mlsanityData to 7 Oct 2026

Advancing human-centric AI for robust X-ray analysis through holistic self-supervised learning

arXiv 2405.01469 ↗First posted 2 May 2024cs.CV cs.AIcited by 18

Not on the map. Why?

Abstract (arXiv)

AI Foundation models are gaining traction in various applications, including medical fields like radiology. However, medical foundation models are often tested on limited tasks, leaving their generalisability and biases unexplored. We present RayDINO, a large visual encoder trained by self-supervision on 873k chest X-rays. We compare RayDINO to previous state-of-the-art models across nine radiology tasks, from classification and dense segmentation to text generation, and provide an in depth analysis of population, age and sex biases of our model. Our findings suggest that self-supervision allows patient-centric AI proving useful in clinical workflows and interpreting X-rays holistically. With RayDINO and small task-specific adapters, we reach state-of-the-art results and improve generalization to unseen populations while mitigating bias, illustrating the true promise of foundation models: versatility and robustness.

Key facts. Cited by 18 papers in the map (data through 7 Oct 2026). Builds on 27 of its 63 references that are in the map. First posted on arXiv 2 May 2024.

Builds on

27 of 63 references.

References · 27

  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. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  4. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,764
  5. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
  6. 2018Unsupervised Feature Learning via Non-Parametric Instance-level Discriminationcited by 1,838
  7. 2019CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparisoncited by 1,410
  8. 2017ChestX-ray8: Hospital-scale Chest X-ray Database and Benchmarks on Weakly-Supervised Classification and Localization of Common Thorax Diseasescited by 969
  9. 2021iBOT: Image BERT Pre-Training with Online Tokenizercited by 891
  10. 2020CheXbert: Combining Automatic Labelers and Expert Annotations for Accurate Radiology Report Labeling Using BERTcited by 329
  11. 2021RadGraph: Extracting Clinical Entities and Relations from Radiology Reportscited by 310
  12. 2019PadChest: A large chest x-ray image dataset with multi-label annotated reportscited by 308
15 more
  1. 2020VinDr-CXR: An open dataset of chest X-rays with radiologist's annotationscited by 236
  2. 2024Exploring scalable medical image encoders beyond text supervisioncited by 129
  3. 2023Knowledge-enhanced Visual-Language Pre-training on Chest Radiology Imagescited by 128
  4. 2021Self-supervised Learning is More Robust to Dataset Imbalancecited by 122
  5. 2018Spreading vectors for similarity searchcited by 114
  6. 2021Generalized Radiograph Representation Learning via Cross-supervision between Images and Free-text Radiology Reportscited by 80
  7. 2022Improving the Fairness of Chest X-ray Classifierscited by 52
  8. 2022Improving Radiology Report Generation Systems by Removing Hallucinated References to Non-existent Priorscited by 48
  9. 2022Detailed Annotations of Chest X-Rays via CT Projection for Report Understandingcited by 24
  10. 2023Accurate Fine-Grained Segmentation of Human Anatomy in Radiographs via Volumetric Pseudo-Labelingcited by 24
  11. 2021VinDr-RibCXR: A Benchmark Dataset for Automatic Segmentation and Labeling of Individual Ribs on Chest X-rayscited by 22
  12. 2023UniChest: Conquer-and-Divide Pre-training for Multi-Source Chest X-Ray Classificationcited by 21
  13. 2022Potential sources of dataset bias complicate investigation of underdiagnosis by machine learning algorithmscited by 19
  14. 2023Foundation Ark: Accruing and Reusing Knowledge for Superior and Robust Performancecited by 11
  15. 2022POLCOVID: a multicenter multiclass chest X-ray database (Poland, 2020-2021)cited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 4; 2025: 8; 2026: 6.

18 papers.

Sort:

By area:

  1. 2025Cluster and Predict Latent Patches for Improved Masked Image Modelingcited by 17
  2. 2024ExPLoRA: Parameter-Efficient Extended Pre-Training to Adapt Vision Transformers under Domain Shiftscited by 16
  3. 2024Robust image representations with counterfactual contrastive learningcited by 12
  4. 2025Foundation Models in Medical Imaging: A Review and Outlookcited by 7
  5. 2024Mask of truth: model sensitivity to unexpected regions of medical imagescited by 6
  6. 2025Chest X-ray Foundation Model with Global and Local Representations Integrationcited by 5
  7. 2025Data Scaling Laws for Radiology Foundation Modelscited by 4
  8. 2025Decipher-MR: A Vision-Language Foundation Model for 3D MRI Representationscited by 4
  9. 2024DiNO-Diffusion. Scaling Medical Diffusion via Self-Supervised Pre-Trainingcited by 2
  10. 2026Multi-Modal Multi-Agent Reinforcement Learning for Radiology Report Generationcited by 1
  11. 2025Unsupervised Parameter Efficient Source-free Post-pretrainingcited by 0
  12. 2025Evaluating Vision Language Models (VLMs) for Radiology: A Comprehensive Analysiscited by 0
6 more
  1. 2025Multi Anatomy X-Ray Foundation Modelcited by 0
  2. 2026Capability neq Interpretability: Human Interpretability of Vision Foundation Modelscited by 0
  3. 2026Who Needs Labels? Adapting Vision Foundation Models With the Metadata You Already Havecited by 0
  4. 2026Mirror-Fusion Attention for Reflection-Aware Self-Supervised Representation Learningcited by 0
  5. 2026Benchmarking the Robustness of Foundation Models for Mammography under Domain Shiftcited by 0
  6. 2026B-MIM: Biased Masked Image Modeling for Generalizable Segmentation of Fine-Grained Anatomical Structurescited by 0