用反事实分析揭露医学影像模型隐藏偏见，提升诊断公平性。
AI Alignment in Medical Imaging: Unveiling Hidden Biases Through Counterfactual Analysis
- 结合条件隐变量扩散模型与假设检验，无须真实反事实数据检测偏见。
- 在cheXpert和MIMIC-CXR数据集上验证，偏差识别准确率显著优于基线。
- 适合关注AI医疗公平性与可解释性的研究者与临床开发者。
医学影像机器学习系统虽具出色诊断能力，但易受偏见影响，危及泛化性能。本文提出一种新型统计框架，评估模型对性别、年龄等敏感属性的依赖性。方法基于反事实不变性，衡量模型预测在假设敏感属性变化时是否保持稳定。我们设计了一种实用算法，融合条件隐变量扩散模型与统计假设检验，无需直接获取反事实数据即可识别并量化偏见。在合成数据集及大规模真实医学影像数据集（包括 extsc{cheXpert}和MIMIC-CXR）上的实验表明，该方法与反事实公平性原则高度一致，性能优于标准基线。本工作为确保医疗AI系统跨人群泛化提供了可靠工具，是迈向医疗AI安全的关键一步。代码已开源。
原文摘要 · Abstract (English)
Machine learning (ML) systems for medical imaging have demonstrated remarkable diagnostic capabilities, but their susceptibility to biases poses significant risks, since biases may negatively impact generalization performance. In this paper, we introduce a novel statistical framework to evaluate the dependency of medical imaging ML models on sensitive attributes, such as demographics. Our method leverages the concept of counterfactual invariance, measuring the extent to which a model's predictions remain unchanged under hypothetical changes to sensitive attributes. We present a practical algorithm that combines conditional latent diffusion models with statistical hypothesis testing to identify and quantify such biases without requiring direct access to counterfactual data. Through experiments on synthetic datasets and large-scale real-world medical imaging datasets, including \textsc{cheXpert} and MIMIC-CXR, we demonstrate that our approach aligns closely with counterfactual fairness principles and outperforms standard baselines. This work provides a robust tool to ensure that ML diagnostic systems generalize well, e.g., across demographic groups, offering a critical step towards AI safety in healthcare. Code: https://github.com/Neferpitou3871/AI-Alignment-Medical-Imaging.
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。