{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,12]],"date-time":"2026-10-12T17:00:33Z","timestamp":1791824433967,"version":"4.3.4"},"reference-count":25,"publisher":"Public Library of Science (PLoS)","issue":"1","license":[{"start":{"date-parts":[[2026,1,6]],"date-time":"2026-01-06T00:00:00Z","timestamp":1767657600000},"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:p>\n                    Diabetic Retinopathy, Cataract, and Glaucoma are major retinal diseases that require early detection to prevent irreversible vision loss. This study proposes a deep learning-based framework for the automated classification of retinal images into four categories: Normal, Diabetic Retinopathy, Cataract, and Glaucoma. The dataset was compiled from publicly available retinal imaging databases, including IDRiD and HRF. Four convolutional neural network architectures\u2014EfficientNet-B0, EfficientNet-B7, a build-from-scratch model, and AlexNet\u2014were evaluated using multiple performance metrics. Among these, AlexNet achieved the highest overall performance, attaining an accuracy of 93.65%, sensitivity of 94.39%, specificity of 98.05%, PPV of 93.65%, NPV of 97.95%, and an F1-score of 93.74%. EfficientNet-B7 followed with an accuracy of 92.82%, confirming the strength of transfer learning in retinal feature extraction. A five-fold cross-validation further validated AlexNet\u2019s robustness, yielding a mean\n                    <jats:italic>R<\/jats:italic>\n                    <jats:sup>2<\/jats:sup>\n                    of 0.8891 with low variance, indicating consistent generalization across folds. Computational efficiency analysis showed that AlexNet achieved high diagnostic accuracy with a moderate processing time of approximately 14 minutes. Model interpretability using SHapley Additive exPlanations (SHAP) revealed that AlexNet highlighted clinically relevant retinal regions, such as the optic disc and macula, thereby enhancing transparency and clinical trust. In summary, the proposed framework demonstrates that interpretable deep learning models can deliver accurate, consistent, and explainable retinal disease classification, offering a foundation for real-time, AI-assisted ophthalmic screening systems.\n                  <\/jats:p>","DOI":"10.1371\/journal.pone.0338415","type":"journal-article","created":{"date-parts":[[2026,1,6]],"date-time":"2026-01-06T19:19:17Z","timestamp":1767727157000},"page":"e0338415","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":6,"title":["Automated retinal disease classification using deep learning and AlexNet with statistical models analysis"],"prefix":"10.1371","volume":"21","author":[{"given":"El-Sayed M.","family":"Elkenawy","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8348-6530","authenticated-orcid":true,"given":"Nima","family":"Khodadadi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Khaled Sh.","family":"Gaber","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5688-0906","authenticated-orcid":true,"given":"Ehsan","family":"Khodadadi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Amel Ali","family":"Alhussan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Doaa Sami","family":"Khafaga","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marwa M.","family":"Eid","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,1,6]]},"reference":[{"key":"pone.0338415.ref001","doi-asserted-by":"crossref","unstructured":"Orfao J, van der Haar D. A comparison of computer vision methods for the combined detection of glaucoma, diabetic retinopathy and cataracts. In: Papi\u00e9z BW, Yaqub M, Jiao J, Namburete AIL, Noble JA, editors. Medical image understanding and analysis. Springer International Publishing; 2021. p. 30\u201342.","DOI":"10.1007\/978-3-030-80432-9_3"},{"issue":"1","key":"pone.0338415.ref002","doi-asserted-by":"crossref","first-page":"487","DOI":"10.1007\/s11831-023-09989-8","article-title":"Analysis of deep learning techniques for prediction of eye diseases: a systematic review","volume":"31","author":"A Bali","year":"2023","journal-title":"Arch Computat Methods Eng."