmentation in the Macenko stain parameter space with a budget calibrated from multi-center statistics via the DKW inequality. On Camelyon17-WILDS (5 seeds), CASA achieves $93.9\% \pm 1.6\%$ slide-level accuracy -- outperforming HED-strong ($88.4\% \pm 7.3\%$), RandStainNA ($85.2\% \pm 6.7\%$), and ERM ($63.9\% \pm 11.3\%$) -- with the highest worst-group accuracy ($84.9\% \pm 0.9\%$) among all 10 compared methods.
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。