Understanding Dataset Bias in Medical Imaging: A Case Study on Chest X-rays

2025/07/10 by Ethan Dack, Dack, Ethan, Chengliang Dai +1 · 1 citation
Computer Science · Medicine · #AI in cancer detection #COVID-19 diagnosis using AI #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Radiomics and Machine Learning in Medical Imaging

paper · pdf · doi:10.48550/arxiv.2507.07722

openalex publication_date 2025/07/10 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Recent works have revisited the infamous task ``Name That Dataset'', demonstrating that non-medical datasets contain underlying biases and that the dataset origin task can be solved with high accuracy. In this work, we revisit the same task applied to popular open-source chest X-ray datasets. Medical images are naturally more difficult to release for open-source due to their sensitive nature, which has led to certain open-source datasets being extremely popular for research purposes. By performing the same task, we wish to explore whether dataset bias also exists in these datasets. To extend our work, we apply simple transformations to the datasets, repeat the same task, and perform an analysis to identify and explain any detected biases. Given the importance of AI applications in medical imaging, it's vital to establish whether modern methods are taking shortcuts or are focused on the relevant pathology. We implement a range of different network architectures on the datasets: NIH, CheXpert, MIMIC-CXR and PadChest. We hope this work will encourage more explainable research being performed in medical imaging and the creation of more open-source datasets in the medical domain. Our code can be found here: https://github.com/eedack01/x_ray_ds_bias.

Citations

• Understanding Bias in Large-Scale Visual Datasets
• A Decade's Battle on Dataset Bias: Are We There Yet?
• Demographic Bias of Expert-Level Vision-Language Foundation Models in Medical Imaging
• Debiasing Counterfactuals In the Presence of Spurious Correlations
• Unlearning Spurious Correlations in Chest X-ray Classification
• Delving into Masked Autoencoders for Multi-Label Thorax Disease Classification
• The Effects of Regularization and Data Augmentation are Class Dependent
• TorchXRayVision: A library of chest X-ray datasets and models
• A Survey on Bias in Visual Datasets
• Intriguing Properties of Vision Transformers
• A Structure-Aware Relation Network for Thoracic Diseases Detection and Segmentation
• Deep Learning Models May Spuriously Classify Covid-19 from X-ray Images Based on Confounders
• VinDr-CXR: An open dataset of chest X-rays with radiologist's annotations
• An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
• "Name that manufacturer". Relating image acquisition bias with task complexity when training deep learning models: experiments on head CT
• RandAugment: Practical automated data augmentation with a reduced search space
• CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features
• CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparison
• ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness
• mixup: Beyond Empirical Risk Minimization
• Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization
• Learning Deep Features for Discriminative Localization
• Deep Residual Learning for Image Recognition
• A Deeper Look at Dataset Bias
• Going Deeper with Convolutions
• ImageNet classification with deep convolutional neural networks

Cited by

• Limitations of Public Chest Radiography Datasets for Artificial Intelligence: Label Quality, Domain Shift, Bias and Evaluation Challenges

Related

• Limitations of Public Chest Radiography Datasets for Artificial Intelligence: Label Quality, Domain Shift, Bias and Evaluation Challenges
• CheXclusion: Fairness gaps in deep chest X-ray classifiers
• AI Alignment in Medical Imaging: Unveiling Hidden Biases Through Counterfactual Analysis
• Exploring large scale public medical image datasets
• Structured dataset documentation: a datasheet for CheXpert