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

Publisher: WILEY-VCH Country of Publication: Germany NLM ID: 101664569 Publication Model: Print-Electronic Cited Medium: Internet ISSN: 2198-3844 (Electronic) Linking ISSN: 21983844 NLM ISO Abbreviation: Adv Sci (Weinh) Subsets: MEDLINE

Original Publication: Weinheim : WILEY-VCH, [2014]-

Eye Diseases*/diagnostic imaging ; Eye Diseases*/diagnosis ; Image Interpretation, Computer-Assisted*/methods ; Artificial Intelligence*; Ultrasonography/methods ; Ophthalmology/methods ; Humans ; Retrospective Studies ; Prospective Studies ; Female ; Male

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.
(© 2026 The Author(s). Advanced Science published by Wiley‐VCH GmbH.)

M. A. Qureshi and K. Laghari, “Role of B‐Scan Ultrasonography in Pre‐Operative Cataract Patients,” International Journal of Health Sciences 4 (2010): 31.
M. De La Hoz Polo, “Ocular Ultrasonography Focused on the Posterior Eye Segment: What Radiologists Should Know,” Insights Into Imaging 7 (2016): 351–364, https://doi.org/10.1007/s13244‐016‐0471‐z.
H. Yu, M. Ding, X. Zhang, and J. Wu, “PCANet Based Nonlocal Means Method for Speckle Noise Removal in Ultrasound Images,” PLoS ONE 13 (2018): 0205390, https://doi.org/10.1371/journal.pone.0205390.
K. M. Meiburger, U. R. Acharya, and F. Molinari, “Automated Localization and Segmentation Techniques for B‐Mode Ultrasound Images: A Review,” Computers in Biology and Medicine 92 (2018): 210–235, https://doi.org/10.1016/j.compbiomed.2017.11.018.
V. Aironi and S. Gandage, “Pictorial Essay: B‐Scan Ultrasonography in Ocular Abnormalities,” Indian Journal of Radiology and Imaging 19 (2009): 109–115.
J. Qiu, J. Wu, H. Wei, et al., “Development and Validation of a Multimodal Multitask Vision Foundation Model for Generalist Ophthalmic Artificial Intelligence,” NEJM AI 1 (2024), AIoa2300221.
Y. Zhou, M. A. Chia, S. K. Wagner, et al., “A Foundation Model for Generalizable Disease Detection From Retinal Images,” Nature 622 (2023): 156–163, https://doi.org/10.1038/s41586‐023‐06555‐x.
X. Wang, J. Zhao, E. Marostica, et al., “A Pathology Foundation Model for Cancer Diagnosis and Prognosis Prediction,” Nature 634 (2024): 970–978, https://doi.org/10.1038/s41586‐024‐07894‐z.
M. Y. Lu, B. Chen, D. F. K. Williamson, et al., “A Multimodal Generative AI Copilot for Human Pathology,” Nature 634 (2024): 466–473, https://doi.org/10.1038/s41586‐024‐07618‐3.
V. M. Rao, M. Hla, M. Moor, et al., “Multimodal Generative AI for Medical Image Interpretation,” Nature 639 (2025): 888–896, https://doi.org/10.1038/s41586‐025‐08675‐y.
OpenAI. ChatGPT: Optimizing Language Models for Dialogue, accessed November 30, 2022, https://openai.com/blog/chatgpt/.
D. Guo, D. Yang, H. Zhang, et al., “DeepSeek-R1 incentivizes reasoning in LLMs through reinforcement learning,” Nature 645 (2025): 633–638, https://doi.org/10.1038/s41586-025-09422-z.
T. Nakamura and T. Sasano, “Emerging Potential and Challenges of AI‐Based ECG Analysis in Clinical Medicine,” JACC: Asia 5 (2025): 99–100, https://doi.org/10.1016/j.jacasi.2024.11.017.
R. Tanno, D. G. T. Barrett, A. Sellergren, et al., “Collaboration Between Clinicians and Vision–Language Models in Radiology Report Generation,” Nature Medicine 31 (2025): 599–608, https://doi.org/10.1038/s41591‐024‐03302‐1.
