{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,30]],"date-time":"2026-10-30T20:54:03Z","timestamp":1793393643911,"version":"4.5.0"},"reference-count":41,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,7,2]],"date-time":"2025-07-02T00:00:00Z","timestamp":1751414400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Med."],"abstract":"<jats:p>Retinal diseases are among the leading causes of blindness worldwide, requiring early detection for effective treatment. Manual interpretation of ophthalmic imaging, such as optical coherence tomography (OCT), is traditionally time-consuming, prone to inconsistencies, and requires specialized expertise in ophthalmology. This study introduces OculusNet, an efficient and explainable deep learning (DL) approach for detecting retinal diseases using OCT images. The proposed method is specifically tailored for complex medical image patterns in OCTs to identify retinal disorders, such as choroidal neovascularization (CNV), diabetic macular edema (DME), and age-related macular degeneration characterized by drusen. The model benefits from Saliency Map visualization, an Explainable AI (XAI) technique, to interpret and explain how it reaches conclusions when identifying retinal disorders. Furthermore, the proposed model is deployed on a web page, allowing users to upload retinal OCT images and receive instant detection results. This deployment demonstrates significant potential for integration into ophthalmic departments, enhancing diagnostic accuracy and efficiency. In addition, to ensure an equitable comparison, a transfer learning approach has been applied to four pre-trained models: VGG19, MobileNetV2, VGG16, and DenseNet-121. Extensive evaluation reveals that the proposed OculusNet model achieves a test accuracy of 95.48% and a validation accuracy of 98.59%, outperforming all other models in comparison. Moreover, to assess the proposed model's reliability and generalizability, the Matthews Correlation Coefficient and Cohen's Kappa Coefficient have been computed, validating that the model can be applied in practical clinical settings to unseen data.<\/jats:p>","DOI":"10.3389\/fmed.2025.1596726","type":"journal-article","created":{"date-parts":[[2025,7,2]],"date-time":"2025-07-02T01:52:46Z","timestamp":1751421166000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["OculusNet: Detection of retinal diseases using a tailored web-deployed neural network and saliency maps for explainable AI"],"prefix":"10.3389","volume":"12","author":[{"given":"Muhammad","family":"Umair","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jawad","family":"Ahmad","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Oumaima","family":"Saidani","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mohammed S.","family":"Alshehri","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alanoud","family":"Al Mazroa","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Muhammad","family":"Hanif","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rahmat","family":"Ullah","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Muhammad Shahbaz","family":"Khan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2025,7,2]]},"reference":[{"key":"B1","doi-asserted-by":"crossref","DOI":"10.1007\/978-94-024-1713-5","volume-title":"Vitamin C in Human Health and Disease: Effects, Mechanisms of Action, and New Guidance on Intake","author":"Lee","year":"2019"},{"key":"B2","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1371\/journal.pone.0288879","article-title":"Association of OCT biomarkers and visual impairment in patients with diabetic macular oedema with vitreomacular adhesion","volume":"18","author":"Subramanian","year":"2023","journal-title":"PLoS ONE"},{"key":"B3","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1371\/journal.pone.0306794","article-title":"VMseg: Using spatial variance to automatically segment retinal non-perfusion on OCT-angiography","volume":"19","author":"Le Boite","year":"2024","journal-title":"PLoS ONE"},{"key":"B4","doi-asserted-by":"publisher","first-page":"1122","DOI":"10.1016\/j.cell.2018.02.010","article-title":"Identifying medical diagnoses and treatable diseases by image-based deep learning","volume":"172","author":"Kermany","year":"2018","journal-title":"Cell"},{"key":"B5","doi-asserted-by":"publisher","first-page":"162","DOI":"10.1016\/j.ophtha.2013.07.013","article-title":"Quantitative classification of eyes with and without intermediate age-related macular degeneration using optical coherence tomography","volume":"121","author":"Farsiu","year":"2014","journal-title":"Ophthalmology"},{"key":"B6","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1371\/journal.pone.0305741","article-title":"Exploring laser-induced acute and chronic retinal vein occlusion mouse models: Development, temporal in vivo imaging, and application perspectives","volume":"19","author":"Xu","year":"2024","journal-title":"PLoS ONE"},{"key":"B7","doi-asserted-by":"publisher","first-page":"91","DOI":"10.18201\/ijisae.2021.236","article-title":"Artificial Intelligence Hybrid System for Enhancing Retinal Diseases Classification Using Automated Deep Features Extracted from OCT Images","volume":"9","author":"Alqudah","year":"2021","journal-title":"Int J Intell