},{"issue":"1","key":"pone.0338415.ref003","doi-asserted-by":"crossref","first-page":"16993","DOI":"10.1038\/s41598-021-96438-w","article-title":"Distribution of diabetic retinopathy in diabetes mellitus patients and its association rules with other eye diseases","volume":"11","author":"X Yao","year":"2021","journal-title":"Sci Rep."},{"issue":"8","key":"pone.0338415.ref004","doi-asserted-by":"crossref","first-page":"366","DOI":"10.3390\/bioengineering9080366","article-title":"The role of medical image modalities and ai in the early detection, diagnosis and grading of retinal diseases: a survey","volume":"9","author":"GA Saleh","year":"2022","journal-title":"Bioengineering (Basel)."},{"key":"pone.0338415.ref005","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.cmpb.2018.07.012","article-title":"Computer-aided diagnosis of glaucoma using fundus images: a review","volume":"165","author":"Y Hagiwara","year":"2018","journal-title":"Comput Methods Programs Biomed."},{"key":"pone.0338415.ref006","doi-asserted-by":"crossref","first-page":"103768","DOI":"10.1016\/j.bspc.2022.103768","article-title":"EfficientNet embedded with spatial attention for recognition of multi-label fundus disease from color fundus photographs","volume":"77","author":"K Sun","year":"2022","journal-title":"Biomedical Signal Processing and Control."},{"issue":"1","key":"pone.0338415.ref007","doi-asserted-by":"crossref","first-page":"13","DOI":"10.1007\/s13755-022-00182-y","article-title":"Optical coherence tomography image based eye disease detection using deep convolutional neural network","volume":"10","author":"Puneet","year":"2022","journal-title":"Health Inf Sci Syst."},{"key":"pone.0338415.ref008","first-page":"1","article-title":"Machine learning and deep learning approach for medical image analysis: diagnosis to detection","author":"M Rana","year":"2022","journal-title":"Multimed Tools Appl."},{"key":"pone.0338415.ref009","doi-asserted-by":"crossref","first-page":"103768","DOI":"10.1016\/j.bspc.2022.103768","article-title":"EfficientNet embedded with spatial attention for recognition of multi-label fundus disease from color fundus photographs","volume":"77","author":"K Sun","year":"2022","journal-title":"Biomedical Signal Processing and Control."},{"key":"pone.0338415.ref010","doi-asserted-by":"crossref","unstructured":"Akil M, Elloumi Y, Kachouri R. Detection of retinal abnormalities in fundus image using CNN deep learning networks. State of the Art in Neural Networks and their Applications. Elsevier. 2021. p. 19\u201361. https:\/\/doi.org\/10.1016\/b978-0-12-819740-0.00002-4","DOI":"10.1016\/B978-0-12-819740-0.00002-4"},{"issue":"3","key":"pone.0338415.ref011","doi-asserted-by":"crossref","first-page":"1787","DOI":"10.1080\/10803548.2021.1936912","article-title":"High frequency of digital eye strain and dry eye disease in teleworkers during the coronavirus disease 2019 pandemic","volume":"28","author":"D Salinas-Toro","year":"2022","journal-title":"Int J Occup Saf Ergon."},{"issue":"1","key":"pone.0338415.ref012","doi-asserted-by":"crossref","first-page":"3637","DOI":"10.1038\/s41598-023-30853-z","article-title":"An interpretable transformer network for the retinal disease classification using optical coherence tomography","volume":"13","author":"J He","year":"2023","journal-title":"Sci Rep."},{"issue":"19","key":"pone.0338415.ref013","doi-asserted-by":"crossref","first-page":"21227","DOI":"10.1007\/s11042-024-19922-1","article-title":"Boost diagnostic performance in retinal disease classification utilizing deep ensemble classifiers based on OCT","volume":"84","author":"US Khan","year":"2024","journal-title":"Multimed Tools Appl."},{"issue":"12","key":"pone.0338415.ref014","article-title":"MHANet: a hybrid attention mechanism for retinal diseases classification","volume":"16","author":"L Xu","year":"2021","journal-title":"PLoS One."},{"key":"pone.0338415.ref015","doi-asserted-by":"crossref","unstructured":"Kim J, Tran L. Retinal disease classification from OCT images using deep learning algorithms. In: 2021 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology (CIBCB). 