Stride-Net: 基于公平性的解耦表征学习用于胸部X光诊断
Stride-Net: Fairness-Aware Disentangled Representation Learning for Chest X-Ray Diagnosis
- Indian Institute of Technology Delhi（印度理工学院德里）
- MBZUAI
- Khalifa University（卡布斯大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
Stride-Net通过解耦和可学习掩码实现公平性，提升胸部X光诊断的公平性和准确性。
AI中文摘要：
深度神经网络在胸部X光分类中实现了强大的平均性能，但往往在特定人口亚组中表现不佳，引发了关于临床安全性和公平性的重大关切。现有的去偏方法经常在不同数据集上产生不一致的改进，或通过降低整体诊断效用来实现公平性，将公平性视为事后约束而非学习表征的属性。在本文中，我们提出Stride-Net（通过解耦和可学习掩码与嵌入对齐实现敏感属性鲁棒学习），这是一个具有公平性的框架，用于学习疾病判别但人口统计学不变的胸部X光分析表征。Stride-Net在片段级别运作，使用可学习的步长掩码选择与标签对齐的图像区域，同时通过对抗混淆损失抑制敏感属性信息。为了将表征锚定在临床语义并防止捷径学习，我们进一步通过组最优传输强制图像特征与基于BioBERT的疾病标签嵌入之间的语义对齐。我们在MIMIC-CXR和CheXpert基准上评估Stride-Net，涵盖种族和交叉种族-性别亚组。在包括ResNet和视觉Transformer在内的架构中，Stride-Net在保持或超越基线准确性的同时，一致提高了公平性指标，实现了比先前去偏方法更有利的准确性-公平性权衡。我们的代码可在https://github.com/Daraksh/Fairness_StrideNet上获得。
英文摘要：
Deep neural networks for chest X-ray classification achieve strong average performance, yet often underperform for specific demographic subgroups, raising critical concerns about clinical safety and equity. Existing debiasing methods frequently yield inconsistent improvements across datasets or attain fairness by degrading overall diagnostic utility, treating fairness as a post hoc constraint rather than a property of the learned representation. In this work, we propose Stride-Net (Sensitive Attribute Resilient Learning via Disentanglement and Learnable Masking with Embedding Alignment), a fairness-aware framework that learns disease-discriminative yet demographically invariant representations for chest X-ray analysis. Stride-Net operates at the patch level, using a learnable stride-based mask to select label-aligned image regions while suppressing sensitive attribute information through adversarial confusion loss. To anchor representations in clinical semantics and discourage shortcut learning, we further enforce semantic alignment between image features and BioBERT-based disease label embeddings via Group Optimal Transport. We evaluate Stride-Net on the MIMIC-CXR and CheXpert benchmarks across race and intersectional race-gender subgroups. Across architectures including ResNet and Vision Transformers, Stride-Net consistently improves fairness metrics while matching or exceeding baseline accuracy, achieving a more favorable accuracy-fairness trade-off than prior debiasing approaches. Our code is available at https://github.com/Daraksh/Fairness_StrideNet.
