Universal restoration of medical images

A self-supervised foundation model, HorusEye, learns realistic noise directly from X-ray scans and enables robust tomography restoration across diverse modalities, scanners, and tasks without clean training data.

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

Access options

Access Nature and 54 other Nature Portfolio journals

Get Nature+, our best-value online-access subscription

$32.99 / 30 days

cancel any time

Subscribe to this journal

Receive 12 digital issues and online access to articles

$119.00 per year

only $9.92 per issue

Rent or buy this article

Prices vary by article type

from$1.95

to$39.95

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

Fig. 1: Universal X-ray tomography restoration across modalities and tasks.

References

• Withers, P. J. et al. Nat. Rev. Methods Primers 1, 18 (2021).

Article

Google Scholar

• Chu, Y. et al. Nat. Comput. Sci. https://doi.org/10.1038/s43588-026-00973-3 (2026).

Article

Google Scholar

• Walsh, C. L. et al. Nat. Methods 18, 1532–1541 (2021).

Article

Google Scholar

• Pfeiffer, F. Nat. Photon. 12, 9–17 (2018).

Article

Google Scholar

• Diwakar, M. & Kumar, M. Biomed. Signal Process. Control 42, 73–88 (2018).

Article

Google Scholar

• Wang, G., Ye, J. C. & De Man, B. Nat. Mach. Intell. 2, 737–748 (2020).

Article

Google Scholar

• Withers, P. J. & Preuss, M. Annu. Rev. Mater. Res. 42, 81–103 (2012).

Article

Google Scholar

• Cao, H. et al. In Computer Vision – ECCV 2022 Workshops, https://doi.org/10.1007/978-3-031-25066-8_9 (Springer, 2023).
• McCollough, C. H. et al. Med. Phys. 44, e339–e352 (2017).

Article

Google Scholar

Download references

Author information

Authors and Affiliations

• Department of Electrical, Computer and Energy Engineering, University of Colorado Boulder, Boulder, CO, USA

Yide Zhang

• Biomedical Engineering Program, University of Colorado Boulder, Boulder, CO, USA

Yide Zhang

Authors

• Yide Zhang

Corresponding author

Correspondence to Yide Zhang.

Ethics declarations

Competing interests

The author declares no competing interests.

About this article

Cite this article

Zhang, Y. Universal restoration of medical images. Nat Comput Sci (2026). https://doi.org/10.1038/s43588-026-00975-1

Download citation

• Published: 03 April 2026
• Version of record: 03 April 2026
• DOI: https://doi.org/10.1038/s43588-026-00975-1