Syst Applic Eng"},{"key":"B8","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1016\/j.preteyeres.2013.10.002","article-title":"Progress on retinal image analysis for age related macular degeneration","volume":"38","author":"Kanagasingam","year":"2014","journal-title":"Prog Retin Eye Res"},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.1117\/12.2543819","article-title":"Widely tunable electrically pumped 1050nm MEMS-VCSELs for optical coherence tomography","author":"Jayaraman","year":"2020","journal-title":"Vertical-Cavity Surface-Emitting Lasers XXIV"},{"key":"B10","doi-asserted-by":"publisher","first-page":"990","DOI":"10.1002\/jemt.23063","article-title":"Diabetic retinopathy detection and classification using hybrid feature set","volume":"81","author":"Amin","year":"2018","journal-title":"Microsc Res Tech"},{"key":"B11","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1007\/s11517-019-02066-y","article-title":"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":"B12","doi-asserted-by":"publisher","first-page":"45","DOI":"10.1016\/j.preteyeres.2007.07.005","article-title":"State-of-the-art retinal optical coherence tomography","volume":"27","author":"Drexler","year":"2008","journal-title":"Prog Retin Eye Res"},{"key":"B13","doi-asserted-by":"publisher","first-page":"217","DOI":"10.1016\/S0161-6420(95)31032-9","article-title":"Imaging of macular diseases with optical coherence tomography","volume":"102","author":"Puliafito","year":"1995","journal-title":"Ophthalmology"},{"key":"B14","doi-asserted-by":"publisher","first-page":"1178","DOI":"10.1126\/science.1957169","article-title":"Optical coherence tomography","volume":"254","author":"Huang","year":"1991","journal-title":"Science"},{"key":"B15","doi-asserted-by":"publisher","first-page":"889","DOI":"10.1364\/OE.11.000889","article-title":"Performance of Fourier domain vs. time domain optical coherence tomography","volume":"11","author":"Leitgeb","year":"2003","journal-title":"Optics Expr"},{"key":"B16","doi-asserted-by":"publisher","first-page":"1704","DOI":"10.1364\/OL.22.001704","article-title":"Optical frequency-domain reflectometry using rapid wavelength tuning of a Cr4+:forsterite laser","volume":"22","author":"Golubovic","year":"1997","journal-title":"Opt Lett"},{"key":"B17","doi-asserted-by":"publisher","first-page":"171165","DOI":"10.1016\/j.ijleo.2023.171165","article-title":"review on texture-based methods for anomaly detection in retinal optical coherence tomography images","volume":"288","author":"Monemian","year":"2023","journal-title":"Optik"},{"key":"B18","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1371\/journal.pone.0307317","article-title":"deep learning framework for the early detection of multi-retinal diseases","volume":"19","author":"Ejaz","year":"2024","journal-title":"PLoS ONE"},{"key":"B19","doi-asserted-by":"publisher","first-page":"305","DOI":"10.1016\/B978-0-443-18450-5.00009-8","article-title":"Chapter 12 - Artificial intelligence-based retinal disease classification using optical coherence tomography images","author":"Patnaik","year":"2023","journal-title":"Applications of Artificial Intelligence in Medical Imaging"},{"key":"B20","doi-asserted-by":"publisher","first-page":"314","DOI":"10.29194\/NJES.26040314","article-title":"Simplified convolutional neural network model for automatic classification of retinal diseases from optical coherence tomography images","volume":"26","author":"Khalaf","year":"2024","journal-title":"Al-Nahrain J Eng Sci"},{"key":"B21","doi-asserted-by":"publisher","first-page":"8901","DOI":"10.1088\/0031-9155\/60\/22\/8901","article-title":"New variational image decomposition model for simultaneously denoising and segmenting optical coherence tomography images","volume":"60","author":"Duan","year":"2015","journal-title":"Phys Med Biol"},{"key":"B22","doi-asserted-by":"publisher","first-page":"906","DOI":"10.1007\/s12539-022-00533-z","article-title":"Deep residual network for diagnosis of retinal diseases using optical coherence tomography images","volume":"14","author":"Asif","year":"2022","journal-title":"Interdisc Sci"},{"key":"B23","doi-asserted-by":"crossref","DOI":"10.1117\/12.808543","article-title":"Automated retinal pigment epithelium identification from optical coherence tomography images","volume-title":"Proceedings Volume 7168, Optical Coherence Tomography and Coherence Domain Optical Methods in Biomedicine XIII; SPIE BiOS","author":"Fabritius","year":"2009"},{"key":"B24","doi-asserted-by":"publisher","first-page":"105619","DOI":"10.1016\/j.bspc.2023.105619","article-title":"Deep learning network (DL-Net) based classification and segmentation of multi-class retinal diseases using OCT scans","volume":"88","author":"Muni Nagamani","year":"2024","journal-title":"Biomed Signal Process Control"},{"key":"B25","doi-asserted-by":"publisher","first-page":"1168","DOI":"10.1109\/TMI.2020.3048975","article-title":"Semi-supervised capsule cGAN for speckle noise reduction in retinal OCT images","volume":"40","author":"Wang","year":"2021","journal-title":"IEEE Trans Med Imag"},{"key":"B26","doi-asserted-by":"publisher","first-page":"5261","DOI":"10.1109\/LRA.2021.3072574","article-title":"Semi-automated extraction of lens fragments via a surgical robot using