{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T00:40:10Z","timestamp":1783125610690,"version":"3.54.6"},"reference-count":31,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2022,10,6]],"date-time":"2022-10-06T00:00:00Z","timestamp":1665014400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100011912","name":"Taipei Veterans General Hospital","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100011912","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Med."],"abstract":"<jats:sec><jats:title>Purpose<\/jats:title><jats:p>Diabetic macular edema (DME) is one of the leading causes of visual impairment in diabetic retinopathy (DR). Physicians rely on optical coherence tomography (OCT) and baseline visual acuity (VA) to tailor therapeutic regimen. However, best-corrected visual acuity (BCVA) from chart-based examinations may not wholly reflect DME status. Chart-based examinations are subjected findings dependent on the patient\u2019s recognition functions and are often confounded by concurrent corneal, lens, retinal, optic nerve, or extraocular disorders. The ability to infer VA from objective optical coherence tomography (OCT) images provides the predicted VA from objective macular structures directly and a better understanding of diabetic macular health. Deviations from chart-based and artificial intelligence (AI) image-based VA will prompt physicians to assess other ocular abnormalities affecting the patients VA and whether pursuing anti-VEGF treatment will likely yield increment in VA.<\/jats:p><\/jats:sec><jats:sec><jats:title>Materials and methods<\/jats:title><jats:p>We enrolled a retrospective cohort of 251 DME patients from Big Data Center (BDC) of Taipei Veteran General Hospital (TVGH) from February 2011 and August 2019. A total of 3,920 OCT images, labeled as \u201cvisually impaired\u201d or \u201cadequate\u201d according to baseline VA, were grouped into training (2,826), validation (779), and testing cohort (315). We applied confusion matrix and receiver operating characteristic (ROC) curve to evaluate the performance.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>We developed an OCT-based convolutional neuronal network (CNN) model that could classify two VA classes by the threshold of 0.50 (decimal notation) with an accuracy of 75.9%, a sensitivity of 78.9%, and an area under the ROC curve of 80.1% on the testing cohort.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusion<\/jats:title><jats:p>This study demonstrated the feasibility of inferring VA from routine objective retinal images.<\/jats:p><\/jats:sec><jats:sec><jats:title>Translational relevance<\/jats:title><jats:p>Serves as a pilot study to encourage further use of deep learning in deriving functional outcomes and secondary surrogate endpoints for retinal diseases.<\/jats:p><\/jats:sec>","DOI":"10.3389\/fmed.2022.1008950","type":"journal-article","created":{"date-parts":[[2022,10,6]],"date-time":"2022-10-06T12:33:18Z","timestamp":1665059598000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":15,"title":["Deep learning to infer visual acuity from optical coherence tomography in diabetic macular edema"],"prefix":"10.3389","volume":"9","author":[{"given":"Ting-Yi","family":"Lin","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hung-Ruei","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hsin-Yi","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu-Ier","family":"Hsiao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zih-Kai","family":"Kao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kao-Jung","family":"Chang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tai-Chi","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chang-Hao","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chung-Lan","family":"Kao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Po-Yin","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shih-En","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chih-Chien","family":"Hsu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu-Bai","family":"Chou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ying-Chun","family":"Jheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shih-Jen","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shih-Hwa","family":"Chiou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"De-Kuang","family":"Hwang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2022,10,6]]},"reference":[{"key":"B1","first-page":"786","article-title":"ETDRS report number 10. Early treatment diabetic retinopathy study research group.","volume":"98","year":"1991","journal-title":"Ophthalmology."