{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T02:21:29Z","timestamp":1790821289101,"version":"4.1.0"},"reference-count":35,"publisher":"BMJ","issue":"12","funder":[{"name":"Teaching Reform Research Project of Guangdong Clinical Teaching Base in 2021","award":["2021JD070"],"award-info":[{"award-number":["2021JD070"]}]}],"content-domain":{"domain":["bmj.com"],"crossmark-restriction":true},"short-container-title":["Br J Ophthalmol"],"accepted":{"date-parts":[[2025,7,1]]},"published-print":{"date-parts":[[2025,12]]},"abstract":"<jats:sec>\n                    <jats:title>Purpose<\/jats:title>\n                    <jats:p>To generate fundus photographs of multiple kinds of retinal disease, bypassing the requirement of coding technique.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>The dataset contained fundus photographs of 10 categories of retinal conditions, with 500 fundus photographs in each category. We randomly divided the collected data into a training set (80%) and a test set (20%). Google Colaboratory was used to implement Pix2Pix to generate fundus photographs for each category. We compared the diagnostic abilities of ophthalmologists on both real and synthetic images. The diagnostic performance of the classification models trained on real, synthetic and combined data sets was also compared. Furthermore, the real and synthesised images were distinguished by ophthalmologists and artificial intelligence (AI) image detection websites.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Fundus photographs of 10 categories were successfully synthesised using our method. The synthetic images showed slightly higher diagnostic accuracy by the three ophthalmologists than the real images (99.7% vs 98.7%, 98.0% vs 96.0% and 99.7% vs 94.3%; p=0.109). Training ResNet-50 and VGG-19 models with a combination of real and synthetic images resulted in significant improvements in accuracy, achieving 93.7% and 89.3%, respectively. Five residents achieved at least 92.5% accuracy in discriminating between real and synthetic images. In contrast, three AI image detection websites showed limited capability in this task, with a maximum accuracy of 51.2%.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>Pix2Pix on Google Colaboratory can efficiently produce a diverse range of fundus images with typical characters.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1136\/bjo-2024-326741","type":"journal-article","created":{"date-parts":[[2025,7,15]],"date-time":"2025-07-15T21:40:28Z","timestamp":1752615628000},"page":"1382-1387","update-policy":"https:\/\/doi.org\/10.1136\/crossmarkpolicy","source":"Crossref","is-referenced-by-count":2,"title":["Generation of multidisease fundus photographs with code-free platform"],"prefix":"10.1136","volume":"109","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-6741-6314","authenticated-orcid":false,"given":"Huiyu","family":"Liang","sequence":"first","affiliation":[{"name":"Joint Shantou International Eye Center of Shantou University and The Chinese University of Hong Kong, Shantou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1914-9695","authenticated-orcid":false,"given":"Qi","family":"Zhang","sequence":"additional","affiliation":[{"name":"Joint Shantou International Eye Center of Shantou University and The Chinese University of Hong Kong, Shantou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6415-5381","authenticated-orcid":false,"given":"Tian","family":"Lin","sequence":"additional","affiliation":[{"name":"Joint Shantou International Eye Center of Shantou University and The Chinese University of Hong Kong, Shantou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-2085-2747","authenticated-orcid":false,"given":"Chenli","family":"Hu","sequence":"additional","affiliation":[{"name":"Joint Shantou International Eye Center of Shantou University and The Chinese University of Hong Kong, Shantou, China"},{"name":"Shenzhen Eye Hospital, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-4651-6326","authenticated-orcid":false,"given":"Chaoxin","family":"Zheng","sequence":"additional","affiliation":[{"name":"Joint Shantou International Eye Center of Shantou University and The Chinese University