深度学习模型会利用性别和种族等隐性特征进行阿尔茨海默病诊断，导致不公平结果。
Invisible Attributes, Visible Biases: Exploring Demographic Shortcuts in MRI-based Alzheimer's Disease Classification
- 通过3D脑MRI分析模型能否识别性别与种族，验证分布偏移存在。
- 训练集种族/性别不均衡时，模型对少数群体性能显著下降。
- 发现大脑不同区域的特征贡献差异，揭示了偏见来源。
磁共振成像（MRI）是脑部影像的金标准。深度学习（DL）算法被用于从MRI扫描中辅助诊断阿尔茨海默病（AD）。然而，深度学习模型可能产生捷径学习现象，即依赖与标签无关的虚假特征进行预测。当这些特征与受保护属性（如种族、性别）相关时，可能导致对代表性不足群体的性能偏差。本文探索基于MRI的深度学习阿尔茨海默病诊断中是否存在捷径学习与人口统计学偏差。首先，我们检验深度学习模型是否能从3D脑部MRI中识别出性别或种族，以确认是否存在基于种族和性别的分布偏移。其次，考察训练数据中种族或性别不平衡是否导致模型性能下降，表明捷径学习与偏差。最后，对不同脑区在受保护属性和AD分类任务中的特征重要性进行定量与定性分析。通过多个数据集和模型（ResNet与SwinTransformer），我们证实了基于种族和性别的捷径学习与偏差在深度学习驱动的阿尔茨海默病分类中确实存在。本工作为构建更公平的脑部MRI深度学习诊断工具奠定基础。代码已公开于 https://github.com/acharaakshit/ShortMR。
原文摘要 · Abstract (English)
Magnetic resonance imaging (MRI) is the gold standard for brain imaging. Deep learning (DL) algorithms have been proposed to aid in the diagnosis of diseases such as Alzheimer's disease (AD) from MRI scans. However, DL algorithms can suffer from shortcut learning, in which spurious features, not directly related to the output label, are used for prediction. When these features are related to protected attributes, they can lead to performance bias against underrepresented protected groups, such as those defined by race and sex. In this work, we explore the potential for shortcut learning and demographic bias in DL based AD diagnosis from MRI. We first investigate if DL algorithms can identify race or sex from 3D brain MRI scans to establish the presence or otherwise of race and sex based distributional shifts. Next, we investigate whether training set imbalance by race or sex can cause a drop in model performance, indicating shortcut learning and bias. Finally, we conduct a quantitative and qualitative analysis of feature attributions in different brain regions for both the protected attribute and AD classification tasks. Through these experiments, and using multiple datasets and DL models (ResNet and SwinTransformer), we demonstrate the existence of both race and sex based shortcut learning and bias in DL based AD classification. Our work lays the foundation for fairer DL diagnostic tools in brain MRI. The code is provided at https://github.com/acharaakshit/ShortMR
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。