},{"key":"B2","doi-asserted-by":"crossref","first-page":"2013","DOI":"10.1016\/j.ophtha.2013.02.034","article-title":"Long-term outcomes of ranibizumab therapy for diabetic macular edema: the 36-month results from two phase III trials: RISE and RIDE.","volume":"120","author":"Brown","year":"2013","journal-title":"Ophthalmology."},{"key":"B3","doi-asserted-by":"crossref","first-page":"2376","DOI":"10.1016\/j.ophtha.2016.07.032","article-title":"Intravitreal aflibercept for diabetic macular edema: 148-week results from the VISTA and VIVID studies.","volume":"123","author":"Heier","year":"2016","journal-title":"Ophthalmology."},{"key":"B4","doi-asserted-by":"crossref","first-page":"1402","DOI":"10.1016\/j.ophtha.2015.02.006","article-title":"The REVEAL study: ranibizumab monotherapy or combined with laser versus laser monotherapy in Asian patients with diabetic macular edema.","volume":"122","author":"Ishibashi","year":"2015","journal-title":"Ophthalmology."},{"key":"B5","doi-asserted-by":"crossref","first-page":"1045","DOI":"10.1016\/j.ophtha.2013.11.041","article-title":"Three-year outcomes of individualized ranibizumab treatment in patients with diabetic macular edema: the RESTORE extension study.","volume":"121","author":"Schmidt-Erfurth","year":"2014","journal-title":"Ophthalmology."},{"key":"B6","doi-asserted-by":"crossref","first-page":"2312","DOI":"10.1016\/j.ophtha.2012.08.022","article-title":"Intravitreal ranibizumab for diabetic macular edema with prompt versus deferred laser treatment: three-year randomized trial results.","volume":"119","author":"Elman","year":"2012","journal-title":"Ophthalmology."},{"key":"B7","doi-asserted-by":"crossref","first-page":"375","DOI":"10.1016\/j.ophtha.2014.08.047","article-title":"Intravitreal ranibizumab for diabetic macular edema with prompt versus deferred laser treatment: 5-year randomized trial results.","volume":"122","author":"Elman","year":"2015","journal-title":"Ophthalmology."},{"key":"B8","doi-asserted-by":"crossref","first-page":"549","DOI":"10.1016\/j.ophtha.2017.10.031","article-title":"Fully automated detection and quantification of macular fluid in OCT using deep learning.","volume":"125","author":"Schlegl","year":"2018","journal-title":"Ophthalmology."},{"key":"B9","doi-asserted-by":"crossref","first-page":"1215","DOI":"10.1001\/jamaophthalmol.2018.3848","article-title":"Correlation of central retinal thickness and visual acuity in diabetic macular edema.","volume":"136","author":"Deak","year":"2018","journal-title":"JAMA Ophthalmol."},{"key":"B10","doi-asserted-by":"crossref","first-page":"267","DOI":"10.1016\/j.ophtha.2017.08.031","article-title":"OCT biomarkers as functional outcome predictors in diabetic macular edema treated with dexamethasone implant.","volume":"125","author":"Zur","year":"2018","journal-title":"Ophthalmology."},{"key":"B11","doi-asserted-by":"crossref","first-page":"127","DOI":"10.1001\/jamaophthalmol.2015.4599","article-title":"Association of baseline visual acuity and retinal thickness with 1-year efficacy of aflibercept, bevacizumab, and ranibizumab for diabetic macular edema.","volume":"134","author":"Wells","year":"2016","journal-title":"JAMA Ophthalmol."},{"key":"B12","doi-asserted-by":"crossref","first-page":"1211","DOI":"10.1016\/j.ophtha.2020.03.010","article-title":"Application of automated quantification of fluid volumes to anti-VEGF therapy of neovascular age-related macular degeneration.","volume":"127","author":"Schmidt-Erfurth","year":"2020","journal-title":"Ophthalmology."},{"key":"B13","doi-asserted-by":"crossref","first-page":"945","DOI":"10.1001\/jamaophthalmol.2020.2457","article-title":"Quantification of fluid resolution and visual acuity gain in patients with diabetic macular edema using deep learning: a post hoc analysis of a randomized clinical trial.","volume":"138","author":"Roberts","year":"2020","journal-title":"JAMA Ophthalmol."},{"key":"B14","doi-asserted-by":"crossref","first-page":"1395","DOI":"10.1016\/j.ophtha.2015.02.036","article-title":"Predictors of functional and anatomic outcomes in patients with diabetic macular edema treated with ranibizumab.","volume":"122","author":"Sophie","year":"2015","journal-title":"Ophthalmology."},{"key":"B15","doi-asserted-by":"crossref","first-page":"1608","DOI":"10.1016\/j.ophtha.2018.04.007","article-title":"Guidelines on diabetic eye care: the international council of ophthalmology recommendations for screening, follow-up, referral, and treatment based on resource settings.","volume":"125","author":"Wong","year":"2018","journal-title":"Ophthalmology."},{"key":"B16","doi-asserted-by":"publisher","DOI":"10.1186\/1741-7015-4-7","article-title":"Revision of visual impairment definitions in the international statistical classification of diseases.","volume":"4","author":"Dandona","year":"2006","journal-title":"BMC Med."