{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T01:13:36Z","timestamp":1790730816075,"version":"4.1.0"},"reference-count":30,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,11,28]],"date-time":"2025-11-28T00:00:00Z","timestamp":1764288000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,11,28]],"date-time":"2025-11-28T00:00:00Z","timestamp":1764288000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Text-to-image (T2I) artificial intelligence models are being increasingly explored in medical education, yet their utility in ophthalmology remains unclear. Slit-lamp anterior segment photography, as a cornerstone of ophthalmic training, provides an ideal context for evaluation. We assessed 40 cases of anterior segment disease. The text descriptions were generated using GPT-4o, and the corresponding images were synthesized via Sora Turbo. Readability was analysed with the Flesch Reading Ease (FRE), Flesch\u2012Kincaid Grade Level (FKGL), and Gunning Fog Scale (GFS). Twenty ophthalmologists (10 juniors, 10 seniors) rated image-text pairs across five dimensions\u2014text accuracy, image reliability, recognizability, educational value, and generation stability\u2014using a 5-point Likert scale. Entities with distinct morphological features, such as cataracts and subconjunctival haemorrhages, received the highest total scores, whereas those with entropion and corneal foreign bodies scored the lowest. Readability analysis indicated advanced text complexity. Senior ophthalmologists consistently provided lower ratings than junior clinicians did, highlighting expertise-related differences in perceived educational value. Sora Turbo can generate clinically useful anterior segment images for educational purposes, particularly for pathologies with prominent morphological features. This first systematic evaluation in ophthalmology demonstrates the promise of AI-generated atlases as scalable teaching resources for early-stage trainees while emphasizing the need for expert validation and ethical oversight before integration into formal curricula.<\/jats:p>","DOI":"10.1038\/s41598-025-27020-x","type":"journal-article","created":{"date-parts":[[2025,11,28]],"date-time":"2025-11-28T10:57:09Z","timestamp":1764327429000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["Assessing the quality and educational applicability of AI-generated anterior segment images in ophthalmology"],"prefix":"10.1038","volume":"15","author":[{"given":"Yizhou","family":"Yang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lifang","family":"Bai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuecheng","family":"Ren","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuanqiao","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,11,28]]},"reference":[{"issue":"1","key":"27020_CR1","doi-asserted-by":"publisher","first-page":"63","DOI":"10.2967\/jnmt.124.268402","volume":"53","author":"G Currie","year":"2025","unstructured":"Currie, G., Hewis, J., Hawk, E., Kiat, H. & Rohren, E. Fitness for purpose of text-to-image generative artificial intelligence image creation in medical imaging. J. Nucl. Med. Technol. 53(1), 63\u201367. https:\/\/doi.org\/10.2967\/jnmt.124.268402 (2025).","journal-title":"J. Nucl. Med. Technol."},{"issue":"1","key":"27020_CR2","doi-asserted-by":"publisher","first-page":"72","DOI":"10.2967\/jnmt.124.268323","volume":"53","author":"GM Currie","year":"2025","unstructured":"Currie, G. M. Generative artificial intelligence in nuclear medicine education. J. Nucl. Med. Technol. 53(1), 72\u201379. https:\/\/doi.org\/10.2967\/jnmt.124.268323 (2025).","journal-title":"J. Nucl. Med. Technol."},{"issue":"6","key":"27020_CR3","doi-asserted-by":"publisher","first-page":"3139","DOI":"10.1007\/s11845-023-03315-8","volume":"192","author":"E Waisberg","year":"2023","unstructured":"Waisberg, E. et al. Text-to-image artificial intelligence to aid clinicians in perceiving unique neuro-ophthalmic visual phenomena. Ir. J. Med. Sci. 192(6), 3139\u20133142. https:\/\/doi.org\/10.1007\/s11845-023-03315-8 (2023).","journal-title":"Ir. J. Med. Sci."