{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,24]],"date-time":"2026-10-24T16:09:54Z","timestamp":1792858194168,"version":"4.5.0"},"reference-count":34,"publisher":"Public Library of Science (PLoS)","issue":"5","license":[{"start":{"date-parts":[[2026,5,11]],"date-time":"2026-05-11T00:00:00Z","timestamp":1778457600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:sec id=\"sec001\">\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>To evaluate a novel image-based deep learning method for the automated identification of inherited retinal diseases (IRDs) and to explore the feasibility of predicting selected causative gene groups using a multimodal analysis of wide-field fundus autofluorescence (FAF) and pseudocolor fundus (pCF) images.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec002\">\n                    <jats:title>Design<\/jats:title>\n                    <jats:p>The method was evaluated using a retrospective dataset of patient studies containing FAF and pCF images, as well as genetic tests for IRD.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec003\">\n                    <jats:title>Participants<\/jats:title>\n                    <jats:p>Patients with confirmed IRD for which both wide-field FAF and pCF images and genetic tests for IRD performed at Hadassah University Medical Center were included. The dataset consisted of 409 patients (330 patients with IRD with the 25 most commonly affected genes in our population and patients without IRD, and 79 patients without IRD).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec004\">\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>Nine EfficientNet-V2-m convolutional neural networks were trained for the following three classification tasks: a binary IRD vs. non-IRD classification, and classification into two groups of five causative genes (Groups 1 and 2). For each task, three models were trained on the FAF images only, the pCF images only, and both the FAF and pCF images. The performance of the models was then evaluated and compared using 5-fold cross-validation.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec005\">\n                    <jats:title>Main outcome measures<\/jats:title>\n                    <jats:p>Accuracy, precision, F1 scores, AUC, and confusion matrices.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec006\">\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The multimodal classification models that were trained on both the FAF and pCF images yielded the best results. The binary classification model had a mean (\u00b1SD) accuracy of 0.95\u2009\u00b1\u20090.01, a mean precision of 0.92\u2009\u00b1\u20090.01, and a mean F1 score of 0.90\u2009\u00b1\u20090.02. The Group 1 classification model had a mean accuracy of 0.92\u2009\u00b1\u20090.03, a mean precision of 0.93\u2009\u00b1\u20090.03, and a mean F1 score of 0.89\u2009\u00b1\u20090.03. Finally, the Group 2 classification model had a mean accuracy of 0.85\u2009\u00b1\u20090.03, a mean precision of 0.87\u2009\u00b1\u20090.04, and a mean F1 score of 0.83\u2009\u00b1\u20090.04.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec007\">\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>Our results indicate that determining whether a patient has IRD can be performed with high accuracy within this retrospective cohort based on FAF and pCF images using image-based deep learning classifiers. This image-based approach may assist clinicians during the patient\u2019s initial visit by providing decision support prior to genetic testing. It may also help prioritize patients for genetic workup, particularly in settings in which genetic testing is not readily available. Further prospective and external validation is required before clinical implementation.