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.

  • Correspondence
  • Published:

Reproducibility report: quantum machine learning methods in fundus analysis—a benchmark study

Eye volume 39, pages 2728–2730 (2025)Cite this article

Subjects

Access through your institution
Buy or subscribe

Building on the article “Quantum Machine Learning in Ophthalmology” [1], which highlights QML’s potential, we address the lack of benchmarks and reproducibility by presenting results and open-source scripts using standard fundus dataset. This report is the first of its kind in ophthalmic AI and aims to pave the way for reliable, transparent, and impactful QML research.

PQC-Based Learning: A hybrid quantum approach where Parameterized Quantum Circuits (PQCs) were used as trainable components in Quantum Neural Networks (QNNs). Two different PQC architectures were developed based on prestigious QML literature in image classification [3, 4]. These models were trained directly on fundus images with available labels and compared against corresponding conventional convolutional neural networks (CNNs).

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

Access options

Access through your institution

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: Side-by-side demonstration of QML and corresponding ML methods addressed in this study.
Fig. 2

Data availability

All the data, scripts, along with comprehensive instructions, are available at https://github.com/mohaEs/QML and https://github.com/gajanm/QML-For-Fundus-Imaging and have been tested by authors independently.

References

  1. Masalkhi M, Ong J, Waisberg E, Lee AG. Quantum machine learning in ophthalmology. Eye. 2024;38:2857–8.

    Article  PubMed  PubMed Central  Google Scholar 

  2. Zhou Y, Chia MA, Wagner SK, Ayhan MS, Williamson DJ, Struyven RR, et al. A foundation model for generalizable disease detection from retinal images. Nature. 2023;622:156–63.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  3. Mari A, Bromley TR, Izaac J, Schuld M, Killoran N. Transfer learning in hybrid classical-quantum neural networks. Quantum. 2020;4:340.

    Article  Google Scholar 

  4. Senokosov A, Sedykh A, Sagingalieva A, Kyriacou B, Melnikov A. Quantum machine learning for image classification. Machine Learn Sci Technol. 2024;5:015040.

    Article  Google Scholar 

  5. Xiong Q, Ding X, Fei Y, Zhou X, Du Q, Feng C, et al. A hybrid quantum ensemble learning model for malicious code detection. Quantum Sci Technol. 2024;9:035021.

    Article  Google Scholar 

Download references

Funding

The research is supported by U.S. Department of Health & Human Services (NIH) National Eye Institute (NEI) P30 EY003790 and R01 EY030575, R01 EY036518.

Author information

Author notes

  1. These authors contributed equally: Mohammad Eslami, Gajan Mohan Raj.

Authors and Affiliations

  1. Harvard Ophthalmology AI Lab, Schepens Eye Research Institute of Massachusetts Eye and Ear, Harvard Medical School, Boston, MA, USA

    Mohammad Eslami, Saber Kazeminasab Hashemabad, Mengyu Wang & Tobias Elze

  2. Biomedical Engineering, High Technology High School, Lincroft, NJ, USA

    Gajan Mohan Raj

  3. Computer Science, Academies of Loudoun, Ashburn, VA, USA

    Zayan Hasan

  4. Massachusetts Eye and Ear, Harvard Medical School, Boston, MA, USA

    Lucia Sobrin, Nazlee Zebardast & Michael G. Morley

Authors
  1. Mohammad Eslami
    View author publications

    Search author on:PubMed Google Scholar

  2. Gajan Mohan Raj
    View author publications

    Search author on:PubMed Google Scholar

  3. Zayan Hasan
    View author publications

    Search author on:PubMed Google Scholar

  4. Saber Kazeminasab Hashemabad
    View author publications

    Search author on:PubMed Google Scholar

  5. Lucia Sobrin
    View author publications

    Search author on:PubMed Google Scholar

  6. Mengyu Wang
    View author publications

    Search author on:PubMed Google Scholar

  7. Nazlee Zebardast
    View author publications

    Search author on:PubMed Google Scholar

  8. Michael G. Morley
    View author publications

    Search author on:PubMed Google Scholar

  9. Tobias Elze
    View author publications

    Search author on:PubMed Google Scholar

Contributions

Mohammad Eslami, Gajan Mohan Raj, and Zayan Hasan reviewed the literature, developed the scripts, and prepared the manuscript. Mohammad Eslami and Saber Kazeminasab Hashemabad reviewed the scripts and ensured reproducibility. Mohammad Eslami, Lucia Sobrin, Mengyu Wang, Nazlee Zebardast, Michael Morley, and Tobias Elze provided the necessary resources and funding, supervised the research, and reviewed the manuscript.

Corresponding author

Correspondence to Mohammad Eslami.

Ethics declarations

Competing interests

The authors declare no competing interests.

Additional information

Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Supplementary information

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Eslami, M., Raj, G.M., Hasan, Z. et al. Reproducibility report: quantum machine learning methods in fundus analysis—a benchmark study. Eye 39, 2728–2730 (2025). https://doi.org/10.1038/s41433-025-03916-w

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue date:

  • DOI: https://doi.org/10.1038/s41433-025-03916-w

Search

Advanced search

Quick links