通过 tile 分数分布匹配实现数字病理中的稳健灵敏度控制
Robust sensitivity control in digital pathology via tile score distribution matching
AI总结：
针对跨中心数字病理模型需满足指定灵敏度的问题，提出基于最优传输与MIL的tile分数分布匹配方法，仅用少量校准样本即可稳健控制WSI分类灵敏度。
摘要：
由于分布偏移，跨医疗中心部署数字病理模型颇具挑战。域泛化的最新进展以受试者工作特征曲线下面积（AUC）衡量的聚合性能提升了模型可迁移性。然而，临床监管通常要求控制其他指标的可迁移性，例如规定的灵敏度水平。我们提出一种控制全切片图像（WSI）分类模型灵敏度的新方法，该方法基于最优传输和多示例学习（MIL）。通过在多个队列和任务上验证，我们的方法仅需少量校准样本即可实现稳健的灵敏度控制，为计算病理系统的可靠部署提供了实用解决方案。
英文摘要：
Deploying digital pathology models across medical centers is challenging due to distribution shifts. Recent advances in domain generalization improve model transferability in terms of aggregated performance measured by the Area Under Curve (AUC). However, clinical regulations often require to control the transferability of other metrics, such as prescribed sensitivity levels. We introduce a novel approach to control the sensitivity of whole slide image (WSI) classification models, based on optimal transport and Multiple Instance Learning (MIL). Validated across multiple cohorts and tasks, our method enables robust sensitivity control with only a handful of calibration samples, providing a practical solution for reliable deployment of computational pathology systems.
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。