2021. p. 1\u20136. https:\/\/doi.org\/10.1109\/cibcb49929.2021.9562919","DOI":"10.1109\/CIBCB49929.2021.9562919"},{"issue":"17","key":"pone.0338415.ref016","doi-asserted-by":"crossref","first-page":"12495","DOI":"10.1007\/s00521-023-08402-6","article-title":"Retinal disease prediction through blood vessel segmentation and classification using ensemble-based deep learning approaches","volume":"35","author":"KS Kumar","year":"2023","journal-title":"Neural Comput & Applic."},{"issue":"14","key":"pone.0338415.ref017","doi-asserted-by":"crossref","first-page":"10551","DOI":"10.1007\/s00521-023-08249-x","article-title":"EyeDeep-Net: a multi-class diagnosis of retinal diseases using deep neural network","volume":"35","author":"N Sengar","year":"2023","journal-title":"Neural Comput & Applic."},{"issue":"1","key":"pone.0338415.ref018","doi-asserted-by":"crossref","first-page":"487","DOI":"10.1007\/s11831-023-09989-8","article-title":"Analysis of deep learning techniques for prediction of eye diseases: a systematic review","volume":"31","author":"A Bali","year":"2023","journal-title":"Arch Computat Methods Eng."},{"issue":"1","key":"pone.0338415.ref019","doi-asserted-by":"crossref","first-page":"20","DOI":"10.1007\/s13721-021-00294-7","article-title":"Comprehensive review of retinal blood vessel segmentation and classification techniques: intelligent solutions for green computing in medical images, current challenges, open issues, and knowledge gaps in fundus medical images","volume":"10","author":"AA Abdulsahib","year":"2021","journal-title":"Netw Model Anal Health Inform Bioinforma."},{"issue":"4","key":"pone.0338415.ref020","doi-asserted-by":"crossref","first-page":"1417","DOI":"10.1007\/s00530-021-00769-7","article-title":"DL-CNN-based approach with image processing techniques for diagnosis of retinal diseases","volume":"28","author":"A Tayal","year":"2021","journal-title":"Multimedia Systems."},{"key":"pone.0338415.ref021","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.cmpb.2018.07.012","article-title":"Computer-aided diagnosis of glaucoma using fundus images: a review","volume":"165","author":"Y Hagiwara","year":"2018","journal-title":"Comput Methods Programs Biomed."},{"key":"pone.0338415.ref022","doi-asserted-by":"crossref","unstructured":"Orfao J, van der Haar D. A comparison of computer vision methods for the combined detection of glaucoma, diabetic retinopathy and cataracts. In: Papi\u00e9z BW, Yaqub M, Jiao J, Namburete AIL, Noble JA, editors. Medical image understanding and analysis. Springer; 2021. p. 30\u201342.","DOI":"10.1007\/978-3-030-80432-9_3"},{"issue":"2","key":"pone.0338415.ref023","doi-asserted-by":"crossref","first-page":"329","DOI":"10.1007\/s00521-015-2059-9","article-title":"Multi-retinal disease classification by reduced deep learning features","volume":"28","author":"R Arunkumar","year":"2015","journal-title":"Neural Comput & Applic."},{"key":"pone.0338415.ref024","first-page":"1","article-title":"Bio-medical imaging (X-ray, CT, ultrasound, ECG), genome sequences applications of deep neural network and machine learning in diagnosis, detection, classification, and segmentation of COVID-19: a Meta-analysis & systematic review","author":"YH Bhosale","year":"2023","journal-title":"Multimed Tools Appl."},{"issue":"14","key":"pone.0338415.ref025","doi-asserted-by":"crossref","first-page":"11423","DOI":"10.1007\/s00521-020-05410-8","article-title":"Efficient deep learning approach for augmented detection of Coronavirus disease","volume":"34","author":"A Sedik","year":"2022","journal-title":"Neural Comput Appl."}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0338415","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,6]],"date-time":"2026-01-06T19:19:25Z","timestamp":1767727165000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0338415"}},"subtitle":[],"editor":[{"given":"Ali Mohammad","family":"Alqudah","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,1,6]]},"references-count":25,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,1,6]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0338415","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,6]]}}}