Abstract
The integration of AI-assisted biomedical image analysis into clinical practice demands AI-generated findings that are not only accurate but also interpretable. However, existing models generally lack the ability to simultaneously generate diagnostic findings and localize corresponding targets. This limitation makes it challenging to correlate AI-generated findings with visual evidence and interpret the results. To this end, we introduce UniBiomed, a universal foundation model for grounded biomedical image interpretation, which is capable of generating accurate diagnostic findings and segmenting the biomedical targets. UniBiomed is based on an integration of Multi-modal Large Language Model and Segment Anything Model, which can unify diverse biomedical tasks in universal training for advancing grounded interpretation. To develop UniBiomed, we curate a large-scale dataset comprising 27 million triplets of images, region annotations, and text descriptions. Extensive validation on 70 internal and 14 external datasets demonstrated the state-of-the-art performance of UniBiomed in diverse biomedical tasks.
Similar content being viewed by others
Acknowledgements
We thank the support of HKUST SuperPOD for providing the GPU platform for model training. Icons of Figs. 1 (a, c, d), 5 (a, b), 6, and Supplementary Figs. A5 (b), A8, A9 (a, b) are made by Freepik from www.flaticon.com.
This project has been reviewed and approved by the Human and Artefacts Research Ethics Committee (HAREC). The protocol number is HREP-2025-0188.
Funding
This work was supported by the Hong Kong Innovation and Technology Commission (Project No. MHP/002/22, GHP/006/22GD and ITCPD/17-9), HKUST (Project No. FS111), and the Research Grants Council of the Hong Kong Special Administrative Region, China (Project Reference Number: T45-401/22-N).
Author information
Authors and Affiliations
Corresponding author
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.
Source data
Rights and permissions
Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by-nc-nd/4.0/.
About this article
Cite this article
Wu, L., Nie, Y., He, S. et al. A universal foundation model for grounded biomedical image interpretation. Nat Commun (2026). https://doi.org/10.1038/s41467-026-73986-1
Received:
Accepted:
Published:
DOI: https://doi.org/10.1038/s41467-026-73986-1
