CHILD: Human-in-the-Loop OOD Detection for Safe Clinical Deployment

2026-09-07

AI Summary

为解决医疗AI系统中OOD检测的安全性问题，提出CHILD框架，通过稀疏的人类反馈和自适应风险感知样本选择机制，在有限监督下提高模型可靠性。

Abstract

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.

Problem

• out-of-distribution detection
• test-time adaptation
• clinical safety
• human-in-the-loop
• resource allocation

Innovation

• Human-in-the-Loop
• OOD Detection
• Adaptive Risk-aware Sample Selection
• Sparse Human Feedback
• Retrieval-based Score Calibration