{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T08:06:40Z","timestamp":1788854800341,"version":"build-2803163510"},"reference-count":62,"publisher":"Wiley","issue":"1","license":[{"start":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T00:00:00Z","timestamp":1785456000000},"content-version":"vor","delay-in-days":211,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"funder":[{"DOI":"10.13039\/501100001801","name":"University of Western Australia","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001801","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Journal of Ophthalmology"],"published-print":{"date-parts":[[2026,1]]},"abstract":"<jats:sec>\n                    <jats:title>Background\/Objectives<\/jats:title>\n                    <jats:p>Inherited retinal diseases (IRDs) are a leading cause of blindness in working\u2010age adults. Although artificial intelligence (AI) shows potential for disease classification, progress is limited by small datasets, reliance on labelled data and limited integration of multiple imaging modalities. RETFound, a foundation model pretrained on over 900,000 fundus photographs, may address these limitations. While RETFound is based on the transformer architecture, convolutional neural networks (CNNs), such as ResNet and EfficientNet_B0, have also demonstrated strong performance in classifying retinal diseases. This study adapted RETFound and CNNs for analysing fundus autofluorescence (FAF) and pseudocolour ultra\u2010widefield (UWF) images, establishing a framework to classify IRDs.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Subjects\/Methods<\/jats:title>\n                    <jats:p>Deidentified FAF and UWF images were obtained from controls and patients with Best disease, rod\u2010cone dystrophy, Stargardt disease and choroideremia. Images underwent preprocessing and were used to fine\u2010tune RETFound. Model performance was compared with classical machine learning algorithms (logistic regression, support vector machine, gradient boosting and random forest) and deep learning architectures (ResNet18, ResNet50, vision transformer, EfficientNet_B0 and ConvNeXt\u2010Tiny) pretrained on ImageNet.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The fine\u2010tuned RETFound model achieved an accuracy of 0.815, with the best performance for rod\u2010cone dystrophy (F1\u2009=\u20090.820). RETFound outperformed classical machine learning models and a vision transformer pretrained on ImageNet. ResNet18 achieved a weighted F1 of 0.839 and demonstrated the best classification performance for Stargardt disease and choroideremia (F1 0.821 and 0.728, respectively). ResNet50 achieved a weighted F1 of 0.825 and demonstrated the best classification performance for normal retinas and Best disease (F1 0.945 and 0.616, respectively). ResNet architectures achieved the best performance overall.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>ResNet architectures and fine\u2010tuned RETFound both demonstrated strong accuracy in classifying IRD classes, demonstrating potential for clinical application and deployment in eye care settings as tools for IRD diagnosis, triage and management.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1155\/joph\/8810684","type":"journal-article","created":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T06:52:51Z","timestamp":1785567171000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Classification of Inherited Retinal Diseases Using Artificial Intelligence Models for Fundus Autofluorescence and Ultrawide Retinal Images"],"prefix":"10.1155","volume":"2026","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-2107-0710","authenticated-orcid":false,"given":"Han","family":"Trinh","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5376-2477","authenticated-orcid":false,"given":"Muhammad","family":"Ibrahim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5778-6310","authenticated-orcid":false,"given":"Jason","family":"Charng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5432-1016","authenticated-orcid":false,"given":"Zahra","family":"Tajbakhsh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2809-9930","authenticated-orcid":false,"given":"Fred K.","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5206-3842","authenticated-orcid":false,"given":"Ajmal","family":"Mian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7779-0467","authenticated-orcid":false,"given":"Khyber","family":"Alam","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2026,7,31]]},"reference":[{"key":"e_1_2_12_1_2","doi-asserted-by":"publisher","DOI":"10.1101\/cshperspect.a041277"},{"key":"e_1_2_12_2_2","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1913179117"},{"key":"e_1_2_12_3_2","doi-asserted-by":"publisher","DOI":"10.1080\/13816810.2021.1913610"},{"key":"e_1_2_12_4_2","unstructured":"DaigerS. GreenbergJ. ChristoffelsA. andHideW. Retnet the Retinal Information Network https:\/\/RetNet.org\/."