{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T11:57:03Z","timestamp":1772884623989,"version":"3.50.1"},"reference-count":28,"publisher":"BMJ","issue":"1","license":[{"start":{"date-parts":[[2025,5,26]],"date-time":"2025-05-26T00:00:00Z","timestamp":1748217600000},"content-version":"unspecified","delay-in-days":25,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100013153","name":"Shantou Science and Technology Project","doi-asserted-by":"publisher","award":["190917155269927"],"award-info":[{"award-number":["190917155269927"]}],"id":[{"id":"10.13039\/501100013153","id-type":"DOI","asserted-by":"publisher"}]},{"name":"2020 Li Ka Shing Foundation Cross-Disciplinary Research Grant","award":["2020LKSFG06B"],"award-info":[{"award-number":["2020LKSFG06B"]}]}],"content-domain":{"domain":["bmj.com"],"crossmark-restriction":true},"short-container-title":["BMJ Open Ophth"],"accepted":{"date-parts":[[2025,5,5]]},"published-print":{"date-parts":[[2025,5]]},"abstract":"<jats:sec>\n                    <jats:title>Purpose<\/jats:title>\n                    <jats:p>To assess the application of generative adversarial networks (GANs) to restore the blurred optical coherence tomography (OCT) images caused by optical media opacity in eyes.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>In this cross-sectional study, a spectral-domain OCT (Zeiss Cirrus 5000, Germany) was used to scan the macula of 510 eyes from 272 Chinese subjects. Optical media opacity was simulated with an algorithm for training set (420 normal eyes). Images for three test sets were from the following: 56 normal eyes before and after fitting neutral density filter (NDF), 34 eyes before and after cataract surgeries and 90 eyes processed by algorithm. GANs of pix2pix was trained with training set and restored blurred images in test sets. Structural similarity index (SSIM) and peak signal-to-noise ratio (PSNR) were used to evaluate the performance of GANs.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>PSNR for test sets before and after image restoration was 18.37\u00b10.44\u2009and 19.94\u00b10.29 for NDF (p\uff1c0.01), 16.65\u00b10.99\u2009and 16.91\u00b10.26 for cataract (p=0.68) and 18.33\u00b10.55\u2009and 20.83\u00b10.41 for algorithm regenerated graph (p\uff1c0.01), respectively. SSIM for test sets before and after image restoration was 0.85\u00b10.02\u2009and 1.00\u00b10.00 for NDF (p\uff1c0.01), 0.92\u00b10.07\u2009and 0.97\u00b10.02 for cataract (p\uff1c0.01) and 0.86\u00b10.02\u2009and 0.99\u00b10.01 for algorithm regenerated graph (p\uff1c0.01), respectively.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>GANs can be used to restore blurred OCT images caused by optical media opacity in eyes. Future studies are warranted to optimise this technique before the application in clinical practice.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1136\/bmjophth-2024-001987","type":"journal-article","created":{"date-parts":[[2025,5,27]],"date-time":"2025-05-27T01:25:11Z","timestamp":1748309111000},"page":"e001987","update-policy":"https:\/\/doi.org\/10.1136\/crossmarkpolicy","source":"Crossref","is-referenced-by-count":2,"title":["Application of generative adversarial networks in the restoration of blurred optical coherence tomography images caused by optical media opacity in eyes"],"prefix":"10.1136","volume":"10","author":[{"given":"Zhengfang","family":"Wang","sequence":"first","affiliation":[{"name":"Joint Shantou International Eye Center of Shantou University and The Chinese University of Hong Kong, Shantou, China"},{"name":"Qingyuan People\u2019s Hospital, Qingyuan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuang","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Physics and Optoelectronic Engineering, Hainan University, Haikou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yeye","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Physics and Optoelectronic Engineering, Hainan University, Haikou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianwei","family":"Lin","sequence":"additional","affiliation":[{"name":"Joint Shantou International Eye Center of Shantou University and The Chinese University of Hong