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.

  • Comment
  • Published:

Visual interpretability of bioimaging deep learning models

Nature Methods volume 21, pages 1394–1397 (2024)Cite this article

Subjects

The success of deep learning in analyzing bioimages comes at the expense of biologically meaningful interpretations. We review the state of the art of explainable artificial intelligence (XAI) in bioimaging and discuss its potential in hypothesis generation and data-driven discovery.

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

Relevant articles

Open Access articles citing this article.

Access options

Buy this article

  • Purchase on SpringerLink
  • Instant access to full article PDF
Buy now

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

Fig. 1: The visual interpretability process.
Fig. 2: Saliency map-based (bottom right) versus counterfactual-based (top) explanations.

References

  1. Zaritsky, A. et al. Cell Syst. 12, 733–747.e6 (2021).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  2. DeGrave, A. J., Cai, Z. R., Janizek, J. D., Daneshjou, R. & Lee, S. I. Nat. Biomed. Eng. https://doi.org/10.1038/s41551-023-01160-9 (2023).

    Article  PubMed  Google Scholar 

  3. Lamiable, A. et al. Nat. Commun. 14, 6386 (2023).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  4. Rotem, O. et al. Preprint at bioRxiv https://doi.org/10.1101/2023.11.15.566968. (2023).

  5. Kobayashi, H., Cheveralls, K. C., Leonetti, M. D. & Royer, L. A. Nat. Methods 19, 995–1003 (2022).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  6. Razdaibiedina, A. et al. Mol. Syst. Biol. 20, 521–548 (2024).

    Article  PubMed  PubMed Central  Google Scholar 

  7. Lundberg, S. & Lee, S.-I. NIPS’17: Proc. 31st International Conference on Neural Information Processing Systems 4768–4777 (ACM, 2017).

  8. Soelistyo, C. J. et al. Nat. Mach. Intell. 4, 636–644 (2022).

    Article  Google Scholar 

  9. Yamamoto, T., Cockburn, K., Greco, V. & Kawaguchi, K. PLOS Comput. Biol. 18, e1010477 (2022).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  10. Schmitt, M. S. et al. Cell 187, 481–494.e24 (2024).

    Article  CAS  PubMed  Google Scholar 

  11. Doron, M. et al. Preprint at bioRxiv https://doi.org/10.1101/2023.06.16.545359 (2023).

  12. LaChance, J., Suh, K., Clausen, J. & Cohen, D. J. PLOS Comput. Biol. 18, e1009293 (2022).

    Article  CAS  Google Scholar 

  13. Yang, K. D. et al. PLOS Comput. Biol. 16, e1007828 (2020).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  14. Eckstein, N. et al. Cell 187, 2574–2594 (2024).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  15. Soelistyo, C. J. & Lowe, A. R. Preprint at arXiv https://doi.org/10.48550/arXiv.2402.03115 (2024).

Download references

Acknowledgements

This research was supported by the Israeli Council for Higher Education (CHE) via the Data Science Research Center, Ben-Gurion University of the Negev, Israel (to AZ), and by the Rosetree trust (to AZ). We thank Nadav Rappoport, Meghan Driscoll, Orit Kliper-Gross and Kevin Dean for critically reading this Comment.

Author information

Authors and Affiliations

  1. Department of Software and Information Systems Engineering, Ben-Gurion University of the Negev, Be’er-Sheva, Israel

    Oded Rotem & Assaf Zaritsky

Authors
  1. Oded Rotem
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Assaf Zaritsky
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

O.R. and A.Z. conceived and wrote this comment.

Corresponding author

Correspondence to Assaf Zaritsky.

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

Rotem, O., Zaritsky, A. Visual interpretability of bioimaging deep learning models. Nat Methods 21, 1394–1397 (2024). https://doi.org/10.1038/s41592-024-02322-6

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1038/s41592-024-02322-6

This article is cited by

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