J. Li, Z. Guan, J. Wang, et al., “Integrated Image‐Based Deep Learning and Language Models for Primary Diabetes Care,” Nature Medicine 30 (2024): 2886–2896.
Q. Wei, Q. Chen, C. Zhao, and R. Jiang, “Performance of Automated Machine Learning in Detecting Fundus Diseases Based on Ophthalmologic B‐Scan Ultrasound Images,” BMJ Open Ophthalmology 9 (2024): 001873, https://doi.org/10.1136/bmjophth‐2024‐001873.
R. Dan, Y. Li, Y. Wang, et al., “CDNet: Contrastive Disentangled Network for Fine‐Grained Image Categorization of Ocular B‐Scan Ultrasound,” IEEE Journal of Biomedical and Health Informatics 27 (2023): 3525–3536, https://doi.org/10.1109/JBHI.2023.3271696.
Z. Li, J. Yang, X. Wang, and S. Zhou, “Establishment and Evaluation of Intelligent Diagnostic Model for Ophthalmic Ultrasound Images Based on Deep Learning,” Ultrasound in Medicine & Biology 49 (2023): 1760–1767, https://doi.org/10.1016/j.ultrasmedbio.2023.03.022.
Z. Li and S. 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.
Y. Wang, Z. Xu, R. Dan, et al., “Automated Classification of Multiple Ophthalmic Diseases Using Ultrasound Images by Deep Learning,” British Journal of Ophthalmology 108 (2024): 999–1004, https://doi.org/10.1136/bjo‐2022‐322953.
S. Zhu, X. Liu, Y. Lu, et al., “Application and Visualization Study of an Intelligence‐Assisted Classification Model for Common Eye Diseases Using B‐Mode Ultrasound Images,” Frontiers in Neuroscience 18 (2024): 1339075, https://doi.org/10.3389/fnins.2024.1339075.
X. Ye, S. He, R. Dan, et al., “Ocular Disease Detection With Deep Learning (Fine‐Grained Image Categorization) Applied to Ocular B‐Scan Ultrasound Images,” Ophthalmology and Therapy 13 (2024): 2645–2659, https://doi.org/10.1007/s40123‐024‐01009‐7.
O. Caki, U. Y. Guleser, D. Ozkan, et al., “Automated Detection of Retinal Detachment Using Deep Learning‐Based Segmentation on Ocular Ultrasonography Images,” Translational Vision Science & Technology 14 (2025): 26, https://doi.org/10.1167/tvst.14.2.26.
J. Wang, J. Fan, M. Zhou, Y. Zhang, and M. Shi, “A Labeled Ophthalmic Ultrasound Dataset with Medical Report Generation Based on Cross‐modal Deep Learning,” Artificial Intelligence in Medicine 171 (2026): 103317.
F. Gan, L. Chen, W. Qin, et al., “An Automated Diagnostic Report and Interpretation System for Ophthalmic B‐scan Ultrasound Using Multimodal Artificial Intelligence,” medRxiv 3 (2025): 03, https://doi.org/10.1101/2025.03.03.25323237.
Y. Wang, Q. Wang, M. Zhou, et al., “Integration of Genetic and Imaging Data for Alzheimer's Disease Diagnosis and Interpretation,” Advanced Science 12 (2025): 07629, https://doi.org/10.1002/advs.202507629.
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.
D. Shi, W. Zhang, J. Yang, et al., “A Multimodal Visual–Language Foundation Model for Computational Ophthalmology,” Npj Digital Medicine 8 (2025): 381, https://doi.org/10.1038/s41746‐025‐01772‐2.
M. Wang, T. Lin, A. Lin, et al., “Enhancing Diagnostic Accuracy in Rare and Common Fundus Diseases With a Knowledge‐Rich Vision‐Language Model,” Nature Communications 16 (2025): 5528, https://doi.org/10.1038/s41467‐025‐60577‐9.
X. Chen, W. Zhang, P. Xu, et al., “FFA‐GPT: An Automated Pipeline for Fundus Fluorescein Angiography Interpretation and Question‐Answer,” Npj Digital Medicine 7 (2024): 111, https://doi.org/10.1038/s41746‐024‐01101‐z.
