mlsanityData to 14 Oct 2026

On the limits of cross-domain generalization in automated X-ray prediction

arXiv 2002.02497 ↗First posted 6 Feb 2020eess.IV cs.LG q-bio.QMcited by 62

Not on the map. Why?

Abstract (arXiv)

This large scale study focuses on quantifying what X-rays diagnostic prediction tasks generalize well across multiple different datasets. We present evidence that the issue of generalization is not due to a shift in the images but instead a shift in the labels. We study the cross-domain performance, agreement between models, and model representations. We find interesting discrepancies between performance and agreement where models which both achieve good performance disagree in their predictions as well as models which agree yet achieve poor performance. We also test for concept similarity by regularizing a network to group tasks across multiple datasets together and observe variation across the tasks. All code is made available online and data is publicly available: https://github.com/mlmed/torchxrayvision

Key facts. Cited by 62 papers in the map (data through 14 Oct 2026). First posted on arXiv 6 Feb 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 10; 2022: 15; 2023: 8; 2024: 10; 2025: 12; 2026: 7.

62 papers.

Sort:

By area:

  1. 2021TorchXRayVision: A library of chest X-ray datasets and modelscited by 131
  2. 2022Adapting Pretrained Vision-Language Foundational Models to Medical Imaging Domainscited by 86
  3. 2021Deep Learning for Chest X-ray Analysis: A Surveycited by 84
  4. 2025MedRAX: Medical Reasoning Agent for Chest X-raycited by 70
  5. 2023Evaluating General Purpose Vision Foundation Models for Medical Image Analysis: An Experimental Study of DINOv2 on Radiology Benchmarkscited by 33
  6. 2021An Empirical Framework for Domain Generalization in Clinical Settingscited by 32
  7. 2022Risk of Bias in Chest Radiography Deep Learning Foundation Modelscited by 27
  8. 2022CNN Filter DB: An Empirical Investigation of Trained Convolutional Filterscited by 20
  9. 2022Medical Image Captioning via Generative Pretrained Transformerscited by 20
  10. 2021GAN-based Data Augmentation for Chest X-ray Classificationcited by 18
  11. 2023When More is Less: Incorporating Additional Datasets Can Hurt Performance By Introducing Spurious Correlationscited by 18
  12. 2022Debiasing Deep Chest X-Ray Classifiers using Intra- and Post-processing Methodscited by 15
38 more
  1. 2021Effect of Pre-Training Scale on Intra- and Inter-Domain Full and Few-Shot Transfer Learning for Natural and Medical X-Ray Chest Imagescited by 11
  2. 2022Domain generalization in deep learning-based mass detection in mammography: A large-scale multi-center studycited by 10
  3. 2022Rethinking Generalization: The Impact of Annotation Style on Medical Image Segmentationcited by 10
  4. 2023End-to-End Supervised Multilabel Contrastive Learningcited by 8
  5. 2024Enhancing chest X-ray datasets with privacy-preserving large language models and multi-type annotations: a data-driven approach for improved classificationcited by 8
  6. 2024A Systematic Review of Generalization Research in Medical Image Classificationcited by 8
  7. 2022An Accurate and Explainable Deep Learning System Improves Interobserver Agreement in the Interpretation of Chest Radiographcited by 7
  8. 2025Improving Performance, Robustness, and Fairness of Radiographic AI Models with Finely-Controllable Synthetic Datacited by 7
  9. 2023K-Diag: Knowledge-enhanced Disease Diagnosis in Radiographic Imagingcited by 6
  10. 2023Preserving privacy in domain transfer of medical AI models comes at no performance costs: The integral role of differential privacycited by 6
  11. 2024Freeze the backbones: A Parameter-Efficient Contrastive Approach to Robust Medical Vision-Language Pre-trainingcited by 6
  12. 2022A Comprehensive Review of Trends, Applications and Challenges In Out-of-Distribution Detectioncited by 5
  13. 2024Decentralised, Collaborative, and Privacy-preserving Machine Learning for Multi-Hospital Datacited by 5
  14. 2023GAT: Guided Adversarial Training with Pareto-optimal Auxiliary Taskscited by 4
  15. 2024MemControl: Mitigating Memorization in Diffusion Models via Automated Parameter Selectioncited by 4
  16. 2025Adjustment for Confounding using Pre-Trained Representationscited by 4
  17. 2021Rethinking Annotation Granularity for Overcoming Shortcuts in Deep Learning-based Radiograph Diagnosis: A Multicenter Studycited by 3
  18. 2022Deep learning for understanding multilabel imbalanced Chest X-ray datasetscited by 3
  19. 2022On Evaluating Adversarial Robustness of Chest X-ray Classification: Pitfalls and Best Practicescited by 3
  20. 2021Gifsplanation via Latent Shift: A Simple Autoencoder Approach to Counterfactual Generation for Chest X-rayscited by 2
  21. 2022Saliency Guided Adversarial Training for Learning Generalizable Features with Applications to Medical Imaging Classification Systemcited by 2
  22. 2024CROCODILE: Causality aids RObustness via COntrastive DIsentangled LEarningcited by 2
  23. 2024Towards Predicting Temporal Changes in a Patient's Chest X-ray Images based on Electronic Health Recordscited by 2
  24. 2024Capacity Control is an Effective Memorization Mitigation Mechanism in Text-Conditional Diffusion Modelscited by 2
  25. 2025Beyond Conventional Transformers: The Medical X-ray Attention (MXA) Block for Improved Multi-Label Diagnosis Using Knowledge Distillationcited by 2
  26. 2025Who Gets Credit or Blame? Attributing Accountability in Modern AI Systemscited by 2
  27. 2021COVID-19 Pneumonia Severity Prediction using Hybrid Convolution-Attention Neural Architecturescited by 1
  28. 2021Impact of class imbalance on chest x-ray classifiers: towards better evaluation practices for discrimination and calibration performancecited by 1
  29. 2021Multi-Domain Balanced Sampling Improves Out-of-Distribution Generalization of Chest X-ray Pathology Prediction Modelscited by 1
  30. 2023Why does my medical AI look at pictures of birds? Exploring the efficacy of transfer learning across domain boundariescited by 1
  31. 2023Generalized Cross-domain Multi-label Few-shot Learning for Chest X-rayscited by 1
  32. 2024Faster ISNet for Background Bias Mitigation on Deep Neural Networkscited by 1
  33. 2025HyDA: Hypernetworks for Test Time Domain Adaptation in Medical Imaging Analysiscited by 1
  34. 2025MIMM-X: Disentangling Spurious Correlations for Medical Image Analysiscited by 1
  35. 2026Mask-HybridGNet: Graph-based segmentation with emergent anatomical correspondence from pixel-level supervisioncited by 1
  36. 2026Optimized Labeling Resource Allocation for Prediction-Assisted Inference via OPALcited by 1
  37. 2022Exploring How Anomalous Model Input and Output Alerts Affect Decision-Making in Healthcarecited by 0
  38. 2022Generalizability of Deep Adult Lung Segmentation Models to the Pediatric Population: A Retrospective Studycited by 0

50 most cited of 62 All 62 (JSON)