Skip to main content

Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.

Machine learning

Harnessing medical twitter data for pathology AI

Nature Medicine volume 29, pages 2181–2182 (2023)Cite this article

Subjects

Using pathology data from Twitter, researchers have built a visual-language model for classifying and retrieving histopathology images — representing a milestone in the development of multifunctional foundational artificial intelligence models in computational pathology.

Until recently, the application of machine-learning to pathology tasks has predominantly dealt with imaging data and has largely ignored language information — which is ubiquitous in the pathologist’s workflow. Visual-language pretraining1 is a machine learning framework aimed at using both image and text data to develop general-purpose models that can work with data from either (and sometimes both) modalities. However, standard models have very limited knowledge of specialized medical domains such as pathology, so their use in clinical tasks—such as helping pathologists to make a diagnosis or find similar cases to a given query — is limited.

This is a preview of subscription content, access via your institution

Access options

Rent or buy this article

Prices vary by article type

from$1.95

to$39.95

Learn more

Prices may be subject to local taxes which are calculated during checkout

Fig. 1: Zero-shot classification with CLIP and PLIP.

References

  1. Gan, Z. et al. Found. Trends Comput. Graph. Vision 14, 163–352 (2022).

    Article  Google Scholar 

  2. Huang, Z. et al. Nat. Med. https://doi.org/10.1038/s41591-023-02504-3 (2023).

    Article  PubMed  PubMed Central  Google Scholar 

  3. Schaumberg, A. J. et al. Modern Pathol. 33, 2169–2185 (2020).

    Article  Google Scholar 

  4. Schuhmann, C. et al. Adv. Neural Inf. Process. Syst. 35, 25278–25294 (2022).

    Google Scholar 

  5. Radford, A. et al. in Proc. 38th International Conference on Machine Learning (eds. Meila, M. & Zhang, T.) 8748–8763 (Springer, 2021).

  6. Russakovsky, O. et al. Int. J. Comput. Vision 115, 211–252 (2015).

    Article  Google Scholar 

  7. Lu, M. Y. et al. in Proc. IEEE/CVF Conference on Computer Vision and Pattern Recognition (Computer Vision Foundation, 2023).

  8. Zhang, S. et al. Preprint at https://doi.org/10.48550/arXiv.2303.00915 (2023).

  9. Ikezogwo, W. O. et al. Preprint at https://doi.org/10.48550/arXiv.2306.11207 (2023).

Download references

Author information

Authors and Affiliations

  1. Department of Pathology, Brigham and Women’s Hospital, Harvard Medical School, Boston, MA, USA

    Ming Y. Lu, Bowen Chen & Faisal Mahmood

  2. Department of Pathology, Massachusetts General Hospital, Harvard Medical School, Boston, MA, USA

    Ming Y. Lu, Bowen Chen & Faisal Mahmood

  3. Cancer Program, Broad Institute of Harvard and MIT, Cambridge, MA, USA

    Ming Y. Lu & Faisal Mahmood

  4. Electrical Engineering and Computer Science, Massachusetts Institute of Technology (MIT), Cambridge, MA, USA

    Ming Y. Lu

  5. Harvard Data Science Initiative, Harvard University, Cambridge, MA, USA

    Ming Y. Lu

  6. Cancer Data Science Program, Dana-Farber Cancer Institute, Boston, MA, USA

    Ming Y. Lu & Faisal Mahmood

Authors
  1. Ming Y. Lu
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Bowen Chen
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Faisal Mahmood
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Faisal Mahmood.

Ethics declarations

Competing interests

The authors declare no competing interests.

Rights and permissions

Reprints and Permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Lu, M.Y., Chen, B. & Mahmood, F. Harnessing medical twitter data for pathology AI. Nat Med 29, 2181–2182 (2023). https://doi.org/10.1038/s41591-023-02530-1

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1038/s41591-023-02530-1

Search

Advanced search

Quick links

Nature Briefing

Sign up for the Nature Briefing newsletter — what matters in science, free to your inbox daily.

Get the most important science stories of the day, free in your inbox. Sign up for Nature Briefing