},{"key":"e_1_2_12_5_2","article-title":"Understanding the Effective Receptive Field in Deep Convolutional Neural Networks","volume":"29","author":"Luo W.","year":"2016","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_12_6_2","article-title":"Attention Is all You Need","volume":"30","author":"Vaswani A.","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_12_7_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.susoc.2022.03.001"},{"key":"e_1_2_12_8_2","unstructured":"TargS. AlmeidaD. andLymanK. Resnet in Resnet: Generalizing Residual Architectures arXiv preprint arXiv:160308029. 2016."},{"key":"e_1_2_12_9_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4842-6168-2_10"},{"key":"e_1_2_12_10_2","doi-asserted-by":"publisher","DOI":"10.3389\/fphys.2023.1126780"},{"key":"e_1_2_12_11_2","doi-asserted-by":"publisher","DOI":"10.1186\/s12859-023-05293-1"},{"key":"e_1_2_12_12_2","unstructured":"TanM.andLeQ. Efficientnet: Rethinking Model Scaling for Convolutional Neural Networks International Conference on Machine Learning 2019 PMLR."},{"key":"e_1_2_12_13_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-024-81132-4"},{"key":"e_1_2_12_14_2","unstructured":"MaswoodM. M. S. HussainT. KhanM. B. IslamM. T. andAlharbiA. G. Cnn Based Detection of the Severity of Diabetic Retinopathy From the Fundus Photography Using efficientnet-b5 2020 11th IEEE Annual Information Technology Electronics and Mobile Communication Conference (IEMCON) 2020 IEEE."},{"key":"e_1_2_12_15_2","doi-asserted-by":"publisher","DOI":"10.17485\/ijst\/v17i32.1997"},{"key":"e_1_2_12_16_2","doi-asserted-by":"crossref","unstructured":"AnithaJ.andSangapuS. C. Diabetic Retinopathy Detection Using EfficientNet-Based Framework With Segmentation 2024 3rd International Conference for Advancement in Technology (ICONAT) 2024 IEEE.","DOI":"10.1109\/ICONAT61936.2024.10775147"},{"key":"e_1_2_12_17_2","doi-asserted-by":"publisher","DOI":"10.3390\/diagnostics13040774"},{"key":"e_1_2_12_18_2","doi-asserted-by":"publisher","DOI":"10.17798\/bitlisfen.1174512"},{"key":"e_1_2_12_19_2","doi-asserted-by":"publisher","DOI":"10.1007\/s00371-021-02114-5"},{"key":"e_1_2_12_20_2","doi-asserted-by":"publisher","DOI":"10.3390\/app14177795"},{"key":"e_1_2_12_21_2","doi-asserted-by":"publisher","DOI":"10.37745\/ejcsit.2013\/vol12n84861"},{"key":"e_1_2_12_22_2","doi-asserted-by":"publisher","DOI":"10.3389\/fmed.2022.808402"},{"key":"e_1_2_12_23_2","doi-asserted-by":"publisher","DOI":"10.3390\/jcm9103303"},{"key":"e_1_2_12_24_2","volume-title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","author":"Simonyan K.","year":"2014"},{"key":"e_1_2_12_25_2","doi-asserted-by":"publisher","DOI":"10.7717\/peerj.6900"},{"key":"e_1_2_12_26_2","doi-asserted-by":"publisher","DOI":"10.1111\/aos.14353"},{"key":"e_1_2_12_27_2","article-title":"Deep Learning-Based Retinal Layer Segmentation in Optical Coherence Tomography Scans of Patients With Inherited Retinal Diseases","author":"Eckardt F.","year":"2024","journal-title":"Klinische Monatsbl\u00e4tter f\u00fcr Augenheilkunde"},{"key":"e_1_2_12_28_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10278-021-00479-6"},{"key":"e_1_2_12_29_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2018.04.065"},{"key":"e_1_2_12_30_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-020-73339-y"},{"key":"e_1_2_12_31_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.oret.2023.09.015"},{"key":"e_1_2_12_32_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-06555-x"},{"key":"e_1_2_12_33_2","unstructured":"WangM. LinT. YuK.et al. Common and Rare Fundus Diseases Identification Using Vision-Language Foundation Model With Knowledge of Over 400 Diseases arXiv e-prints. 2024:arXiv: 2406.09317."