CHILD：面向安全临床部署的基于人在回路的OOD检测
CHILD: Human-in-the-Loop OOD Detection for Safe Clinical Deployment
浏览论文内容
中文总结 AI 辅助
CHILD提出一种无需训练、基于稀疏人工反馈的流式OOD检测框架，通过自适应样本选择和检索式分数校准，在5%反馈预算下显著提升医疗AI部署的可靠性。
中文摘要 AI 辅助
分布外（OOD）检测对于医疗AI系统的安全部署至关重要。近年来，测试时自适应（TTA）已成为OOD检测的一种新范式，可在部署期间自动调整检测器行为。然而，这种自动自适应机制在安全关键的临床环境中可能引发安全隐患。虽然医生监督可以降低这些风险，但监督是资源密集型的，必须合理分配。为兼顾安全性与效率，我们提出了CHILD，一种无需训练、通过稀疏人工反馈增强流式OOD检测的框架。在严格的预算约束下，CHILD采用自适应风险感知样本选择机制，仅挑选最具决策不确定性的样本进行审查。关键在于，它通过基于检索的分数校准模块最大化稀疏反馈的效用，该模块利用紧凑的特征缓存精炼模型预测，无需任何参数更新。在四个医学基准上的大量实验表明，CHILD将有限的监督转化为显著的可靠性提升：在仅5%的稀疏反馈预算下，它将平均FPR95从72.63%降至60.26%，并将AUROC从75.53%提升至81.85%，持续优于最先进的基线方法。我们的代码已公开于该https URL。
英文摘要
Out-of-distribution (OOD) detection is critical for safe deployment of medical AI systems. Recently, test-time adaptation (TTA) has emerged as a new paradigm for OOD detection, automatically adjusting detector behavior during deployment. However, such automatic adaptation mechanisms may raise safety concerns in safety-critical clinical environments. While physician oversight can mitigate these risks, it is resource-intensive and must be judiciously allocated. To reconcile safety with efficiency, we propose CHILD, a training-free framework designed to enhance streaming OOD detection via sparse human feedback. Operating under strict budget constraints, CHILD employs an adaptive risk-aware sample selection mechanism to pinpoint only the most decision-uncertain samples for review. Crucially, it maximizes the utility of this sparse feedback through a retrieval-based score calibration module, which refines model predictions using a compact feature cache without any parameter updates. Extensive experiments on four medical benchmarks demonstrate that CHILD turns limited supervision into significant reliability gains: with a sparse feedback budget of only 5%, it reduces the average FPR95 from 72.63% to 60.26% and improves AUROC from 75.53% to 81.85%, consistently outperforming state-of-the-art baselines. Our code is publicly available at https://github.com/figec/CHILD.
发表机构
- Peng Cheng Laboratory（鹏城实验室）
- Hong Kong University of Science and Technology（香港科技大学）
机构由 AI 辅助整理，请以论文原文为准。
