BagShift：测量切片选择如何改变全切片多实例学习所见的证据
BagShift: Measuring How Patch Selection Changes the Evidence Seen by Whole-Slide MIL
浏览论文内容
中文总结 AI 辅助
BagShift通过配对协议探究全切片MIL中切片选择变化对证据的影响，在PANDA、CAMELYON16等数据集上验证了选择方式对模型性能的显著影响，提出合并重复局部切片的优化方法。
中文摘要 AI 辅助
全切片多实例学习（MIL）仅观察其选择器所允许的切片。在部署过程中，即使切片数量不变，选择器也会因计算限制、组织掩码或区域工作流程而发生改变。我们提出BagShift，一种配对协议，它在保持相同样本的特征和预测器固定的同时，改变其选择器，从而将选择器的响应与样本混合分离开来。在相等的128切片预算下，对整个组织进行采样或集中在一个坐标周围，会暴露出明显不同的证据：在PANDA数据集上，两种视图分别将二次加权kappa降低1.57和17.96个点（QWK按×100比例报告）。在CAMELYON16数据集上，从模型开发中 withheld 的病变注释显示，局部视图仅在10.0%的微转移观察中保留肿瘤，而匹配的暴露并不能一致地恢复损失。相同的固定数量压力源在外部肺亚型任务上产生的响应要小得多，尽管相对覆盖范围的差异使得跨任务的严重性具有描述性。当有重复的局部观察可用时，在一次非线性MIL传递之前合并它们的切片，比平均区域预测将PANDA QWK提高7.87个点。切片数量指定的是计算量，而非观察到的证据；部署评估应同时报告选择器保留的内容以及重复观察的聚合方式。
英文摘要
Whole-slide multiple-instance learning (MIL) observes only the patches admitted by its selector. Deployment can alter this selector through compute limits, tissue masking, or regional workflows, even when the patch count is unchanged. We introduce BagShift, a paired protocol that changes the selector for the same case while holding its features and predictor fixed, thereby isolating selector response from case mix. With equal 128-patch budgets, sampling across the tissue or concentrating around one coordinate exposes markedly different evidence: on PANDA, the two views reduce quadratic weighted kappa by 1.57 and 17.96 points, respectively (QWK reported on the $\times100$ scale). On CAMELYON16, lesion annotations withheld from model development show that localized views retain tumor in only 10.0\% of micrometastatic observations, and matched exposure does not consistently recover the loss. The same fixed-count stressor produces a much smaller response on external lung subtyping, although differences in relative coverage make cross-task severity descriptive. When repeated localized observations are available, unioning their patches before one nonlinear MIL pass improves PANDA QWK by 7.87 points over averaging regional predictions. Patch count specifies computation, not observed evidence; deployment evaluations should report both what a selector preserves and how repeated observations are aggregated.