of Hong Kong, Shantou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-2317-0545","authenticated-orcid":false,"given":"Xue","family":"Yao","sequence":"additional","affiliation":[{"name":"Joint Shantou International Eye Center of Shantou University and The Chinese University of Hong Kong, Shantou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-1616-7467","authenticated-orcid":false,"given":"Man","family":"Chen","sequence":"additional","affiliation":[{"name":"Joint Shantou International Eye Center of Shantou University and The Chinese University of Hong Kong, Shantou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-9184-2936","authenticated-orcid":false,"given":"Yifan","family":"Chen","sequence":"additional","affiliation":[{"name":"Joint Shantou International Eye Center of Shantou University and The Chinese University of Hong Kong, Shantou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6752-797X","authenticated-orcid":false,"given":"Yih Chung","family":"Tham","sequence":"additional","affiliation":[{"name":"Department of Ophthalmology, Yong Loo Lin School of Medicine, National University of Singapore, Singapore"},{"name":"Centre for Innovation and Precision Eye Health, Yong Loo Lin School of Medicine, National University of Singapore, Singapore"},{"name":"Ophthalmology and Visual Science Academic Clinical Program, Duke-NUS Medical School, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0676-4610","authenticated-orcid":false,"given":"Haoyu","family":"Chen","sequence":"additional","affiliation":[{"name":"Joint Shantou International Eye Center of Shantou University and The Chinese University of Hong Kong, Shantou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"239","published-online":{"date-parts":[[2025,7,15]]},"reference":[{"key":"2025112002101384000_109.12.1382.1","doi-asserted-by":"publisher","DOI":"10.1001\/jamaophthalmol.2018.6156"},{"key":"2025112002101384000_109.12.1382.2","doi-asserted-by":"crossref","first-page":"6","DOI":"10.1186\/s40662-022-00277-3","article-title":"Application of generative adversarial networks (GAN) for ophthalmology image domains: a survey","volume":"9","author":"You","year":"2022","journal-title":"Eye and Vis"},{"key":"2025112002101384000_109.12.1382.3","doi-asserted-by":"crossref","first-page":"2211","DOI":"10.1109\/TMI.2019.2903434","article-title":"Retinal Image Synthesis and Semi-Supervised Learning for Glaucoma Assessment","volume":"38","author":"Diaz-Pinto","year":"2019","journal-title":"IEEE Trans Med Imaging"},{"key":"2025112002101384000_109.12.1382.4","doi-asserted-by":"crossref","first-page":"574","DOI":"10.1109\/TASE.2020.2981637","article-title":"Diabetic Retinopathy Diagnosis Using Multichannel Generative Adversarial Network With Semisupervision","volume":"18","author":"Wang","year":"2021","journal-title":"IEEE Trans Automat Sci Eng"},{"key":"2025112002101384000_109.12.1382.5","doi-asserted-by":"publisher","DOI":"10.1364\/BOE.477906"},{"key":"2025112002101384000_109.12.1382.6","doi-asserted-by":"crossref","DOI":"10.3389\/fmed.2023.1184892","article-title":"Synthetic artificial intelligence using generative adversarial network for retinal imaging in detection of age-related macular degeneration","volume":"10","author":"Wang","year":"2023","journal-title":"Front Med (Lausanne)"},{"key":"2025112002101384000_109.12.1382.7","doi-asserted-by":"crossref","DOI":"10.1155\/2021\/3812865","article-title":"RF-GANs: A Method to Synthesize Retinal Fundus Images Based on Generative Adversarial Network","volume":"2021","author":"Chen","year":"2021","journal-title":"Comput Intell Neurosci"},{"key":"2025112002101384000_109.12.1382.8","doi-asserted-by":"crossref","DOI":"10.1016\/j.xops.2021.100079","article-title":"Deepfakes in Ophthalmology: Applications and Realism of Synthetic Retinal Images from Generative Adversarial Networks","volume":"1","author":"Chen","year":"2021","journal-title":"Ophthalmol Sci"},{"key":"2025112002101384000_109.12.1382.9","doi-asserted-by":"crossref","first-page":"17307","DOI":"10.1038\/s41598-022-20698-3","article-title":"Synthesizing realistic high-resolution retina image by style-based generative adversarial network and its utilization","volume":"12","author":"Kim","year":"2022","journal-title":"Sci