},{"key":"B17","doi-asserted-by":"crossref","first-page":"789","DOI":"10.1016\/j.ophtha.2011.12.039","article-title":"Ranibizumab for diabetic macular edema: results from 2 phase III randomized trials: RISE and RIDE.","volume":"119","author":"Nguyen","year":"2012","journal-title":"Ophthalmology."},{"key":"B18","doi-asserted-by":"crossref","first-page":"2247","DOI":"10.1016\/j.ophtha.2014.05.006","article-title":"Intravitreal aflibercept for diabetic macular edema.","volume":"121","author":"Korobelnik","year":"2014","journal-title":"Ophthalmology."},{"key":"B19","doi-asserted-by":"crossref","first-page":"257","DOI":"10.1007\/s12194-017-0406-5","article-title":"Overview of deep learning in medical imaging.","volume":"10","author":"Suzuki","year":"2017","journal-title":"Radiol Phys Technol."},{"key":"B20","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1007\/s11517-019-02066-y","article-title":"AOCT-NET: a convolutional network automated classification of multiclass retinal diseases using spectral-domain optical coherence tomography images.","volume":"58","author":"Alqudah","year":"2020","journal-title":"Med Biol Eng Comput."},{"key":"B21","first-page":"6105","article-title":"EfficientNet: rethinking model scaling for convolutional neural networks.","author":"Tan","year":"2019","journal-title":"Proceedings of the 36th International Conference on Machine Learning, ICML 2019."},{"key":"B22","doi-asserted-by":"crossref","first-page":"232","DOI":"10.7150\/thno.28447","article-title":"Artificial intelligence-based decision-making for age-related macular degeneration.","volume":"9","author":"Hwang","year":"2019","journal-title":"Theranostics."},{"key":"B23","doi-asserted-by":"crossref","first-page":"190","DOI":"10.1515\/med-2020-0028","article-title":"Classification of pathological types of lung cancer from CT images by deep residual neural networks with transfer learning strategy.","volume":"15","author":"Wang","year":"2020","journal-title":"Open Med (Wars)."},{"key":"B24","doi-asserted-by":"crossref","first-page":"357","DOI":"10.1136\/emermed-2017-206735","article-title":"What is an ROC curve?","volume":"34","author":"Hoo","year":"2017","journal-title":"Emerg Med J."},{"key":"B25","doi-asserted-by":"crossref","first-page":"5469","DOI":"10.1007\/s00330-019-06167-y","article-title":"Application of a deep learning algorithm for detection and visualization of hip fractures on plain pelvic radiographs.","volume":"29","author":"Cheng","year":"2019","journal-title":"Eur Radiol."},{"key":"B26","doi-asserted-by":"crossref","DOI":"10.1038\/s41598-019-45415-5","article-title":"Deep-learning-based imaging-classification identified cingulate island sign in dementia with Lewy bodies.","volume":"9","author":"Iizuka","year":"2019","journal-title":"Sci Rep."},{"key":"B27","doi-asserted-by":"publisher","DOI":"10.1186\/s12859-018-2516-4","article-title":"DeepM6ASeq: prediction and characterization of m6A-containing sequences using deep learning.","volume":"19","author":"Zhang","year":"2018","journal-title":"BMC Bioinformatics."},{"key":"B28","doi-asserted-by":"crossref","DOI":"10.1016\/S0140-6736(21)02149-8","article-title":"Digitising the vision test.","volume":"398","author":"Piech","year":"2021","journal-title":"Lancet."},{"key":"B29","doi-asserted-by":"crossref","first-page":"1880","DOI":"10.1001\/jama.2019.5790","article-title":"Effect of initial management with aflibercept vs laser photocoagulation vs observation on vision loss among patients with diabetic macular edema involving the center of the macula and good visual acuity: a randomized clinical trial.","volume":"321","author":"Baker","year":"2019","journal-title":"JAMA."},{"key":"B30","article-title":"Observation versus treatment in diabetic macular edema with very good visual acuity \u2013 the OBTAIN study.","volume":"60","author":"Busch","year":"2019","journal-title":"Invest Ophthalmol Vis Sci."},{"key":"B31","doi-asserted-by":"crossref","first-page":"168","DOI":"10.1001\/jamaophthalmol.2013.6426","article-title":"Underuse of the health care system by persons with diabetes mellitus and diabetic macular edema in the United States.","volume":"132","author":"Bressler","year":"2014","journal-title":"JAMA Ophthalmol."}],"container-title":["Frontiers in Medicine"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2022.1008950\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,6]],"date-time":"2022-10-06T12:33:47Z","timestamp":1665059627000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2022.1008950\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,6]]},"references-count":31,"alternative-id":["10.3389\/fmed.2022.1008950"],"URL":"https:\/\/doi.org\/10.3389\/fmed.2022.1008950","relation":{},"ISSN":["2296-858X"],"issn-type":[{"value":"2296-858X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,10,6]]},"article-number":"1008950"}}