},{"issue":"1","key":"27020_CR4","doi-asserted-by":"publisher","first-page":"e75","DOI":"10.1016\/j.jcjo.2023.09.006","volume":"59","author":"M Balas","year":"2024","unstructured":"Balas, M., Micieli, J. A., Wulc, A. & Ing, E. B. Text-to-image artificial intelligence models for preoperative counselling in oculoplastics. Can. J. Ophthalmol. J. Can. D\u2019ophtalmol. 59(1), e75\u2013e76. https:\/\/doi.org\/10.1016\/j.jcjo.2023.09.006 (2024).","journal-title":"Can. J. Ophthalmol. J. Can. D\u2019ophtalmol."},{"key":"27020_CR5","doi-asserted-by":"publisher","DOI":"10.3390\/jcm14072136","author":"SA Haider","year":"2025","unstructured":"Haider, S. A. et al. A validity analysis of text-to-image generative artificial intelligence models for craniofacial anatomy illustration. J. Clin. Med. https:\/\/doi.org\/10.3390\/jcm14072136 (2025).","journal-title":"J. Clin. Med."},{"issue":"11","key":"27020_CR6","doi-asserted-by":"publisher","DOI":"10.7759\/cureus.74193","volume":"16","author":"P Muhr","year":"2024","unstructured":"Muhr, P. et al. Evaluating text-to-image generated photorealistic images of human anatomy. Cureus 16(11), e74193. https:\/\/doi.org\/10.7759\/cureus.74193 (2024).","journal-title":"Cureus"},{"issue":"1","key":"27020_CR7","doi-asserted-by":"publisher","first-page":"54","DOI":"10.1007\/s10916-024-02072-0","volume":"48","author":"MH Temsah","year":"2024","unstructured":"Temsah, M. H. et al. Art or artifact: evaluating the accuracy, appeal, and educational value of AI-generated imagery in DALL\u00b7E 3 for illustrating congenital heart diseases. J. Med. Syst. 48(1), 54. https:\/\/doi.org\/10.1007\/s10916-024-02072-0 (2024).","journal-title":"J. Med. Syst."},{"issue":"1","key":"27020_CR8","doi-asserted-by":"publisher","DOI":"10.7759\/cureus.77593","volume":"17","author":"MH Temsah","year":"2025","unstructured":"Temsah, M. H. et al. OpenAI\u2019s Sora and Google\u2019s Veo 2 in action: A narrative review of artificial intelligence-driven video generation models transforming healthcare. Cureus 17(1), e77593. https:\/\/doi.org\/10.7759\/cureus.77593 (2025).","journal-title":"Cureus"},{"key":"27020_CR9","doi-asserted-by":"publisher","first-page":"1211","DOI":"10.12688\/f1000research.73249.2","volume":"10","author":"H Mahjoub","year":"2023","unstructured":"Mahjoub, H., Vasavda, C., Bertram, A., Davison, A. & Sozio, S. The perceived impact of the COVID-19 pandemic on medical students\u2019 future careers. F1000Research 10, 1211. https:\/\/doi.org\/10.12688\/f1000research.73249.2 (2023).","journal-title":"F1000Research"},{"issue":"2","key":"27020_CR10","doi-asserted-by":"publisher","first-page":"167","DOI":"10.1136\/bjophthalmol-2018-313173","volume":"103","author":"DSW Ting","year":"2019","unstructured":"Ting, D. S. W. et al. Artificial intelligence and deep learning in ophthalmology. Br. J. Ophthalmol. 103(2), 167\u2013175. https:\/\/doi.org\/10.1136\/bjophthalmol-2018-313173 (2019).","journal-title":"Br. J. Ophthalmol."},{"issue":"6","key":"27020_CR11","doi-asserted-by":"publisher","first-page":"1051","DOI":"10.1016\/j.survophthal.2021.03.005","volume":"66","author":"AN Buffenn","year":"2021","unstructured":"Buffenn, A. N. The impact of strabismus on psychosocial health and quality of life: a systematic review. Surv. Ophthalmol. 66(6), 1051\u20131064. https:\/\/doi.org\/10.1016\/j.survophthal.2021.03.005 (2021).","journal-title":"Surv. Ophthalmol."},{"issue":"5","key":"27020_CR12","doi-asserted-by":"publisher","first-page":"325","DOI":"10.3928\/01913913-20240409-01","volume":"61","author":"L Do\u011fan","year":"2024","unstructured":"Do\u011fan, L., \u00d6z\u00e7akmakc\u0131, G. B. & Y\u0131lmaz, \u012cE. The performance of chatbots and the AAPOS website as a tool for amblyopia education. J. Pediatr. Ophthalmol. Strabismus 61(5), 325\u2013331. https:\/\/doi.org\/10.3928\/01913913-20240409-01 (2024).","journal-title":"J. Pediatr. Ophthalmol. Strabismus"},{"issue":"4","key":"27020_CR13","doi-asserted-by":"publisher","first-page":"1181","DOI":"10.1007\/s11999-014-4071-2","volume":"473","author":"AE Eltorai","year":"2015","unstructured":"Eltorai, A. E., Sharma, P., Wang, J. & Daniels, A. H. Most American Academy of Orthopaedic Surgeons\u2019 online patient education material exceeds average patient reading level. Clin. Orthop. Relat. Res. 473(4), 1181\u20131186. https:\/\/doi.org\/10.1007\/s11999-014-4071-2 (2015).","journal-title":"Clin. Orthop. Relat. Res."