Kong, Shantou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinyan","family":"Lin","sequence":"additional","affiliation":[{"name":"Department of Physics, Shantou University, Shantou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ming","family":"Zhu","sequence":"additional","affiliation":[{"name":"School of Physics and Optoelectronic Engineering, Hainan University, Haikou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tsz Kin","family":"Ng","sequence":"additional","affiliation":[{"name":"Joint Shantou International Eye Center of Shantou University and The Chinese University of Hong Kong, Shantou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weifeng","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Physics and Optoelectronic Engineering, Hainan University, Haikou, China"},{"name":"Center for Theoretical Physics, Hainan University, Haikou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8476-1955","authenticated-orcid":false,"given":"Geng","family":"Wang","sequence":"additional","affiliation":[{"name":"Joint Shantou International Eye Center of Shantou University and The Chinese University of Hong Kong, Shantou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"239","published-online":{"date-parts":[[2025,5,26]]},"reference":[{"key":"2026010721204248000_10.1.e001987.1","doi-asserted-by":"publisher","DOI":"10.1001\/archopht.1995.01100030081025"},{"key":"2026010721204248000_10.1.e001987.2","doi-asserted-by":"publisher","DOI":"10.1001\/archopht.1994.01090240090031"},{"key":"2026010721204248000_10.1.e001987.3","doi-asserted-by":"publisher","DOI":"10.1364\/OL.18.001864"},{"key":"2026010721204248000_10.1.e001987.4","doi-asserted-by":"publisher","DOI":"10.1016\/S0161-6420(95)31032-9"},{"key":"2026010721204248000_10.1.e001987.5","unstructured":"Lim JS . Two-dimensional signal and image processing. 1989."},{"key":"2026010721204248000_10.1.e001987.6","unstructured":"Gonzalez RC , Woods RE . Digital image processing. Prentice Hall, 2002."},{"key":"2026010721204248000_10.1.e001987.7","doi-asserted-by":"crossref","first-page":"259","DOI":"10.1016\/0167-2789(92)90242-F","article-title":"Nonlinear total variation based noise removal algorithms","volume":"60","author":"Rudin","year":"1992","journal-title":"Physica D: Nonlinear Phenomena"},{"key":"2026010721204248000_10.1.e001987.8","unstructured":"Krizhevsky A , Sutskever I , Hinton G . ImageNet Classification with Deep Convolutional Neural Networks. 2012."},{"key":"2026010721204248000_10.1.e001987.9","doi-asserted-by":"crossref","unstructured":"BvM KC , Caglar Gulcehre DB , Fethi Bougares HS , et al . Learning phrase representations using rnn encoder\u2013decoder for statistical machine translation. Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP) EMNLP: Association for Computational Linguistics; 2014:1724.","DOI":"10.3115\/v1\/D14-1179"},{"key":"2026010721204248000_10.1.e001987.10","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"2026010721204248000_10.1.e001987.11","doi-asserted-by":"crossref","first-page":"103147","DOI":"10.1016\/j.cviu.2020.103147","article-title":"A comprehensive review of past and present image inpainting methods","volume":"203","author":"Jam","year":"2021","journal-title":"Comput Vis Image Underst"},{"key":"2026010721204248000_10.1.e001987.12","doi-asserted-by":"crossref","DOI":"10.1167\/tvst.9.2.29","article-title":"Assessment of Generative Adversarial Networks Model for Synthetic Optical Coherence Tomography Images of Retinal Disorders","volume":"9","author":"Zheng","year":"2020","journal-title":"Transl Vis Sci Technol"},{"key":"2026010721204248000_10.1.e001987.13","doi-asserted-by":"crossref","first-page":"101906","DOI":"10.1016\/j.media.2020.101906","article-title":"Improving statistical power of glaucoma clinical trials using an ensemble of cyclical generative adversarial networks","volume":"68","author":"Lazaridis","year":"2021","journal-title":"Med Image Anal"},{"key":"2026010721204248000_10.1.e001987.14","doi-asserted-by":"crossref","DOI":"10.1002\/jbio.201960135","article-title":"Optical coherence tomography image denoising using a generative adversarial network with speckle modulation","volume":"13","author":"Dong","year":"2020","journal-title":"J