CoChat
Sign Up
Cited by 110Generative Adversarial Networks and Image SynthesisArtificial Intelligence in Healthcare and EducationMultimodal Machine Learning Applications

The DOI matches its Crossref record; 45 of the 45 references it cites were found in a registry or an index.

A vision–language foundation model for the generation of realistic chest X-ray images

Open access
Bluethgen, Christian, Chambon, Pierre, Delbrouck, Jean-Benoit, van der Sluijs, Rogier, Połacin, Małgorzata, Zambrano Chaves, Juan Manuel, Abraham, Tanishq Mathew, Purohit, Shivanshu, Langlotz, Curtis P., Chaudhari, Akshay S.·2024·Nature Biomedical Engineering
DOI 10.1038/s41551-024-01246-yPMC PMC11861387
Open this paper in CoChat — free accountOpen PDF

Abstract

The paucity of high-quality medical imaging datasets could be mitigated by machine learning models that generate compositionally diverse images that faithfully represent medical concepts and pathologies. However, large vision-language models are trained on natural images, and the diversity distribution of the generated images substantially differs from that of medical images. Moreover, medical language involves specific and semantically rich vocabulary. Here we describe a domain-adaptation strategy for large vision-language models that overcomes distributional shifts. Specifically, by leveraging publicly available datasets of chest X-ray images and the corresponding radiology reports, we adapted a latent diffusion model pre-trained on pairs of natural images and text descriptors to generate diverse and visually plausible synthetic chest X-ray images (as confirmed by board-certified radiologists) whose appearance can be controlled with free-form medical text prompts. The domain-adaptation strategy for the text-conditioned synthesis of medical images can be used to augment training datasets and is a viable alternative to the sharing of real medical images for model training and fine-tuning.

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1038/s41551-024-01246-y

Cites

45 of 45 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Research works printed but not linked: 16

  1. Ramesh, A., Dhariwal, P., Nichol, A., Chu, C. & Chen, M. Hierarchical text-conditional image generation with CLIP latents. Preprint at https://arxiv.org/abs/2204.06125v1 (2022). · arXiv
  2. Lin, C.-Y. ROUGE: A package for automatic evaluation of summaries. In Text Summarization Branches Out 74–81 (Association for Computational Linguistics, 2004).
  3. Zhang, T., Kishore, V., Wu, F., Weinberger, K. Q. & Artzi, Y. BERTScore: evaluating text generation with BERT. In International Conference on Learning Representations (2020).
  4. Zhang, Y., Jiang, H., Miura, Y., Manning, C. D. & Langlotz, C. P. Contrastive Learning of Medical Visual Representations from Paired Images and Text. In Proc. 7th Machine Learning for Healthcare Conference Vol. 182 (eds Lipton, Z., Ranganath, R., Sendak, M., Sjoding, M. & Yeung, S.) 2–25 (PMLR, 2022).
  5. Endo, M., Krishnan, R., Krishna, V., Ng, A. Y. & Rajpurkar, P. Retrieval-based chest x-ray report generation using a pre-trained contrastive language-image model. In Proc. Machine Learning for Health Vol. 158 (eds Roy, S. et al.) 209–219 (PMLR, 2021).
  6. van der Sluijs, R., Bhaskhar, N., Rubin, D., Langlotz, C. & Chaudhari, A. Exploring image augmentations for siamese representation learning with chest X-rays. In Medical Imaging with Deep Learning Vol. 227 (eds Oguz, I. et al.) 444–467 (PMLR, 2024).
  7. Alain, G. & Bengio, Y. Understanding intermediate layers using linear classifier probes. Preprint at https://arxiv.org/abs/1610.01644v4 (2016). · arXiv
  8. Liu, C., Shah, A., Bai, W. & Arcucci, R. Utilizing synthetic data for medical vision-language pre-training: bypassing the need for real images. Preprint at https://arxiv.org/abs/2310.07027 (2023). · arXiv
  9. Clark, K., Vicol, P., Swersky, K. & Fleet, D. J. Directly fine-tuning diffusion models on differentiable rewards. In The Twelfth International Conference on Learning Representations (ICLR) https://openreview.net/forum?id=1vmSEVL19f (2024).
  10. Liu, L., Ren, Y., Lin, Z. & Zhao, Z. Pseudo numerical methods for diffusion models on manifolds. In The Tenth International Conference on Learning Representations (ICLR) https://openreview.net/forum?id=PlKWVd2yBkY (2022).
  11. Chambon, P., Bluethgen, C., Langlotz, C. P. & Chaudhari, A. Adapting pretrained vision-language foundational models to medical imaging domains. In NeurIPS 2022 Foundation Models for Decision Making Workshop https://openreview.net/forum?id=QtxbYdJVT8Q (2022).
  12. Kynkäänniemi, T., Karras, T., Aittala, M., Aila, T. & Lehtinen, J. The role of ImageNet classes in Fréchet inception distance. In The Eleventh International Conference on Learning Representations (ICLR) https://openreview.net/forum?id=4oXTQ6m_ws8 (2023).
  13. Wang, Z., Simoncelli, E. P. & Bovik, A. C. Multiscale structural similarity for image quality assessment. In Thirty-Seventh Asilomar Conference on Signals, Systems and Computers 2003 Vol. 2, 1398–1402 (IEEE, 2003).
  14. Szymański, P. & Kajdanowicz, T. A network perspective on stratification of multi-label data. In Proc. First International Workshop on Learning with Imbalanced Domains: Theory and Applications Vol. 74 (eds Torgo, L., Branco, P. & Moniz, N.) 22–35 (PMLR, 2017).
  15. Chen, T., Kornblith, S., Norouzi, M. & Hinton, G. A simple framework for contrastive learning of visual representations. In Proc. 37th International Conference on Machine Learning 119 (eds Daumé III, H. & Singh, A.) 1597–1607 (PMLR, 2020).
  16. Chen, X., Fan, H., Girshick, R. & He, K. Improved baselines with momentum contrastive learning. Preprint at https://arxiv.org/abs/2003.04297v1 (2020). · arXiv