},{"issue":"5","key":"27020_CR14","doi-asserted-by":"publisher","first-page":"503","DOI":"10.1016\/j.sapharm.2012.05.009","volume":"9","author":"LW Wang","year":"2013","unstructured":"Wang, L. W., Miller, M. J., Schmitt, M. R. & Wen, F. K. Assessing readability formula differences with written health information materials: application, results, and recommendations. Res. Soc. Adm. Pharm. RSAP. 9(5), 503\u2013516. https:\/\/doi.org\/10.1016\/j.sapharm.2012.05.009 (2013).","journal-title":"Res. Soc. Adm. Pharm. RSAP."},{"issue":"6","key":"27020_CR15","doi-asserted-by":"publisher","first-page":"712","DOI":"10.1002\/ca.70002","volume":"38","author":"M Eldesoqui","year":"2025","unstructured":"Eldesoqui, M. et al. Assessing the anatomical accuracy of AI-generated medical illustrations: A comparative study of text-to-image generator tools in anatomy education. Clin. Anat. 38(6), 712\u2013717. https:\/\/doi.org\/10.1002\/ca.70002 (2025).","journal-title":"Clin. Anat."},{"issue":"2","key":"27020_CR16","doi-asserted-by":"publisher","first-page":"44","DOI":"10.1080\/17453054.2025.2504491","volume":"48","author":"JS Bae","year":"2025","unstructured":"Bae, J. S., Kim, G. Y., Kim, H. J., Han, S. H. & Youn, K. H. Comparison of anatomy image generation capability in AI image generation models. J. Vis. Commun. Med. 48(2), 44\u201351. https:\/\/doi.org\/10.1080\/17453054.2025.2504491 (2025).","journal-title":"J. Vis. Commun. Med."},{"key":"27020_CR17","doi-asserted-by":"publisher","unstructured":"Joerg, L. et al. AI-generated dermatologic images show deficient skin tone diversity and poor diagnostic accuracy: An experimental study. J. Eur. Acad. Dermatol. Venereol. https:\/\/doi.org\/10.1111\/jdv.20849(2025).","DOI":"10.1111\/jdv.20849("},{"issue":"1","key":"27020_CR18","doi-asserted-by":"publisher","first-page":"186","DOI":"10.1186\/s13244-023-01508-4","volume":"14","author":"EIS Hofmeijer","year":"2023","unstructured":"Hofmeijer, E. I. S. et al. Artificial CT images can enhance variation of case images in diagnostic radiology skills training. Insights Imag. 14(1), 186. https:\/\/doi.org\/10.1186\/s13244-023-01508-4 (2023).","journal-title":"Insights Imag."},{"issue":"12","key":"27020_CR19","doi-asserted-by":"publisher","first-page":"1610","DOI":"10.1001\/jamaophthalmol.2013.5521","volume":"131","author":"MR Edmunds","year":"2013","unstructured":"Edmunds, M. R., Barry, R. J. & Denniston, A. K. Readability assessment of online ophthalmic patient information. JAMA Ophthalmol. 131(12), 1610\u20131616. https:\/\/doi.org\/10.1001\/jamaophthalmol.2013.5521 (2013).","journal-title":"JAMA Ophthalmol."},{"issue":"5","key":"27020_CR20","doi-asserted-by":"publisher","DOI":"10.1117\/1.Jmi.7.5.051203","volume":"7","author":"TT Bruny\u00e9","year":"2020","unstructured":"Bruny\u00e9, T. T. et al. Eye tracking reveals expertise-related differences in the time-course of medical image inspection and diagnosis. J. Med. Imag. (Bellingham) 7(5), 051203. https:\/\/doi.org\/10.1117\/1.Jmi.7.5.051203 (2020).","journal-title":"J. Med. Imag. (Bellingham)"},{"key":"27020_CR21","doi-asserted-by":"publisher","first-page":"226","DOI":"10.1198\/108571105X46642","volume":"10","author":"P Legendre","year":"2005","unstructured":"Legendre, P. Species associations: the Kendall coefficient of concordance revisited. J. Agric. Biol. Environ. Stat. 10, 226\u2013245 (2005).","journal-title":"J. Agric. Biol. Environ. Stat."