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1371\/journal.pone.0348866","type":"journal-article","created":{"date-parts":[[2026,5,11]],"date-time":"2026-05-11T17:27:37Z","timestamp":1778520457000},"page":"e0348866","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":2,"title":["Using deep learning to identify inherited retinal diseases based on wide-field retinal imaging data"],"prefix":"10.1371","volume":"21","author":[{"given":"Leo","family":"Joskowicz","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tim","family":"Buchbinder","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Eldan","family":"Chodorov","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4542-6254","authenticated-orcid":true,"given":"Assaf","family":"Hoogi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Katherine","family":"Matos","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Antonio","family":"Rivera","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dror","family":"Sharon","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Eyal","family":"Banin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0043-4354","authenticated-orcid":true,"given":"Jaime","family":"Levy","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,5,11]]},"reference":[{"issue":"3","key":"pone.0348866.ref001","doi-asserted-by":"crossref","first-page":"270","DOI":"10.1111\/ceo.13917","article-title":"Inherited retinal diseases: Therapeutics, clinical trials and end points-A review","volume":"49","author":"M Georgiou","year":"2021","journal-title":"Clin Exp Ophthalmol"},{"issue":"4","key":"pone.0348866.ref002","doi-asserted-by":"crossref","first-page":"189","DOI":"10.1177\/014107680609900417","article-title":"Genetics of inherited retinal disease","volume":"99","author":"PJ Francis","year":"2006","journal-title":"J R Soc Med"},{"key":"pone.0348866.ref003","doi-asserted-by":"crossref","first-page":"101029","DOI":"10.1016\/j.preteyeres.2021.101029","article-title":"Inherited retinal diseases: Linking genes, disease-causing variants, and relevant therapeutic modalities","volume":"89","author":"N Schneider","year":"2022","journal-title":"Prog Retin Eye Res"},{"issue":"9549","key":"pone.0348866.ref004","doi-asserted-by":"crossref","first-page":"1795","DOI":"10.1016\/S0140-6736(06)69740-7","article-title":"Retinitis pigmentosa","volume":"368","author":"DT Hartong","year":"2006","journal-title":"Lancet"},{"key":"pone.0348866.ref005","doi-asserted-by":"crossref","first-page":"101244","DOI":"10.1016\/j.preteyeres.2024.101244","article-title":"Phenotyping and genotyping inherited retinal diseases: Molecular genetics, clinical and imaging features, and therapeutics of macular dystrophies, cone and cone-rod dystrophies, rod-cone dystrophies, Leber congenital amaurosis, and cone dysfunction syndromes","volume":"100","author":"M Georgiou","year":"2024","journal-title":"Prog Retin Eye Res"},{"issue":"1","key":"pone.0348866.ref006","doi-asserted-by":"crossref","first-page":"514","DOI":"10.1186\/s13023-021-02145-0","article-title":"Genetic testing and diagnosis of inherited retinal diseases","volume":"16","author":"BL Lam","year":"2021","journal-title":"Orphanet J Rare Dis"},{"issue":"3","key":"pone.0348866.ref007","doi-asserted-by":"crossref","first-page":"307","DOI":"10.1016\/S0959-437X(00)00195-7","article-title":"Molecular genetics and prospects for therapy of the inherited retinal dystrophies","volume":"11","author":"DA Bessant","year":"2001","journal-title":"Curr Opin Genet Dev"},{"issue":"7","key":"pone.0348866.ref008","doi-asserted-by":"crossref","first-page":"609","DOI":"10.1001\/jamaophthalmol.2024.1461","article-title":"Nationwide Prevalence of Inherited Retinal Diseases in the Israeli Population","volume":"142","author":"S Shalom","year":"2024","journal-title":"JAMA Ophthalmol"},{"issue":"5","key":"pone.0348866.ref009","doi-asserted-by":"crossref","first-page":"2710","DOI":"10.1073\/pnas.1913179117","article-title":"Worldwide carrier frequency and genetic prevalence of autosomal recessive inherited retinal diseases","volume":"117","author":"M Hanany","year":"2020","journal-title":"Proc Natl Acad Sci U S