Rep"},{"key":"2025112002101384000_109.12.1382.10","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1109\/JBHI.2020.3045475","article-title":"DR-GAN: Conditional Generative Adversarial Network for Fine-Grained Lesion Synthesis on Diabetic Retinopathy Images","volume":"26","author":"Zhou","year":"2022","journal-title":"IEEE J Biomed Health Inform"},{"key":"2025112002101384000_109.12.1382.11","doi-asserted-by":"crossref","first-page":"1029","DOI":"10.1001\/jamaophthalmol.2023.4508","article-title":"Clinician-Driven AI: Code-Free Self-Training on Public Data for Diabetic Retinopathy Referral","volume":"141","author":"Korot","year":"2023","journal-title":"JAMA Ophthalmol"},{"key":"2025112002101384000_109.12.1382.12","doi-asserted-by":"crossref","DOI":"10.3390\/diagnostics13101664","article-title":"Identifying the Key Components in ResNet-50 for Diabetic Retinopathy Grading from Fundus Images: A Systematic Investigation","volume":"13","author":"Huang","year":"2023","journal-title":"Diagnostics (Basel)"},{"key":"2025112002101384000_109.12.1382.13","doi-asserted-by":"crossref","DOI":"10.1088\/1742-6596\/1518\/1\/012041","article-title":"Application of a Novel and Improved VGG-19 Network in the Detection of Workers Wearing Masks","volume":"1518","author":"Xiao","year":"2020","journal-title":"J Phys Conf Ser"},{"key":"2025112002101384000_109.12.1382.14","doi-asserted-by":"crossref","first-page":"401","DOI":"10.1007\/s11517-021-02321-1","article-title":"Feasibility study to improve deep learning in OCT diagnosis of rare retinal diseases with few-shot classification","volume":"59","author":"Yoo","year":"2021","journal-title":"Med Biol Eng Comput"},{"key":"2025112002101384000_109.12.1382.15","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2018.07.001"},{"key":"2025112002101384000_109.12.1382.16","doi-asserted-by":"crossref","first-page":"781","DOI":"10.1109\/TMI.2017.2759102","article-title":"End-to-End Adversarial Retinal Image Synthesis","volume":"37","author":"Costa","year":"2018","journal-title":"IEEE Trans Med Imaging"},{"key":"2025112002101384000_109.12.1382.17","doi-asserted-by":"crossref","first-page":"1093","DOI":"10.1609\/aaai.v33i01.33011093","article-title":"Pathological Evidence Exploration in Deep Retinal Image Diagnosis","volume":"33","author":"Niu","year":"2019","journal-title":"AAAI"},{"key":"2025112002101384000_109.12.1382.18","first-page":"60","article-title":"A Two-Stage GAN for High-Resolution Retinal Image Generation and Segmentation","volume":"11","author":"Andreini","year":"2022","journal-title":"Electronics (Basel)"},{"key":"2025112002101384000_109.12.1382.19","first-page":"2185","article-title":"Fundus GAN - GAN-based Fundus Image Synthesis for Training Retinal Image Classifiers","volume":"2022","author":"Shenkut","year":"2022","journal-title":"Annu Int Conf IEEE Eng Med Biol Soc"},{"key":"2025112002101384000_109.12.1382.20","doi-asserted-by":"crossref","first-page":"105878","DOI":"10.1016\/j.compbiomed.2022.105878","article-title":"LEGAN: A Light and Effective Generative Adversarial Network for medical image synthesis","volume":"148","author":"Gao","year":"2022","journal-title":"Comput Biol Med"},{"key":"2025112002101384000_109.12.1382.21","first-page":"661","article-title":"k-SALSA: k-anonymous synthetic averaging of retinal images via local style alignment","volume":"13681","author":"Jeon","year":"2022","journal-title":"Comput Vis ECCV"},{"key":"2025112002101384000_109.12.1382.22","doi-asserted-by":"crossref","first-page":"2815","DOI":"10.1016\/j.bpj.2024.02.019","article-title":"VSG-GAN: A high-fidelity image synthesis method with semantic manipulation in retinal fundus image","volume":"123","author":"Liu","year":"2024","journal-title":"Biophys J"},{"key":"2025112002101384000_109.12.1382.23","doi-asserted-by":"crossref","first-page":"13","DOI":"10.1167\/tvst.10.2.13","article-title":"Addressing Artificial Intelligence Bias in Retinal Diagnostics","volume":"10","author":"Burlina","year":"2021","journal-title":"Transl Vis Sci Technol"},{"key":"2025112002101384000_109.12.1382.24","doi-asserted-by":"crossref","first-page":"62","DOI":"10.1186\/s12938-019-0682-x","article-title":"Retinal