TRUST：用于乳腺癌筛查中可验证弃权（不执行）的阈值重新校准不确定性安全训练
TRUST: Threshold-Recalibrated Uncertainty-Safe Training for Certified Dismissal in Breast Cancer Screening
浏览论文内容
中文总结 AI 辅助
本研究提出TRUST闭环阈值感知训练策略，在NLBS、RSNA等数据集上验证其可在98%和95%召回率下提升乳腺癌筛查的病例级弃权率，减少放射科医生工作量且不影响癌症检测。
中文摘要 AI 辅助
减少对明确为癌症阴性的乳腺钼靶筛查结果的审核，可降低放射科医生的工作量且不影响癌症检测。我们提出一种闭环阈值感知训练策略，在训练期间重新计算弃权阈值，并用该阈值惩罚接近弃权区域的癌症阳性图像。我们在NLBS和RSNA数据集上采用五种受控训练配置评估该方法，基于单侧99% Clopper-Pearson界限对弃权病例中的癌症患病率进行病例级评估。所提模型在98%和95%召回率目标下均达到最高病例级弃权率：在NLBS数据集上，弃权率分别达19.74%和21.70%，而交叉熵基准模型未达到任一召回率目标；在RSNA数据集上，弃权率从7.04%提升至14.31%、从13.49%提升至19.69%；在RSNA→NLBS外部评估中，所提模型在98%和95%召回率目标下的弃权率分别为12.95%和19.87%。这些结果支持闭环阈值感知训练用于高召回率选择性弃权（不执行）。
英文摘要
Reducing the review of clearly cancer-negative screening mammograms could lower radiologist workload without compromising cancer detection. We propose a closed-loop threshold-aware training strategy in which the dismissal threshold is recalculated during training and used to penalize cancer-positive images that approach the dismissal region. We evaluated the method on NLBS and RSNA using five controlled training configurations, with case-level assessment based on a one-sided 99\% Clopper--Pearson upper bound for cancer prevalence among dismissed cases. The proposed model achieved the highest case-level dismissal rates at both 98\% and 95\% recall targets. On NLBS, dismissal reached 19.74\% and 21.70\%, while the cross-entropy baseline did not meet either recall target. On RSNA, dismissal improved from 7.04\% to 14.31\% and from 13.49\% to 19.69\%. In external RSNA$\to$NLBS evaluation, the proposed model achieved dismissal rates of 12.95\% and 19.87\% at the 98\% and 95\% recall targets, respectively. These results support closed-loop threshold-aware training for high-recall selective dismissal.
发表机构
- Memorial University of Newfoundland（纽芬兰纪念大学）
- Cancer Care, Newfoundland and Labrador Health Services（纽芬兰与拉布拉多卫生服务癌症中心）
机构由 AI 辅助整理，请以论文原文为准。