Cited by

Sorted by citations

See all 110

Related

See all

Metadata

Authors
Bluethgen, C., Chambon, P., Delbrouck, J.-B., van der Sluijs, R., Połacin, M., Zambrano Chaves, J. M., Abraham, T. M., Purohit, S., Langlotz, C. P., & Chaudhari, A. S.
Affiliations
  • Stanford University (US)
  • University of California, Davis (US)
ORCID
Venue
Nature Biomedical Engineering
Publisher
Springer Science and Business Media LLC
Published
2024-08-26
Volume
9
Issue
4
Pages
494-506
ISSN
2157-846X (ISSN-L)
DOI
10.1038/s41551-024-01246-y
PMC
PMC11861387
OpenAlex
W4401888965
Cited by
108
References
43
Citations by year
2026: 48 · 2025: 54 · 2024: 6
FWCI
15.12
Type
journal article
Language
en
Open access
Licence
Locations
  • Nature Biomedical Engineering (publishedVersion)
  • PubMed (publishedVersion)
  • PubMed Central (acceptedVersion)
  • Zurich Open Repository and Archive (University of Zurich) (submittedVersion)
Funders
  • Schweizerische Gesellschaft für Radiologie
  • National Institutes of Health (75N92020C00021, 75N92020C00008, AR077604, EB002524)
  • National Heart, Lung, and Blood Institute (75N92020C00008, 75N92020C00021, R01HL169345, R01HL167974)
  • National Institute of Arthritis and Musculoskeletal and Skin Diseases (R01AR077604, R01AR079431)
  • National Institute of Biomedical Imaging and Bioengineering (75N92020C00021, EB 002524, 75N92020C00008, P41EB027060, R01EB002524)
Topics
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Generative Adversarial Networks and Image Synthesis
  • Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Multimodal Machine Learning Applications
Keywords
vision-language foundation models, latent diffusion models, domain adaptation, distribution shift, radiology reports, medical image synthesis, data augmentation, medical image dataset
MeSH terms
Machine Learning, Algorithms, Humans, Image Processing, Computer-Assisted, Language, Radiography, Thoracic, Thorax, Databases, Factual

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review