image synthesis from multiple-landmarks input with generative adversarial networks","volume":"18","author":"Yu","year":"2019","journal-title":"Biomed Eng Online"},{"key":"2025112002101384000_109.12.1382.25","doi-asserted-by":"crossref","first-page":"90","DOI":"10.1109\/JBHI.2021.3085770","article-title":"Unsupervised Domain Adaptation Based Image Synthesis and Feature Alignment for Joint Optic Disc and Cup Segmentation","volume":"26","author":"Lei","year":"2022","journal-title":"IEEE J Biomed Health Inform"},{"key":"2025112002101384000_109.12.1382.26","doi-asserted-by":"crossref","DOI":"10.1167\/tvst.13.6.1","article-title":"Assessing the Efficacy of Synthetic Optic Disc Images for Detecting Glaucomatous Optic Neuropathy Using Deep Learning","volume":"13","author":"Chaurasia","year":"2024","journal-title":"Transl Vis Sci Technol"},{"key":"2025112002101384000_109.12.1382.27","unstructured":"Beers A , Brown J , Chang K , et al . High-resolution medical image synthesis using progressively grown generative adversarial networks. arXiv 2018."},{"key":"2025112002101384000_109.12.1382.28","first-page":"329","article-title":"Diagnosability of Synthetic Retinal Fundus Images for Plus Disease Detection in Retinopathy of Prematurity","volume":"2020","author":"Coyner","year":"2020","journal-title":"AMIA Annu Symp Proc"},{"key":"2025112002101384000_109.12.1382.29","doi-asserted-by":"crossref","DOI":"10.1016\/j.xops.2022.100126","article-title":"Synthetic Medical Images for Robust, Privacy-Preserving Training of Artificial Intelligence: Application to Retinopathy of Prematurity Diagnosis","volume":"2","author":"Coyner","year":"2022","journal-title":"Ophthalmol Sci"},{"key":"2025112002101384000_109.12.1382.30","doi-asserted-by":"crossref","unstructured":"Hou N , Shi J , Ding X , et al . ROP-GAN: an image synthesis method for retinopathy of prematurity based on generative adversarial network. Phys Med Biol 2023;68. doi:10.1088\/1361-6560\/acf3c9","DOI":"10.1088\/1361-6560\/acf3c9"},{"key":"2025112002101384000_109.12.1382.31","doi-asserted-by":"crossref","first-page":"25","DOI":"10.1186\/s12911-024-02431-4","article-title":"Development of a generative deep learning model to improve epiretinal membrane detection in fundus photography","volume":"24","author":"Choi","year":"2024","journal-title":"BMC Med Inform Decis Mak"},{"key":"2025112002101384000_109.12.1382.32","doi-asserted-by":"publisher","DOI":"10.1111\/ijcp.12627"},{"key":"2025112002101384000_109.12.1382.33","doi-asserted-by":"crossref","DOI":"10.1167\/tvst.11.2.22","article-title":"Simple Code Implementation for Deep Learning-Based Segmentation to Evaluate Central Serous Chorioretinopathy in Fundus Photography","volume":"11","author":"Yoo","year":"2022","journal-title":"Transl Vis Sci Technol"},{"key":"2025112002101384000_109.12.1382.34","doi-asserted-by":"crossref","first-page":"10395","DOI":"10.1038\/s41598-024-60807-y","article-title":"Automated machine learning model for fundus image classification by health-care professionals with no coding experience","volume":"14","author":"Zago Ribeiro","year":"2024","journal-title":"Sci Rep"},{"key":"2025112002101384000_109.12.1382.35","doi-asserted-by":"crossref","first-page":"421","DOI":"10.36644\/mlr.116.3.regulating","article-title":"Regulating Black-Box Medicine","volume":"116","author":"Price","year":"2017","journal-title":"Mich Law Rev"}],"container-title":["British Journal of Ophthalmology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1136\/bjo-2024-326741","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,14]],"date-time":"2025-12-14T09:23:39Z","timestamp":1765704219000},"score":1,"resource":{"primary":{"URL":"https:\/\/bjo.bmj.com\/lookup\/doi\/10.1136\/bjo-2024-326741"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,15]]},"references-count":35,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2025,11,20]]},"published-print":{"date-parts":[[2025,12]]}},"alternative-id":["10.1136\/bjo-2024-326741"],"URL":"https:\/\/doi.org\/10.1136\/bjo-2024-326741","relation":{},"ISSN":["0007-1161","1468-2079"],"issn-type":[{"value":"0007-1161","type":"print"},{"value":"1468-2079","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7,15]]}}}