ORIGINAL RESEARCH article
Front. Cell Dev. Biol.
Sec. Molecular and Cellular Pathology
Volume 13 - 2025 | doi: 10.3389/fcell.2025.1665173
This article is part of the Research TopicArtificial Intelligence Applications in Chronic Ocular Diseases, Volume IIView all 52 articles
Diagnostic performance and generalizability of deep learning for multiple retinal diseases using bimodal imaging of fundus photography and optical coherence tomography
Provisionally accepted
Xingwang Gu1Yang Zhou2Jianchun Zhao2Hongzhe Zhang1Xinlei Pan3Bing Li1Bilei Zhang4
Yuelin Wang5Song Xia6Hailan Lin7Jie Wang7
Dayong Ding2Xirong Li7*Shan Wu8*
Jingyuan Yang1*
Youxin Chen1*- 1Peking Union Medical College Hospital (CAMS), Beijing, China
- 2Visionary Intelligence Ltd., Beijing, China
- 3The First Affiliated Hospital of Zhejiang University School of Medicine, Hangzhou, China
- 4Hunan Provincial People's Hospital, Changsha, China
- 5Peking University Third Hospital, Beijing, China
- 6Guizhou Provincial People's Hospital, Guiyang, China
- 7Renmin University of China, Beijing, China
- 8Beijing Hospital, Beijing, China
Select one of your emails
You have multiple emails registered with Frontiers:
Notify me on publication
Please enter your email address:
If you already have an account, please login
You don't have a Frontiers account ? You can register here
Purpose: To develop and evaluate deep learning (DL) models for detecting multiple retinal diseases using bimodal imaging of color fundus photography (CFP) and optical coherence tomography (OCT), assessing diagnostic performance and generalizability. Methods: This cross-sectional study utilized 1445 CFP-OCT pairs from 1029 patients across three hospitals. Five bimodal models developed, and the model with best performance (Fusion-MIL) was tested and compared with CFP-MIL and OCT-MIL. Models were trained on 710 pairs (Maestro device), validated on 241, and tested on 255 (dataset 1). Additional tests used different devices and scanning patterns: 88 pairs (dataset 2, DRI-OCT), 91 (dataset 3, DRI-OCT), 60 (dataset 4, Visucam/VG200 OCT). Seven retinal conditions, including normal, diabetic retinopathy, dry and wet age-related macular degeneration, pathologic myopia (PM), epiretinal membran, and macular edema, were assessed. PM ATN (atrophy, traction, neovascularization) classification was trained and tested on another 1184 pairs. Area under receiver operating characteristic curve (AUC) was calculated to evaluated the performance. Results: Fusion-MIL achieved mean AUC 0.985 (95% CI 0.971-0.999) in dataset 2, outperforming CFP-MIL (0.876, P < 0.001) and OCT-MIL (0.982, P = 0.337), as well as in dataset 3 (0.978 vs. 0.913, P < 0.001 and 0.962, P = 0.025) and dataset 4 (0.962 vs. 0.962, P < 0.001 and 0.962, P = 0.079). Fusion-MIL also achieved superior accuracy. In ATN classification, AUC ranges 0.902-0.997 for atrophy, 0.869-0.982 for traction, and 0.742-0.976 for neovascularization. Conclusions: Bimodal Fusion-MIL improved diagnosis over single-modal models, showing strong generalizability across devices and detailed grading ability, valuable for various scenarios.
Keywords: deep learning, diagnosis, fundus photography, Optical Coherence Tomography, Retinal disease
Received: 13 Jul 2025; Accepted: 19 Aug 2025.
Copyright: © 2025 Gu, Zhou, Zhao, Zhang, Pan, Li, Zhang, Wang, Xia, Lin, Wang, Ding, Li, Wu, Yang and Chen. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
* Correspondence:
Xirong Li, Renmin University of China, Beijing, China
Shan Wu, Beijing Hospital, Beijing, China
Jingyuan Yang, Peking Union Medical College Hospital (CAMS), Beijing, China
Youxin Chen, Peking Union Medical College Hospital (CAMS), Beijing, China
Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.