A"},{"issue":"11","key":"pone.0348866.ref010","doi-asserted-by":"crossref","first-page":"2408","DOI":"10.1016\/j.ophtha.2012.05.047","article-title":"Recommendations for genetic testing of inherited eye diseases: report of the American Academy of Ophthalmology task force on genetic testing","volume":"119","author":"EM Stone","year":"2012","journal-title":"Ophthalmology"},{"issue":"1","key":"pone.0348866.ref011","doi-asserted-by":"crossref","first-page":"142","DOI":"10.1186\/s13023-021-01756-x","article-title":"The need for widely available genomic testing in rare eye diseases: an ERN-EYE position statement","volume":"16","author":"GC Black","year":"2021","journal-title":"Orphanet J Rare Dis"},{"issue":"5","key":"pone.0348866.ref012","doi-asserted-by":"crossref","first-page":"1485","DOI":"10.1037\/xlm0000117","article-title":"Central and peripheral vision loss differentially affects contextual cueing in visual search","volume":"41","author":"F Geringswald","year":"2015","journal-title":"J Exp Psychol Learn Mem Cogn"},{"issue":"1","key":"pone.0348866.ref013","doi-asserted-by":"crossref","first-page":"80","DOI":"10.4103\/joco.joco_172_21","article-title":"Vision-Related Quality of Life in Patients with Inherited Retinal Dystrophies","volume":"34","author":"S Shojaei","year":"2022","journal-title":"J Curr Ophthalmol"},{"issue":"21","key":"pone.0348866.ref014","doi-asserted-by":"crossref","first-page":"1972","DOI":"10.1056\/NEJMoa2309915","article-title":"Gene Editing for CEP290-Associated Retinal Degeneration","volume":"390","author":"EA Pierce","year":"2024","journal-title":"N Engl J Med"},{"issue":"2","key":"pone.0348866.ref015","article-title":"Clinical characteristics and current therapies for inherited retinal degenerations","volume":"5","author":"J-A Sahel","year":"2014","journal-title":"Cold Spring Harb Perspect Med"},{"issue":"5","key":"pone.0348866.ref016","doi-asserted-by":"crossref","DOI":"10.1111\/aos.13602","article-title":"Fundus autofluorescence imaging in hereditary retinal diseases","volume":"96","author":"F Pichi","year":"2018","journal-title":"Acta Ophthalmol"},{"issue":"1","key":"pone.0348866.ref017","doi-asserted-by":"crossref","first-page":"93","DOI":"10.1186\/s13023-024-03099-9","article-title":"Cost-of-illness studies of inherited retinal diseases: a systematic review","volume":"19","author":"QX Ng","year":"2024","journal-title":"Orphanet J Rare Dis"},{"key":"pone.0348866.ref018","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.preteyeres.2018.07.004","article-title":"Artificial intelligence in retina","volume":"67","author":"U Schmidt-Erfurth","year":"2018","journal-title":"Prog Retin Eye Res"},{"key":"pone.0348866.ref019","doi-asserted-by":"crossref","first-page":"39","DOI":"10.1038\/s41746-018-0040-6","article-title":"Pivotal trial of an autonomous AI-based diagnostic system for detection of diabetic retinopathy in primary care offices","volume":"1","author":"MD Abr\u00e0moff","year":"2018","journal-title":"NPJ Digit Med"},{"issue":"4","key":"pone.0348866.ref020","doi-asserted-by":"crossref","first-page":"322","DOI":"10.1016\/j.oret.2016.12.009","article-title":"Deep learning is effective for the classification of OCT images of normal versus Age-related Macular Degeneration","volume":"1","author":"CS Lee","year":"2017","journal-title":"Ophthalmol Retina"},{"issue":"8","key":"pone.0348866.ref021","doi-asserted-by":"crossref","first-page":"1199","DOI":"10.1016\/j.ophtha.2018.01.023","article-title":"Efficacy of a Deep Learning System for Detecting Glaucomatous Optic Neuropathy Based on Color Fundus Photographs","volume":"125","author":"Z Li","year":"2018","journal-title":"Ophthalmology"},{"issue":"10","key":"pone.0348866.ref022","doi-asserted-by":"crossref","first-page":"3303","DOI":"10.3390\/jcm9103303","article-title":"Deep Learning-Based Classification of Inherited Retinal Diseases Using Fundus Autofluorescence","volume":"9","author":"A Miere","year":"2020","journal-title":"J Clin