通过图像旋转检测胸部X光片模型的过度自信错误
Uncovering Overconfident Failures in CXR Models via Augmentation-Sensitivity Risk Scoring
- 用临床合理的旋转增强检测模型敏感度，识别高风险病例
- 敏感度高的病例召回率低0.2~0.3，但模型仍自认可信
- 无需标注即可筛选需医生复核的病例，提升医疗AI公平性
深度学习模型在胸部放射影像（CXR）解读中表现优异，但公平性和可靠性问题依然存在。模型在不同患者群体中的准确率不均，导致聚合指标无法反映隐藏的失败。现有错误检测方法依赖置信度校准或分布外（OOD）检测，难以发现细微的分布内错误；而基于图像与表征一致性的方法在医学影像中尚未充分探索。本文提出一种增强敏感性风险评分（ASRS）框架，用于识别易出错的CXR病例。ASRS对图像施加临床上合理的旋转（±15°/±30°），并使用RAD-DINO编码器测量嵌入变化。敏感度得分将样本分为稳定性四分位，高度敏感案例虽具高AUROC和高置信度，但召回率却降低0.2至0.3。该方法提供无标签的可选预测与医生审查机制，提升医疗AI的公平性与安全性。
原文摘要 · Abstract (English)
Deep learning models achieve strong performance in chest radiograph (CXR) interpretation, yet fairness and reliability concerns persist. Models often show uneven accuracy across patient subgroups, leading to hidden failures not reflected in aggregate metrics. Existing error detection approaches -- based on confidence calibration or out-of-distribution (OOD) detection -- struggle with subtle within-distribution errors, while image- and representation-level consistency-based methods remain underexplored in medical imaging. We propose an augmentation-sensitivity risk scoring (ASRS) framework to identify error-prone CXR cases. ASRS applies clinically plausible rotations ($\pm 15^\circ$/$\pm 30^\circ$) and measures embedding shifts with the RAD-DINO encoder. Sensitivity scores stratify samples into stability quartiles, where highly sensitive cases show substantially lower recall ($-0.2$ to $-0.3$) despite high AUROC and confidence. ASRS provides a label-free means for selective prediction and clinician review, improving fairness and safety in medical AI.
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。