{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,23]],"date-time":"2026-09-23T05:02:05Z","timestamp":1790139725505,"version":"4.0.1"},"reference-count":40,"publisher":"BMJ","issue":"7","license":[{"start":{"date-parts":[[2025,2,12]],"date-time":"2025-02-12T00:00:00Z","timestamp":1739318400000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100004926","name":"Canadian Medical Association","doi-asserted-by":"publisher","award":["Joule Innovation Grant"],"award-info":[{"award-number":["Joule Innovation Grant"]}],"id":[{"id":"10.13039\/501100004926","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000262","name":"Fighting Blindness Canada","doi-asserted-by":"crossref","award":["Eye on the Cure"],"award-info":[{"award-number":["Eye on the Cure"]}],"id":[{"id":"10.13039\/501100000262","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100020895","name":"Temerty Faculty of Medicine, University of Toronto","doi-asserted-by":"publisher","award":["Chisolm Memorial Scholarship"],"award-info":[{"award-number":["Chisolm Memorial Scholarship"]}],"id":[{"id":"10.13039\/501100020895","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["bmj.com"],"crossmark-restriction":true},"short-container-title":["Br J Ophthalmol"],"accepted":{"date-parts":[[2025,1,9]]},"published-print":{"date-parts":[[2025,7]]},"abstract":"<jats:sec>\n                  <jats:title>Aims<\/jats:title>\n                  <jats:p>This study aims to investigate whether denoising diffusion probabilistic models (DDPMs) could generate realistic retinal images, and if they could be used to improve the performance of a deep convolutional neural network (CNN) ensemble for multiple retinal disease classification, which was previously shown to outperform human experts.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Methods<\/jats:title>\n                  <jats:p>We trained DDPMs to generate retinal fundus images representing diabetic retinopathy, age-related macular degeneration, glaucoma or normal eyes. Eight board-certified ophthalmologists evaluated 96 test images to assess the realism of generated images and classified them based on disease labels. Subsequently, between 100 and 1000 generated images were employed to augment training of deep convolutional ensembles for classifying retinal disease. We measured the accuracy of ophthalmologists in correctly identifying real and generated images. We also measured the classification accuracy, F-score and area under the receiver operating curve of a trained CNN in classifying retinal diseases from a test set of 100 fundus images.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>Ophthalmologists exhibited a mean accuracy of 61.1% (range: 51.0%\u201368.8%) in differentiating real and generated images. Augmenting the training set with 238 generated images in the smallest class statistically significantly improved the F-score and accuracy by 5.3% and 5.8%, respectively (p&lt;0.01) in a retinal disease classification task, compared with a baseline model trained only with real images.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Conclusions<\/jats:title>\n                  <jats:p>Latent diffusion models generated highly realistic retinal images, as validated by human experts. Adding generated images to the training set improved performance of a CNN ensemble without requiring additional real patient data.