Med"},{"issue":"9","key":"pone.0348866.ref023","doi-asserted-by":"crossref","first-page":"1272","DOI":"10.1136\/bjophthalmol-2020-318544","article-title":"Prediction of causative genes in inherited retinal disorder from fundus photography and autofluorescence imaging using deep learning techniques","volume":"105","author":"Y Fujinami-Yokokawa","year":"2021","journal-title":"Br J Ophthalmol"},{"key":"pone.0348866.ref024","first-page":"1161","article-title":"Eye2Gene: prediction of causal inherited retinal disease gene from multimodal imaging using deep-learning","volume":"63","author":"N Pontikos","year":"2022","journal-title":"Invest Ophthalmol Vis Sci"},{"issue":"6","key":"pone.0348866.ref025","doi-asserted-by":"crossref","DOI":"10.1111\/aos.14353","article-title":"Automated classification of normal and Stargardt disease optical coherence tomography images using deep learning","volume":"98","author":"M Shah","year":"2020","journal-title":"Acta Ophthalmol"},{"issue":"1","key":"pone.0348866.ref026","doi-asserted-by":"crossref","first-page":"140","DOI":"10.1002\/humu.23903","article-title":"A nationwide genetic analysis of inherited retinal diseases in Israel as assessed by the Israeli inherited retinal disease consortium (IIRDC)","volume":"41","author":"D Sharon","year":"2020","journal-title":"Hum Mutat"},{"key":"pone.0348866.ref027","first-page":"10096","article-title":"EfficientNetv2: smaller models and faster training. Proc Int Conf Mach Learn. arXiv:2104.00298","author":"M Tan","year":"2021"},{"key":"pone.0348866.ref028","doi-asserted-by":"crossref","unstructured":"Deng J, Dong W, Socher R, Li L-J, Kai Li, Li F-F. ImageNet: A large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition. 2009. p. 248\u201355.","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"pone.0348866.ref029","article-title":"Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980.","author":"DP Kingma"},{"issue":"3","key":"pone.0348866.ref030","doi-asserted-by":"crossref","first-page":"119","DOI":"10.2307\/3001946","article-title":"Probability tables for individual comparisons by ranking methods","volume":"3","author":"F Wilcoxin","year":"1947","journal-title":"Biometrics"},{"issue":"9","key":"pone.0348866.ref031","doi-asserted-by":"crossref","first-page":"1361","DOI":"10.18240\/ijo.2023.09.02","article-title":"Guidelines on clinical research evaluation of artificial intelligence in ophthalmology","volume":"16","author":"WH Yang","year":"2023","journal-title":"Int J Ophthalmol"},{"issue":"3","key":"pone.0348866.ref032","doi-asserted-by":"crossref","DOI":"10.1136\/bmjopen-2022-071043","article-title":"Can artificial intelligence accelerate the diagnosis of inherited retinal diseases? Protocol for a data-only retrospective cohort study (Eye2Gene)","volume":"13","author":"Q Nguyen","year":"2023","journal-title":"BMJ Open"},{"issue":"7","key":"pone.0348866.ref033","first-page":"2154","article-title":"Economic value of early genetic testing in inherited retinal dystrophies diagnosis","volume":"65","author":"Q Zhang","year":"2024","journal-title":"Invest Ophthalmol Vis Sci"},{"issue":"6","key":"pone.0348866.ref034","doi-asserted-by":"crossref","first-page":"967","DOI":"10.1038\/s42256-025-01040-8","article-title":"Next-generation phenotyping of inherited retinal diseases from multimodal imaging with Eye2Gene","volume":"7","author":"N Pontikos","year":"2025","journal-title":"Nat Mach Intell"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0348866","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,11]],"date-time":"2026-05-11T17:27:45Z","timestamp":1778520465000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0348866"}},"subtitle":[],"editor":[{"given":"Ogugua Ndubuisi","family":"Okonkwo","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,5,11]]},"references-count":34,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2026,5,11]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0348866","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,11]]}}}