可解释图推理框架FFA-RGNet用于眼底荧光血管造影诊断,内部测试F1达95.38%
An interpretable graph reasoning framework for enhanced diagnosis in fundus fluorescein angiography
研究团队提出可解释图推理框架FFA-RGNet,对序列眼底荧光血管造影(FFA)图像中的病灶时序与解剖位置建模以辅助疾病诊断,并在25,312张FFA图像、2651例患者的多中心数据上训练与验证。
- Article
- Open access
- Published: 27 October 2026
- Xiaocong Liu ORCID: orcid.org/0000-0001-5323-29541 na1,
- An Shao2 na1,
- Xindi Liu2,
- Zichang Su ORCID: orcid.org/0009-0004-2917-73172,
- Xiaoling Huang2,
- Yufeng Xu2,
- Hongkang Wu2,
- Wenyue Shen2,
- Yingyu Li2,
- Hongxia Xu ORCID: orcid.org/0000-0001-5384-46271,
- Juan Ye ORCID: orcid.org/0000-0002-1948-25002 &
- …
- Jian Wu ORCID: orcid.org/0000-0002-3230-63921
npj Digital Medicine (2026) Cite this article
We’re sharing this article early to provide faster access to peer-reviewed, accepted research. It is citable and carries a permanent DOI. This version is subject to further edits and will be replaced automatically by the final Version of Record. All legal disclaimers apply.
Abstract
Fundus fluorescein angiography (FFA) is the gold standard for diagnosing retinal vascular diseases. However, interpretable artificial intelligence (AI) systems for FFA image analysis that align with clinicians’ reasoning processes and real-world diagnostic workflows remain scarce. In this study, we introduce an interpretable graph reasoning framework, FFA-RGNet, that explicitly models the temporal patterns of fine-grained lesions across imaging phases and anatomical locations for disease diagnosis from sequential FFA images. FFA-RGNet was trained and validated on a large, fine-grained, multi-center dataset consisting of 25,312 FFA images from 2651 patients. FFA-RGNet outperformed nine baseline models on the internal test set, achieving an F1-score of 95.38% (95% CI: 92.24%–97.88%), and demonstrated consistent performance across multi-center and prospective validation datasets. Its diagnostic performance not only surpassed that of ophthalmologists, residents and ophthalmology students, but also improved their diagnostic F1-score by 7.48% to 14.11% when used as an assistive tool. Comprehensive inference analysis further revealed its superior ability to correctly recognize fine-grained semantic entities, and to learn stable, disease-specific graph reasoning patterns aligned with clinical knowledge. These results suggest that FFA-RGNet enables accurate diagnosis with interpretable reasoning progresses, highlighting its strong potential as a reliable AI system for FFA interpretation and clinical decision support.
Acknowledgements
We thank the Second Affiliated Hospital of Xi’an Jiaotong University (Shanxi, China) and Taizhou First People’s Hospital (Zhejiang, China) for their contribution in the dataset construction.
Funding
This research was partially supported by the National Key R&D Program of China under Grant No. 2025YFC2423903 to Jian Wu; the Transvascular Implantation Devices Research Institute (TIDRI) under Grant Nos. KY012024005 and KY012025006 to Jian Wu; the National Natural Science Foundation of China under Grants No. T2541004 to Jian Wu; and the Zhejiang Key Laboratory of Medical Imaging Artificial Intelligence to Jian Wu.
Author information
Author notes
These authors contributed equally: Xiaocong Liu, An Shao.
Authors and Affiliations
Transvascular Implantation Devices Research Institute, State Key Laboratory of Transvascular Implantation Devices of the Second Affiliated Hospital, and Zhejiang University School of Medicine, Hangzhou, China
Xiaocong Liu, Hongxia Xu & Jian Wu
Zhejiang University, Eye Center of Second Affiliated Hospital, School of Medicine, China. Zhejiang Provincial Key Laboratory of Ophthalmology. Zhejiang Provincial Clinical Research Center for Eye Diseases. Zhejiang Provincial Engineering Institute on Eye Diseases, Hangzhou, China
An Shao, Xindi Liu, Zichang Su, Xiaoling Huang, Yufeng Xu, Hongkang Wu, Wenyue Shen, Yingyu Li & Juan Ye
Authors
- Xiaocong Liu
- An Shao
- Xindi Liu
- Zichang Su
- Xiaoling Huang
- Yufeng Xu
- Hongkang Wu
- Wenyue Shen
- Yingyu Li
- Hongxia Xu
- Juan Ye
- Jian Wu
Corresponding authors
Correspondence to Juan Ye or Jian Wu.
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.
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
Liu, X., Shao, A., Liu, X. et al. An interpretable graph reasoning framework for enhanced diagnosis in fundus fluorescein angiography. npj Digit. Med. (2026). https://doi.org/10.1038/s41746-026-03428-1
Received: 28 April 2026
Accepted: 08 October 2026
Published: 27 October 2026
DOI: https://doi.org/10.1038/s41746-026-03428-1
来源:Nature 健康护理主题 · nature.com