DataVXAdvanced SciencePaper
journal article·2026-03Open access

OBUSight: Clinically Aligned Generative AI for Ophthalmic Ultrasound Interpretation and Diagnosis

Xiaocong Liu, An Shao, Bingtao Guan, Ziyao Luo, Weiyi Lai, Xiaoling Huang, Jun Liu, Jie Yan, Huimin Li, Xiangji Pan, Jiawei Wang, Zichang Su, Yih Chung Tham, Jie Yang, Haotian Lin, Juan Ye, Hongxia Xu, Jian Wu

Advanced Science· Volume 13· Issue 16
Publisher pageOpen full text
Source abstract

Abstract

ABSTRACT Ocular B‐scan ultrasonography (OBU), widely used for diagnosing posterior segment ocular disorders, poses unique challenges for ophthalmologists in image interpretation. In this study, a clinically aligned generative artificial intelligence (AI) model, OBUSight, was proposed to jointly generate reports and diagnose diseases for comprehensive OBU image interpretation. OBUSight was trained and validated on a large multi‐center OBU dataset consisting of 39 654 images and 17 586 corresponding reports from 11 381 patients. By evaluating the quality of generated reports using natural language generation (NLG) metrics and clinical efficacy (CE) metrics, OBUSight outperformed eight state‐of‐the‐art models and demonstrated robust performance across multi‐center and multimorbidity validation datasets. The expert rating further indicated that OBUSight can provide clinically aligned reports without major corrections. The ancillary role of OBUSight in enhancing diagnostic efficiency was evaluated by providing ophthalmologists, residents, and ophthalmology students with its generated reports and predicted diagnoses during the diagnostic process. In both retrospective and prospective evaluations, OBUSight significantly outperformed residents and ophthalmology students (all p < 0.05), achieved diagnostic performance comparable to ophthalmologists, and reduced diagnostic time. In conclusion, OBUSight represents a promising AI tool for enhancing diagnostic efficiency in ophthalmic ultrasound practice, especially for less experienced clinicians.
Source: crossref · Quality: baseline

Research context

OpenAlex topics: Artificial Intelligence in Healthcare and Education · Retinal Imaging and Analysis · Ocular Diseases and Behçet’s Syndrome

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

Affiliations

State Key Laboratory of Transvascular Implantation Devices of the Second Affiliated Hospital Zhejiang University School of Medicine and Transvascular Implantation Devices Research Institute Hangzhou China

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

Zhongshan Ophthalmic Center, Sun Yat‐sen University, WHO Collaborating Centre for Eye Care and Vision, State Key Laboratory of Ophthalmology, Guangdong Provincial Key Laboratory of Ophthalmology and Visual Science Guangdong Provincial Clinical Research Center for Ocular Diseases Guangzhou China

Department of Ophthalmology National University of Singapore Singapore Singapore

Singapore Eye Research Institute Singapore National Eye Centre Singapore Singapore

Centre for Innovation and Precision Eye Health National University of Singapore Singapore Singapore

Division of Pharmacoepidemiology and Pharmacoeconomics Department of Medicine Brigham and Women's Hospital and Harvard Medical School Boston Massachusetts USA

Department of Genetics and Biomedical Informatics Zhongshan School of Medicine Institute for Frontier Interdisciplinary Research in Health Sciences and Technology Sun Yat‐sen University Guangzhou China

Hainan Eye Hospital and Key Laboratory of Ophthalmology, Zhongshan Ophthalmic Center Sun Yat‐sen University Guangzhou China

Liangzhu Laboratory and WeDoctor Cloud Zhejiang Key Laboratory of Medical Imaging Artificial Intelligence Hangzhou China

Funding

National Natural Science Foundation of China

References (48)