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1136\/bjo-2024-326122","type":"journal-article","created":{"date-parts":[[2025,2,12]],"date-time":"2025-02-12T13:20:43Z","timestamp":1739366443000},"page":"791-798","update-policy":"https:\/\/doi.org\/10.1136\/crossmarkpolicy","source":"Crossref","is-referenced-by-count":8,"title":["Realistic fundus photograph generation for improving automated disease classification"],"prefix":"10.1136","volume":"109","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9275-590X","authenticated-orcid":false,"given":"Prashant U","family":"Pandey","sequence":"first","affiliation":[{"name":"School of Biomedical Engineering, The University of British Columbia, Vancouver, British Columbia, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jonathan A","family":"Micieli","sequence":"additional","affiliation":[{"name":"Department of Ophthalmology and Vision Sciences, University of Toronto, Toronto, Ontario, Canada"},{"name":"Kensington Vision and Research Centre and Kensington Research Institute, Toronto, Ontario, Canada"},{"name":"Department of Ophthalmology, St. Michael\u2019s Hospital, Unity Health, Toronto, Ontario, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8619-1490","authenticated-orcid":false,"given":"Stephan","family":"Ong Tone","sequence":"additional","affiliation":[{"name":"Department of Ophthalmology and Vision Sciences, University of Toronto, Toronto, Ontario, Canada"},{"name":"Kensington Vision and Research Centre and Kensington Research Institute, Toronto, Ontario, Canada"},{"name":"Department of Ophthalmology and Vision Sciences, Sunnybrook Research Institute, Toronto, Ontario, Canada"},{"name":"John and Liz Tory Eye Centre, Sunnybrook Health Sciences Centre, Toronto, Ontario, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kenneth T","family":"Eng","sequence":"additional","affiliation":[{"name":"Department of Ophthalmology and Vision Sciences, University of Toronto, Toronto, Ontario, Canada"},{"name":"John and Liz Tory Eye Centre, Sunnybrook Health Sciences Centre, Toronto, Ontario, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peter J","family":"Kertes","sequence":"additional","affiliation":[{"name":"Department of Ophthalmology and Vision Sciences, University of Toronto, Toronto, Ontario, Canada"},{"name":"Kensington Vision and Research Centre and Kensington Research Institute, Toronto, Ontario, Canada"},{"name":"John and Liz Tory Eye Centre, Sunnybrook Health Sciences Centre, Toronto, Ontario, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7980-9352","authenticated-orcid":false,"given":"Jovi C Y","family":"Wong","sequence":"additional","affiliation":[{"name":"Department of Ophthalmology and Vision Sciences, University of Toronto, Toronto, Ontario, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"239","published-online":{"date-parts":[[2025,2,12]]},"reference":[{"key":"2025071523151320000_109.7.791.1","unstructured":"Ho J , Jain A , Abbeel P . Denoising diffusion probabilistic models. In: Advances in Neural Information Processing Systems. Curran Associates, Inc, 2020: 6840\u201351. Available: https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2020\/hash\/4c5bcfec8584af0d967f1ab10179ca4b-Abstract.html"},{"key":"2025071523151320000_109.7.791.2","doi-asserted-by":"crossref","unstructured":"Rombach R , Blattmann A , Lorenz D , et al . High-resolution image synthesis with latent diffusion models. 2022:10684\u201395. Available: https:\/\/openaccess.thecvf.com\/content\/CVPR2022\/html\/Rombach_High-Resolution_Image_Synthesis_With_Latent_Diffusion_Models_CVPR_2022_paper.html","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"2025071523151320000_109.7.791.3","doi-asserted-by":"publisher","DOI":"10.1007\/s11517-024-03056-5"},{"key":"2025071523151320000_109.7.791.4","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2018.07.001"},{"key":"2025071523151320000_109.7.791.5","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2020.105761"},{"key":"2025071523151320000_109.7.791.6","doi-asserted-by":"publisher","DOI":"10.1001\/jamaophthalmol.2018.6156"},{"key":"2025071523151320000_109.7.791.7","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":"2025071523151320000_109.7.791.8","doi-asserted-by":"publisher","DOI":"10.1136\/bjophthalmol-2019-315338"},{"key":"2025071523151320000_109.7.791.9","doi-asserted-by":"publisher","DOI":"10.1038\/s41433-019-0566-0"},{"key":"2025071523151320000_109.7.791.10","doi-asserted-by":"publisher","DOI":"10.1016\/j.preteyeres.2020.100900"},{"key":"2025071523151320000_109.7.791.11","doi-asserted-by":"crossref","DOI":"10.1001\/jamanetworkopen.2021.34254","article-title":"Pivotal