mlsanityData to 7 Oct 2026

Fair Foundation Models for Medical Image Analysis: Challenges and Perspectives

arXiv 2502.16841 ↗First posted 24 Feb 2025cs.CV cs.AI cs.LGcited by 3

Not on the map. Why?

Abstract (arXiv)

Ensuring equitable Artificial Intelligence (AI) in healthcare demands systems that make unbiased decisions across all demographic groups, bridging technical innovation with ethical principles. Foundation Models (FMs), trained on vast datasets through self-supervised learning, enable efficient adaptation across medical imaging tasks while reducing dependency on labeled data. These models demonstrate potential for enhancing fairness, though significant challenges remain in achieving consistent performance across demographic groups. Our review indicates that effective bias mitigation in FMs requires systematic interventions throughout all stages of development. While previous approaches focused primarily on model-level bias mitigation, our analysis reveals that fairness in FMs requires integrated interventions throughout the development pipeline, from data documentation to deployment protocols. This comprehensive framework advances current knowledge by demonstrating how systematic bias mitigation, combined with policy engagement, can effectively address both technical and institutional barriers to equitable AI in healthcare. The development of equitable FMs represents a critical step toward democratizing advanced healthcare technologies, particularly for underserved populations and regions with limited medical infrastructure and computational resources.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 100 of its 200 references that are in the map. First posted on arXiv 24 Feb 2025.

Builds on

100 of 200 references.

References · 100

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  4. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  5. 2023Visual Instruction Tuningcited by 7,792
  6. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,764
  7. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,339
  8. 2021On the Opportunities and Risks of Foundation Modelscited by 3,961
  9. 2023QLoRA: Efficient Finetuning of Quantized LLMscited by 3,355
  10. 2023Sigmoid Loss for Language Image Pre-Trainingcited by 3,048
  11. 2022Survey of Hallucination in Natural Language Generationcited by 2,056
  12. 2020Shortcut Learning in Deep Neural Networkscited by 1,928
38 more
  1. 2019A Survey on Bias and Fairness in Machine Learningcited by 1,911
  2. 2023A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questionscited by 1,582
  3. 2019CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparisoncited by 1,410
  4. 2023LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Daycited by 1,287
  5. 2025SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Featurescited by 1,127
  6. 2015Prioritized Experience Replaycited by 1,070
  7. 2018Model Cards for Model Reportingcited by 1,068
  8. 2023Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecturecited by 982
  9. 2017ChestX-ray8: Hospital-scale Chest X-ray Database and Benchmarks on Weakly-Supervised Classification and Localization of Common Thorax Diseasescited by 969
  10. 2023SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Modelscited by 787
  11. 2021Deduplicating Training Data Makes Language Models Bettercited by 705
  12. 2019MIMIC-CXR-JPG, a large publicly available database of labeled chest radiographscited by 590
  13. 2022MedCLIP: Contrastive Learning from Unpaired Medical Images and Textcited by 564
  14. 2023BiomedCLIP: a multimodal biomedical foundation model pretrained from fifteen million scientific image-text pairscited by 506
  15. 2023Improved Techniques for Training Consistency Modelscited by 430
  16. 2017On Fairness and Calibrationcited by 406
  17. 2024A Survey on Hallucination in Large Vision-Language Modelscited by 352
  18. 2019Differential Privacy Has Disparate Impact on Model Accuracycited by 316
  19. 2019PadChest: A large chest x-ray image dataset with multi-label annotated reportscited by 308
  20. 2023Demystifying CLIP Datacited by 265
  21. 2022Prioritized Training on Points that are Learnable, Worth Learning, and Not Yet Learntcited by 233
  22. 2023Segment Anything in Medical Imagescited by 226
  23. 2023PMC-CLIP: Contrastive Language-Image Pre-training using Biomedical Documentscited by 212
  24. 2021Self-supervised Pretraining of Visual Features in the Wildcited by 197
  25. 2021Evaluating Deep Neural Networks Trained on Clinical Images in Dermatology with the Fitzpatrick 17k Datasetcited by 184
  26. 2021On Hallucination and Predictive Uncertainty in Conditional Language Generationcited by 176
  27. 2020To be Robust or to be Fair: Towards Fairness in Adversarial Trainingcited by 137
  28. 2023On the Challenges and Perspectives of Foundation Models for Medical Image Analysiscited by 135
  29. 2019Fairness in Deep Learning: A Computational Perspectivecited by 123
  30. 2020Ethical Machine Learning in Health Carecited by 112
  31. 2024BiomedParse: a biomedical foundation model for image parsing of everything everywhere all at oncecited by 107
  32. 2024The rising costs of training frontier AI modelscited by 91
  33. 2023Generative models improve fairness of medical classifiers under distribution shiftscited by 90
  34. 2021MedPerf: Open Benchmarking Platform for Medical Artificial Intelligence using Federated Evaluationcited by 88
  35. 2024RADIOv2.5: Improved Baselines for Agglomerative Vision Foundation Modelscited by 88
  36. 2024Large Concept Models: Language Modeling in a Sentence Representation Spacecited by 86
  37. 2022Video Polyp Segmentation: A Deep Learning Perspectivecited by 81
  38. 2022Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervisioncited by 80

50 most cited of 100 All 100 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 1; 2026: 2.

3 papers.

  1. 2025From Classical Machine Learning to Emerging Foundation Models: Review on Multimodal Data Integration for Cancer Researchcited by 6
  2. 2026A pipeline for enabling path-specific causal fairness in observational health datacited by 0
  3. 2026FOCUS: Benchmarking Retinal Model Generalization from Foundation Vision Encoders to Multimodal LLMscited by 0