Biophotonics"},{"key":"2026010721204248000_10.1.e001987.15","doi-asserted-by":"crossref","first-page":"6205","DOI":"10.1364\/BOE.9.006205","article-title":"Retinal optical coherence tomography image enhancement via deep learning","volume":"9","author":"Halupka","year":"2018","journal-title":"Biomed Opt Express"},{"key":"2026010721204248000_10.1.e001987.16","doi-asserted-by":"crossref","first-page":"180","DOI":"10.1109\/TMI.2020.3024097","article-title":"SiameseGAN: A Generative Model for Denoising of Spectral Domain Optical Coherence Tomography Images","volume":"40","author":"Kande","year":"2021","journal-title":"IEEE Trans Med Imaging"},{"key":"2026010721204248000_10.1.e001987.17","doi-asserted-by":"publisher","DOI":"10.1136\/bjophthalmol-2019-315338"},{"key":"2026010721204248000_10.1.e001987.18","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":"2026010721204248000_10.1.e001987.19","doi-asserted-by":"crossref","DOI":"10.1038\/s41598-020-78696-2","article-title":"A novel deep learning conditional generative adversarial network for producing angiography images from retinal fundus photographs","volume":"10","author":"Tavakkoli","year":"2020","journal-title":"Sci Rep"},{"key":"2026010721204248000_10.1.e001987.20","doi-asserted-by":"crossref","first-page":"183","DOI":"10.1007\/s11548-019-02046-5","article-title":"Improving realism in patient-specific abdominal ultrasound simulation using CycleGANs","volume":"15","author":"Vitale","year":"2020","journal-title":"Int J Comput Assist Radiol Surg"},{"key":"2026010721204248000_10.1.e001987.21","doi-asserted-by":"publisher","DOI":"10.1167\/iovs.08-2364"},{"key":"2026010721204248000_10.1.e001987.22","doi-asserted-by":"crossref","unstructured":"Isola P , Zhu J-Y , Zhou T , et al . Image-to-image translation with conditional adversarial networks. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR); Honolulu, HI, 2017:1125\u201334. doi:10.1109\/CVPR.2017.632","DOI":"10.1109\/CVPR.2017.632"},{"key":"2026010721204248000_10.1.e001987.23","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"2026010721204248000_10.1.e001987.24","doi-asserted-by":"crossref","first-page":"3374","DOI":"10.1109\/JBHI.2020.2999077","article-title":"Dehaze of Cataractous Retinal Images Using an Unpaired Generative Adversarial Network","volume":"24","author":"Luo","year":"2020","journal-title":"IEEE J Biomed Health Inform"},{"key":"2026010721204248000_10.1.e001987.25","doi-asserted-by":"crossref","unstructured":"Fu H , Wang B , Shen J , et al . Evaluation of retinal image quality assessment networks in different color-spaces.2019:48\u201356.","DOI":"10.1007\/978-3-030-32239-7_6"},{"key":"2026010721204248000_10.1.e001987.26","doi-asserted-by":"crossref","first-page":"1775","DOI":"10.1007\/s11548-019-02040-x","article-title":"Deep learning-based digital subtraction angiography image generation","volume":"14","author":"Gao","year":"2019","journal-title":"Int J Comput Assist Radiol Surg"},{"key":"2026010721204248000_10.1.e001987.27","doi-asserted-by":"crossref","first-page":"15","DOI":"10.5120\/ijca2017913060","article-title":"Image Restoration Techniques: A Survey","volume":"160","author":"Maru","year":"2017","journal-title":"IJCA"},{"key":"2026010721204248000_10.1.e001987.28","doi-asserted-by":"crossref","DOI":"10.3390\/jimaging7120262","article-title":"Optical to Planar X-ray Mouse Image Mapping in Preclinical Nuclear Medicine Using Conditional Adversarial Networks","volume":"7","author":"Fysikopoulos","year":"2021","journal-title":"J Imaging"}],"container-title":["BMJ Open Ophthalmology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1136\/bmjophth-2024-001987","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,8]],"date-time":"2026-01-08T05:21:14Z","timestamp":1767849674000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmjophth.bmj.com\/lookup\/doi\/10.1136\/bmjophth-2024-001987"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5]]},"references-count":28,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,5,26]]},"published-print":{"date-parts":[[2025,5]]}},"alternative-id":["10.1136\/bmjophth-2024-001987"],"URL":"https:\/\/doi.org\/10.1136\/bmjophth-2024-001987","relation":{},"ISSN":["2397-3269"],"issn-type":[{"value":"2397-3269","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5]]}}}