Show source-provided references
1. Role of B‐Scan Ultrasonography in Pre‐Operative Cataract Patients
2. 10.1007/s13244‐016‐0471‐z10.1007/s13244‐016‐0471‐z ↗
3. 10.1371/journal.pone.020539010.1371/journal.pone.0205390 ↗
4. 10.1016/j.compbiomed.2017.11.01810.1016/j.compbiomed.2017.11.018 ↗
5. 10.4103/0971-3026.5082710.4103/0971-3026.50827 ↗
6. 10.1056/AIoa230022110.1056/AIoa2300221 ↗
7. 10.1038/s41586‐023‐06555‐x10.1038/s41586‐023‐06555‐x ↗
8. 10.1038/s41586‐024‐07894‐z10.1038/s41586‐024‐07894‐z ↗
9. 10.1038/s41586‐024‐07618‐310.1038/s41586‐024‐07618‐3 ↗
10. 10.1038/s41586‐025‐08675‐y10.1038/s41586‐025‐08675‐y ↗
11. OpenAI.ChatGPT: Optimizing Language Models for Dialogue accessed November 30 2022 https://openai.com/blog/chatgpt/.
12. 10.1038/s41586-025-09422-z10.1038/s41586-025-09422-z ↗
13. 10.1016/j.jacasi.2024.11.01710.1016/j.jacasi.2024.11.017 ↗
14. 10.1038/s41591‐024‐03302‐110.1038/s41591‐024‐03302‐1 ↗
15. 10.1038/s41591-024-03139-810.1038/s41591-024-03139-8 ↗
16. 10.1136/bmjophth‐2024‐00187310.1136/bmjophth‐2024‐001873 ↗
17. 10.1109/JBHI.2023.327169610.1109/JBHI.2023.3271696 ↗
18. 10.1016/j.ultrasmedbio.2023.03.02210.1016/j.ultrasmedbio.2023.03.022 ↗
19. Z.LiandS.Zhou “Deep Learning‐Based Intelligent Aided Diagnosis System for Ophthalmic Ultrasound Images ”2024 17th Int. Congress on Image and Signal Processing BioMedical Engineering and Informatics (CISP‐BMEI) ″ (IEEE 2024):1–7.10.1109/CISP-BMEI64163.2024.10906113 ↗
20. 10.1136/bjo‐2022‐32295310.1136/bjo‐2022‐322953 ↗
21. 10.3389/fnins.2024.133907510.3389/fnins.2024.1339075 ↗
22. 10.1007/s40123‐024‐01009‐710.1007/s40123‐024‐01009‐7 ↗
23. 10.1167/tvst.14.2.2610.1167/tvst.14.2.26 ↗
24. 10.1016/j.artmed.2025.10331710.1016/j.artmed.2025.103317 ↗
25. 10.1101/2025.03.03.2532323710.1101/2025.03.03.25323237 ↗
26. 10.1002/advs.20250762910.1002/advs.202507629 ↗
27. A.Radford J. W.Kim C.Hallacy et al. “Learning Transferable Visual Models From Natural Language Supervision ” Proc. of the 38th Int. Conf. on Machine Learning (ICML 2021)Proceedings of Machine Learning Research (2021) http://arxiv.org/abs/2103.00020.
28. 10.1038/s41746‐025‐01772‐210.1038/s41746‐025‐01772‐2 ↗
29. 10.1038/s41467‐025‐60577‐910.1038/s41467‐025‐60577‐9 ↗
30. 10.1038/s41746‐024‐01101‐z10.1038/s41746‐024‐01101‐z ↗
31. 10.1016/j.artmed.2023.10271410.1016/j.artmed.2023.102714 ↗
32. 10.1016/j.media.2023.10279810.1016/j.media.2023.102798 ↗
33. 10.1101/2025.03.03.2532323710.1101/2025.03.03.25323237 ↗
34. ChatFFA: An Ophthalmic Chat System for Unified Vision‐Language Understanding and Question Answering for
35. A.Vaswani N.Shazeer N.Parmar et al. “Attention is All You Need ”Advances in Neural Information Processing Systemsal Information Processing Systems(Curran Associates Inc. 2017):5998–6008.
36. J.Irvin P.Rajpurkar M.Ko et al. “CheXpert: A Large Chest Radiograph Dataset With Uncertainty Labels and Expert Comparison ” Proc. of the AAAI Conf. on Artificial IntelligenceAssociation for the Advancement of Artificial Intelligence 33(2019):590–597.10.1609/aaai.v33i01.3301590 ↗
37. K.He X.Zhang S.Ren andJ.Sun “Deep Residual Learning for Image Recognition ”2016 IEEE Conf. on Computer Vision and Pattern Recognition (CVPR)IEEE (2016):770–778 https://doi.org/10.1109/CVPR.2016.90.10.1109/CVPR.2016.90 ↗
38. Y.Cui W.Che T.Liu B.Qin andZ.Yang “Pre‐Training With Whole Word Masking for Chinese BERT ”IEEE/ACM Transactions on Audio Speech and Language Processing29(IEEE 2021):3504–3514 https://doi.org/10.1109/TASLP.2021.3124365.10.1109/TASLP.2021.3124365 ↗
39. Z.Chen Y.Song T. H.Chang andX.Wan “Generating Radiology Reports via Memory‐Driven Transformer ”Proc. of the 2020 Conf. on Empirical Methods in Natural Language Processing (EMNLP)(Association for Computational Linguistics 2020):1439–1449 https://doi.org/10.18653/v1/2020.emnlp‐main.112.10.18653/v1/2020.emnlp-main.112 ↗
40. H.QinandY.Song “Reinforced Cross‐modal Alignment for Radiology Report Generation ”Findings of the Association for Computational Linguistics: ACL 2022(Association for Computational Linguistics 2022):448–458 https://doi.org/10.18653/v1/2022.findings‐acl.38.10.18653/v1/2022.findings-acl.38 ↗
41. A.Yan Z.He X.Lu et al. “Weakly Supervised Contrastive Learning for Chest X‐Ray Report Generation ”Findings of the Association for Computational Linguistics: EMNLP 2021(Association for Computational Linguistics 2021):4009–4015 https://doi.org/10.18653/v1/2021.findings‐emnlp.336.10.18653/v1/2021.findings-emnlp.336 ↗
42. Z.Chen Y.Shen Y.Song andX.Wan “Cross‐Modal Memory Networks for Radiology Report Generation ”Proc. of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th Int. Joint Conf. on Natural Language Processing(Association for Computational Linguistics 2021):5904–5914.10.18653/v1/2021.acl-long.459 ↗
43. 10.1038/s41746‐025‐01759‐z10.1038/s41746‐025‐01759‐z ↗
44. 10.48550/arXiv.2510.0866810.48550/arXiv.2510.08668 ↗
45. K.Papineni S.Roukos T.Ward andW. J.Zhu “BLEU: A Method for Automatic Evaluation of Machine Translation ”Proceedings of the 40th Annual Meeting on Association for Computational Linguistics—ACL ′02(Association for Computational Linguistics 2001):311 https://doi.org/10.3115/1073083.1073135.10.3115/1073083.1073135 ↗
46. Machine Translation on the Medical Domain: The Role of BLEU/NIST and METEOR in a Controlled Vocabulary Setting
47. Lin C. Y. · 2004 · 74
48. 10.1038/s41467-025-58344-x10.1038/s41467-025-58344-x ↗