},{"key":"e_1_2_12_34_2","doi-asserted-by":"crossref","unstructured":"FecsoR. MoranoJ. Schmidt-ErfurthU. andBogunovi\u0107H. RetFiner: A Vision-Language Refinement Scheme for Retinal Foundation Models 2025 arXiv preprint arXiv:250622149.","DOI":"10.1007\/978-3-032-04971-1_51"},{"key":"e_1_2_12_35_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41551-025-01365-0"},{"key":"e_1_2_12_36_2","doi-asserted-by":"publisher","DOI":"10.1097\/iae.0000000000002519"},{"key":"e_1_2_12_37_2","doi-asserted-by":"publisher","DOI":"10.1186\/s40942-016-0035-x"},{"key":"e_1_2_12_38_2","volume-title":"ACTRN12618000738224. The Western Australia Retinal Degeneration Study: An Natural History Observational Cohort Study of Retinal Degenerations and in Vitro Retinal Disease Modelling Using Patient Derived Stem Cells","author":"Australian New Zealand Clinical Trials Registry","year":"2018"},{"key":"e_1_2_12_39_2","article-title":"The Australian Inherited Retinal Disease Registry and DNA Bank","author":"DeRoach J.","year":"2017","journal-title":"Clinical and Experimental Ophthalmology"},{"key":"e_1_2_12_40_2","doi-asserted-by":"publisher","DOI":"10.1002\/humu.22981"},{"key":"e_1_2_12_41_2","doi-asserted-by":"publisher","DOI":"10.1038\/gim.2015.30"},{"key":"e_1_2_12_42_2","doi-asserted-by":"publisher","DOI":"10.1186\/s13073-019-0690-2"},{"key":"e_1_2_12_43_2","doi-asserted-by":"publisher","DOI":"10.1613\/jair.953"},{"key":"e_1_2_12_44_2","unstructured":"JinX. ZhuH. LiS.et al. A Survey on Mixup Augmentations and Beyond 2024 arXiv preprint arXiv:240905202."},{"key":"e_1_2_12_45_2","unstructured":"LoshchilovI.andHutterF. Fixing Weight Decay Regularization in Adam 2017 5 no. 5 arXiv preprint arXiv:171105101."},{"key":"e_1_2_12_46_2","unstructured":"MaoA. MohriM. andZhongY. Cross-Entropy Loss Functions: Theoretical Analysis and Applications International Conference on Machine Learning 2023 PMLR."},{"key":"e_1_2_12_47_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.xops.2025.100720"},{"key":"e_1_2_12_48_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2024.108635"},{"key":"e_1_2_12_49_2","article-title":"Multimodal Deep Learning for Retinal Disease Diagnosis","author":"Wang D.","year":"2025","journal-title":"International Symposium on Neural Networks"},{"key":"e_1_2_12_50_2","doi-asserted-by":"publisher","DOI":"10.1109\/tmi.2021.3059956"},{"key":"e_1_2_12_51_2","doi-asserted-by":"publisher","DOI":"10.1001\/jamaophthalmol.2022.6393"},{"key":"e_1_2_12_52_2","doi-asserted-by":"crossref","unstructured":"HeK. ZhangX. RenS. andSunJ. Deep Residual Learning for Image Recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition 2016.","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_2_12_53_2","doi-asserted-by":"publisher","DOI":"10.1088\/2057-1976\/ad27ea"},{"key":"e_1_2_12_54_2","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0318657"},{"key":"e_1_2_12_55_2","doi-asserted-by":"publisher","DOI":"10.1177\/1932296821999370"},{"key":"e_1_2_12_56_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.xops.2022.100228"},{"key":"e_1_2_12_57_2","doi-asserted-by":"publisher","DOI":"10.1177\/11206721261419673"},{"key":"e_1_2_12_58_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ophtha.2020.06.038"},{"key":"e_1_2_12_59_2","doi-asserted-by":"publisher","DOI":"10.1097\/iae.0000000000002659"},{"key":"e_1_2_12_60_2","doi-asserted-by":"crossref","unstructured":"Rezaei-DastjerdeheiM. R. MijaniA. andFatemizadehE. Addressing Imbalance in Multi-Label Classification Using Weighted Cross Entropy Loss Function 2020 27th National and 5th International Iranian Conference on Biomedical Engineering (ICBME) November 2020.","DOI":"10.1109\/ICBME51989.2020.9319440"},{"key":"e_1_2_12_61_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2022.108295"},{"key":"e_1_2_12_62_2","unstructured":"SelvarajuR. R. DasA. VedantamR. CogswellM. ParikhD. andBatraD. Grad-CAM: Why Did You Say That? 2016 arXiv preprint arXiv:161107450."}],"container-title":["Journal of Ophthalmology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1155\/joph\/8810684","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1155\/joph\/8810684","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1155\/joph\/8810684","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T07:08:22Z","timestamp":1788851302000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1155\/joph\/8810684"}},"subtitle":[],"editor":[{"given":"Wataru","family":"Matsumiya","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,1]]},"references-count":62,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,1]]}},"alternative-id":["10.1155\/joph\/8810684"],"URL":"https:\/\/doi.org\/10.1155\/joph\/8810684","archive":["Portico"],"relation":{},"ISSN":["2090-004X","2090-0058"],"issn-type":[{"value":"2090-004X","type":"print"},{"value":"2090-0058","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1]]},"assertion":[{"value":"2025-12-05","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-07-02","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-07-31","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"8810684"}}