G. Zhao, Z. Zhao, W. Gong, and F. Li, “Radiology Report Generation With Medical Knowledge and Multilevel Image‐Report Alignment: A New Method and its Verification,” Artificial Intelligence in Medicine 146 (2023): 102714, https://doi.org/10.1016/j.artmed.2023.102714.
S. Yang, X. Wu, S. Ge, Z. Zheng, S. K. Zhou, and L. Xiao, “Radiology Report Generation With a Learned Knowledge Base and Multi‐Modal Alignment,” Medical Image Analysis 86 (2023): 102798, https://doi.org/10.1016/j.media.2023.102798.
F. Gan, L. Chen, W. G. Qin, et al., “OphthUS‐GPT: Multimodal AI for Automated Reporting in Ophthalmic B‐Scan Ultrasound,” medRxiv 3 (2025), https://doi.org/10.1101/2025.03.03.25323237.
X. Chen, P. Xu, Y. Li, et al., “ChatFFA: An Ophthalmic Chat System for Unified Vision‐Language Understanding and Question Answering for,” Fundus Fluorescein Angiography Iscience 27 (2024): 110021.
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.
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 Intelligence Association for the Advancement of Artificial Intelligence, 33 (2019): 590–597.
K. He, X. Zhang, S. Ren, and J. 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.
Y. Cui, W. Che, T. Liu, B. Qin, and Z. Yang, “Pre‐Training With Whole Word Masking for Chinese BERT,” IEEE/ACM Transactions on Audio, Speech, and Language Processing 29 (IEEE, 2021): 3504–3514, https://doi.org/10.1109/TASLP.2021.3124365.
Z. Chen, Y. Song , T. H. Chang , and X. 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.
H. Qin and Y. 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.
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.
Z. Chen, Y. Shen, Y. Song, and X. 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.
A. Shao, X. Liu, W. Shen, et al., “Generative artificial Intelligence for Fundus Fluorescein Angiography Interpretation and Human Expert Evaluation,” Npj Digital Medicine 8 (2025): 396, https://doi.org/10.1038/s41746‐025‐01759‐z.
S. Jiang, Y. Wang, S. Song, et al., “Hulu‐Med: A Transparent Generalist Model towards Holistic Medical Vision‐Language Understanding,” arXiv (2025); arXiv:251008668, https://doi.org/10.48550/arXiv.2510.08668.
K. Papineni, S. Roukos, T. Ward, and W. 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.
A. Castilla, A. Bacic, and S. Furuie, “Machine Translation on the Medical Domain: The Role of BLEU/NIST and METEOR in a Controlled Vocabulary Setting,” Proceedings of Machine Translation Summit X International Association for Machine Translation (2005): 47–54.
C. Y. Lin, “ROUGE: A Package for Automatic Evaluation of Summaries,” Text Summarization Branches Out (Association for Computational Linguistics, 2004): 74–81.
J. M. Zambrano Chaves, S. C. Huang, Y. Xu, et al., “A Clinically Accessible Small Multimodal Radiology Model and Evaluation Metric for Chest X‐ray Findings,” Nature Communications 16 (2025): 3108.

82202984 National Natural Science Foundation of China; T2541004 National Natural Science Foundation of China; 2024SSYS0026 Zhejiang Key R&D Program of China; LDT23F02023F02 Zhejiang Key R&D Program of China; KY052025003 Transvascular Implantation Devices Research Institute (TIDRI); Zhejiang Key Laboratory of Medical Imaging Artificial Intelligence

Keywords: disease diagnosis; generative artificial intelligence; multimodal learning; ocular B‐scan ultrasonography; report generation

Date Created: 20260108 Date Completed: 20260318 Latest Revision: 20260403

20260515

PMC13042833

10.1002/advs.202515864

41504332