},{"issue":"11","key":"27020_CR22","doi-asserted-by":"publisher","first-page":"11363","DOI":"10.7759\/cureus.11363","volume":"12","author":"A Vergis","year":"2020","unstructured":"Vergis, A., Leung, C. & Roberston, R. Rater training in medical education: A scoping review. Cureus 12(11), 11363. https:\/\/doi.org\/10.7759\/cureus.11363 (2020).","journal-title":"Cureus"},{"issue":"3","key":"27020_CR23","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.232471","volume":"312","author":"LR Koetzier","year":"2024","unstructured":"Koetzier, L. R. et al. Generating synthetic data for medical imaging. Radiology 312(3), e232471. https:\/\/doi.org\/10.1148\/radiol.232471 (2024).","journal-title":"Radiology"},{"issue":"1150","key":"27020_CR24","doi-asserted-by":"publisher","first-page":"20230023","DOI":"10.1259\/bjr.20230023","volume":"96","author":"JW Gichoya","year":"2023","unstructured":"Gichoya, J. W. et al. AI pitfalls and what not to do: mitigating bias in AI. Br J Radiol. 96(1150), 20230023. https:\/\/doi.org\/10.1259\/bjr.20230023 (2023).","journal-title":"Br J Radiol."},{"issue":"3","key":"27020_CR25","doi-asserted-by":"publisher","DOI":"10.7759\/cureus.80852","volume":"17","author":"A Sriram","year":"2025","unstructured":"Sriram, A., Ramachandran, K. & Krishnamoorthy, S. Artificial intelligence in medical education: transforming learning and practice. Cureus 17(3), e80852. https:\/\/doi.org\/10.7759\/cureus.80852 (2025).","journal-title":"Cureus"},{"key":"27020_CR26","doi-asserted-by":"publisher","DOI":"10.3390\/bioengineering11040337","author":"S Maleki Varnosfaderani","year":"2024","unstructured":"Maleki Varnosfaderani, S. & Forouzanfar, M. The role of AI in hospitals and clinics: transforming healthcare in the 21st century. Bioengineering (Basel) https:\/\/doi.org\/10.3390\/bioengineering11040337 (2024).","journal-title":"Bioengineering (Basel)"},{"issue":"3","key":"27020_CR27","doi-asserted-by":"publisher","first-page":"2103","DOI":"10.1007\/s43681-024-00531-5","volume":"5","author":"F Friedrich","year":"2025","unstructured":"Friedrich, F. et al. Auditing and instructing text-to-image generation models on fairness. AI Ethics. 5(3), 2103\u20132123. https:\/\/doi.org\/10.1007\/s43681-024-00531-5 (2025).","journal-title":"AI Ethics."},{"issue":"5","key":"27020_CR28","doi-asserted-by":"publisher","first-page":"e542","DOI":"10.5001\/omj.2023.129","volume":"38","author":"M Kashoub","year":"2023","unstructured":"Kashoub, M. et al. Artificial Intelligence in Medicine: A double-edged sword or a Pandora\u2019s box?. Oman Med. J. 38(5), e542. https:\/\/doi.org\/10.5001\/omj.2023.129 (2023).","journal-title":"Oman Med. J."},{"key":"27020_CR29","unstructured":"Morrison K, Mathur A, Bradshaw A, et al. A Human-centered approach to identifying promises, risks, & challenges of text-to-image generative AI in radiology. ArXiv. 2025;abs\/2507.16207."},{"key":"27020_CR30","unstructured":"Jin, W., Sinha, A., Abhishek, K. & Hamarneh, G. Ethical medical image synthesis. ArXiv. 2025;abs\/2508.09293."}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-27020-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-27020-x","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-27020-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,28]],"date-time":"2025-11-28T10:57:10Z","timestamp":1764327430000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-27020-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,28]]},"references-count":30,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["27020"],"URL":"https:\/\/doi.org\/10.1038\/s41598-025-27020-x","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,28]]},"assertion":[{"value":"12 October 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"31 October 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 November 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}},{"value":"This study involved no human participants or patient data and used publicly accessible AI tools. The institutional review board determined that ethics review and informed consent were not required.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}},{"value":"All the authors have read and approved the final version of this manuscript to be published. We affirm that the content of this manuscript has not been published elsewhere and is not under consideration for publication elsewhere.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}}],"article-number":"42778"}}