Evaluation of an Artificial Intelligence System for Autonomous Detection of Referrable and Vision-Threatening Diabetic Retinopathy","volume":"4","author":"Ipp","year":"2021","journal-title":"JAMA Netw Open"},{"key":"2025071523151320000_109.7.791.12","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-018-0040-6"},{"key":"2025071523151320000_109.7.791.13","doi-asserted-by":"crossref","unstructured":"Wang Z , Keane PA , Chiang M , et al . Artificial intelligence and deep learning in ophthalmology. In: Lidstr\u00f6mer N , Ashrafian H , eds. Artificial Intelligence in Medicine. Cham: Springer International Publishing, 2022: 1519\u201352. Available: https:\/\/doi.org\/10.1007\/978-3-030-64573-1_200","DOI":"10.1007\/978-3-030-64573-1_200"},{"key":"2025071523151320000_109.7.791.14","doi-asserted-by":"publisher","DOI":"10.1111\/1754-9485.13261"},{"key":"2025071523151320000_109.7.791.15","unstructured":"Ting DSW , Pasquale LR , Peng L , et al . Artificial intelligence and deep learning in ophthalmology. 2017 IEEE International Conference on Computer Vision (ICCV); 2017:2242\u201351."},{"key":"2025071523151320000_109.7.791.16","unstructured":"M\u00fcller-Franzes G , Niehues JM , Khader F , et al . Diffusion Probabilistic Models beat GANs on Medical Images. arXiv 2022. Available: http:\/\/arxiv.org\/abs\/2212.07501"},{"key":"2025071523151320000_109.7.791.17","doi-asserted-by":"crossref","DOI":"10.1038\/s41598-023-39278-0","article-title":"A multimodal comparison of latent denoising diffusion probabilistic models and generative adversarial networks for medical image synthesis","volume":"13","author":"M\u00fcller-Franzes","year":"2023","journal-title":"Sci Rep"},{"key":"2025071523151320000_109.7.791.18","unstructured":"Mirza M , Osindero S . Conditional Generative Adversarial Nets. arXiv 2014. Available: http:\/\/arxiv.org\/abs\/1411.1784"},{"key":"2025071523151320000_109.7.791.19","unstructured":"Karras T , Aittala M , Laine S , et al . Alias-free generative adversarial networks. Advances in Neural Information Processing Systems,\u00a0Curran Associates, Inc; 2021:852\u201363. Available: https:\/\/proceedings.neurips.cc\/paper\/2021\/hash\/076ccd93ad68be51f23707988e934906-Abstract.html"},{"key":"2025071523151320000_109.7.791.20","unstructured":"Karras T , Aila T , Laine S , et al . Progressive Growing of GANs for Improved Quality, Stability, and Variation. arXiv 2018. Available: http:\/\/arxiv.org\/abs\/1710.10196"},{"key":"2025071523151320000_109.7.791.21","doi-asserted-by":"publisher","DOI":"10.1136\/bjo-2022-322183"},{"key":"2025071523151320000_109.7.791.22","unstructured":"de C , Vermeer KA , Jaccard N , et al . AIROGS: Artificial Intelligence for RObust Glaucoma Screening Challenge. arXiv 2023. Available: http:\/\/arxiv.org\/abs\/2302.01738"},{"key":"2025071523151320000_109.7.791.23","doi-asserted-by":"crossref","unstructured":"Kauppi T , Kalesnykiene V , Kamarainen J-K , et al . The diaretdb1 diabetic retinopathy database and evaluation protocol. BMVC 2007 - Proceedings of the British Machine Vision Conference 2007, British Machine Vision Association; 2017:15.1\u201315.10. Available: http:\/\/www.bmva.org\/bmvc\/2007\/papers\/paper-60.html","DOI":"10.5244\/C.21.15"},{"key":"2025071523151320000_109.7.791.24","doi-asserted-by":"crossref","unstructured":"Sivaswamy J , Krishnadas SR , Datt Joshi G , et al . Drishti-GS: retinal image dataset for optic nerve head(ONH) segmentation. 2014 IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014. Institute of Electrical and Electronics Engineers Inc; 2014:53\u20136.","DOI":"10.1109\/ISBI.2014.6867807"},{"key":"2025071523151320000_109.7.791.25","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2004.825627"},{"key":"2025071523151320000_109.7.791.26","doi-asserted-by":"crossref","DOI":"10.1155\/2013\/154860","article-title":"Robust vessel segmentation in fundus images","volume":"2013","author":"Budai","year":"2013","journal-title":"Int J Biomed Imaging"},{"key":"2025071523151320000_109.7.791.27","unstructured":"Dugas E , Jorge J , Cukierski W . Diabetic retinopathy detection. Kaggle; 2015. Available: https:\/\/kaggle.com\/competitions\/diabetic-retinopathy-detection"},{"key":"2025071523151320000_109.7.791.28","doi-asserted-by":"publisher","DOI":"10.5566\/ias.1155"},{"key":"2025071523151320000_109.7.791.29","unstructured":"Zhang Z , Yin FS , Liu J , et al . ORIGA-light: an online retinal fundus image database for glaucoma analysis and research. 2010 Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC\u201910; 2010:3065\u20138."},{"key":"2025071523151320000_109.7.791.30","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2019.101570"},{"key":"2025071523151320000_109.7.791.31","unstructured":"Peking University . Ocular disease recognition. 2019. Available: https:\/\/www.kaggle.com\/andrewmvd\/ocular-disease-recognition-odir5k\/metadata"},{"key":"2025071523151320000_109.7.791.32","doi-asserted-by":"publisher","DOI":"10.1109\/42.845178"},{"key":"2025071523151320000_109.7.791.33","unstructured":"Porwal P , Pachade S , Kamble R , et al . Indian diabetic retinopathy image dataset (IDRID). IEEE dataport. 2018."},{"key":"2025071523151320000_109.7.791.34","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-021-25138-w"},{"key":"2025071523151320000_109.7.791.35","unstructured":"Heusel M , Ramsauer H , Unterthiner T , et al . GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium. arXiv 2018. Available: http:\/\/arxiv.org\/abs\/1706.08500"},{"key":"2025071523151320000_109.7.791.36","unstructured":"Salimans T , Goodfellow I , Zaremba W , et al . Improved techniques for training gans. Advances in Neural Information Processing Systems, Curran Associates, Inc; 2016 Available: https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2016\/hash\/8a3363abe792db2d8761d6403605aeb7-Abstract.html"},{"key":"2025071523151320000_109.7.791.37","doi-asserted-by":"crossref","unstructured":"Szegedy C , Vanhoucke V , Ioffe S , et al . Rethinking the inception architecture for computer vision. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, IEEE Computer Society; 2016:2818\u201326.","DOI":"10.1109\/CVPR.2016.308"},{"key":"2025071523151320000_109.7.791.38","doi-asserted-by":"publisher","DOI":"10.1001\/jamaophthalmol.2022.3375"},{"key":"2025071523151320000_109.7.791.39","doi-asserted-by":"crossref","unstructured":"Kamran SA , Fariha Hossain K , Tavakkoli A , et al . Fundus2Angio: a conditional gan architecture for generating fluorescein angiography images from retinal fundus photography. In: Bebis G , Yin Z , Kim E , et al , eds. Advances in Visual Computing. Cham: Springer International Publishing, 2020: 125\u201338.","DOI":"10.1007\/978-3-030-64559-5_10"},{"key":"2025071523151320000_109.7.791.40","doi-asserted-by":"publisher","DOI":"10.1038\/s41551-023-01049-7"}],"container-title":["British Journal of Ophthalmology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1136\/bjo-2024-326122","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,16]],"date-time":"2025-07-16T06:16:19Z","timestamp":1752646579000},"score":1,"resource":{"primary":{"URL":"https:\/\/bjo.bmj.com\/lookup\/doi\/10.1136\/bjo-2024-326122"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2,12]]},"references-count":40,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2025,6,23]]},"published-print":{"date-parts":[[2025,7]]}},"alternative-id":["10.1136\/bjo-2024-326122"],"URL":"https:\/\/doi.org\/10.1136\/bjo-2024-326122","relation":{},"ISSN":["0007-1161","1468-2079"],"issn-type":[{"value":"0007-1161","type":"print"},{"value":"1468-2079","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,2,12]]}}}