semantic segmentation of OCT images with deep learning - experimental results in ex vivo animal model","volume":"6","author":"Shin","year":"2021","journal-title":"IEEE Robot Autom Lett"},{"key":"B27","doi-asserted-by":"crossref","first-page":"37","DOI":"10.1109\/ICENCO49778.2020.9357324","article-title":"Automatic classification of retinal eye diseases from optical coherence tomography using transfer learning","volume-title":"2020 16th International Computer Engineering Conference (ICENCO)","author":"Adel","year":"2020"},{"key":"B28","doi-asserted-by":"crossref","first-page":"281","DOI":"10.1109\/CBMS.2019.00066","article-title":"Identifying diabetic retinopathy from OCT images using deep transfer learning with artificial neural networks","volume-title":"2019 IEEE 32nd International Symposium on Computer-Based Medical Systems (CBMS)","author":"Islam","year":"2019"},{"key":"B29","doi-asserted-by":"publisher","first-page":"1803","DOI":"10.1007\/s00417-021-05104-4","article-title":"Classification of pachychoroid on optical coherence tomography using deep learning","volume":"259","author":"Kang","year":"2021","journal-title":"Graefe's Arch Clin Exper Ophthalmol"},{"key":"B30","doi-asserted-by":"publisher","first-page":"1110","DOI":"10.1097\/IAE.0000000000002992","article-title":"Detection of morphologic patterns of diabetic macular edema using a deep learning approach based on optical coherence tomography images","volume":"41","author":"Wu","year":"2021","journal-title":"Retina"},{"key":"B31","doi-asserted-by":"crossref","first-page":"206","DOI":"10.1109\/CAIDA51941.2021.9425161","article-title":"Deep learning-based automatic detection of central serous retinopathy using optical coherence tomographic images","author":"Hassan","year":"2021","journal-title":"2021 1st International Conference on Artificial Intelligence and Data Analytics (CAIDA)."},{"key":"B32","doi-asserted-by":"publisher","first-page":"78125","DOI":"10.1007\/s11042-024-18627-9","article-title":"Towards improved fundus disease detection using Swin Transformers","volume":"83","author":"Jawad","year":"2024","journal-title":"Multimed Tools Appl"},{"key":"B33","doi-asserted-by":"publisher","first-page":"103935","DOI":"10.1016\/j.bspc.2022.103935","article-title":"Deep and dense convolutional neural network for multi category classification of magnification specific and magnification independent breast cancer histopathological images","volume":"78","author":"Abdul Jawad","year":"2022","journal-title":"Biomed Signal Process Control"},{"key":"B34","doi-asserted-by":"publisher","first-page":"106299","DOI":"10.1016\/j.bspc.2024.106299","article-title":"A novel approach for color-balanced reference image selection for breast histology image normalization","volume":"94","author":"Abdul Jawad","year":"2024","journal-title":"Biomed Signal Process Control"},{"key":"B35","doi-asserted-by":"publisher","first-page":"219","DOI":"10.3390\/jimaging9100219","article-title":"Evaluating retinal disease diagnosis with an interpretable lightweight CNN model resistant to adversarial attacks","volume":"9","author":"Bhandari","year":"2023","journal-title":"J Imaging"},{"key":"B36","author":"Kermany","year":"2018","journal-title":"Labeled optical coherence tomography (OCT) and chest X-ray images for classification"},{"key":"B37","doi-asserted-by":"publisher","first-page":"3235","DOI":"10.1007\/s13042-020-01248-7","article-title":"IoT enabled depthwise separable convolution neural network with deep support vector machine for COVID-19 diagnosis and classification","volume":"12","author":"Le","year":"2021","journal-title":"Int J Mach Learn Cybern"},{"key":"B38","doi-asserted-by":"publisher","first-page":"104837","DOI":"10.1016\/j.compbiomed.2021.104837","article-title":"A depthwise separable dense convolutional network with convolution block attention module for COVID-19 diagnosis on CT scans","volume":"137","author":"Li","year":"2021","journal-title":"Comput Biol Med"},{"key":"B39","doi-asserted-by":"publisher","first-page":"5813","DOI":"10.3390\/s21175813","article-title":"Detection of COVID-19 using transfer learning and grad-CAM visualization on indigenously collected x-ray dataset","volume":"21","author":"Umair","year":"2021","journal-title":"Sensors"},{"key":"B40","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1371\/journal.pone.0296175","article-title":"Explainable ensemble learning method for OCT detection with transfer learning","volume":"19","author":"Yang","year":"2024","journal-title":"PLoS ONE"},{"key":"B41","doi-asserted-by":"publisher","first-page":"106156","DOI":"10.1016\/j.compbiomed.2022.106156","article-title":"Explanatory classification of CXR images into COVID-19, Pneumonia and Tuberculosis using deep learning and XAI","volume":"150","author":"Bhandari","year":"2022","journal-title":"Comput Biol Med"}],"container-title":["Frontiers in Medicine"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2025.1596726\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,2]],"date-time":"2025-07-02T01:52:49Z","timestamp":1751421169000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2025.1596726\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,2]]},"references-count":41,"alternative-id":["10.3389\/fmed.2025.1596726"],"URL":"https:\/\/doi.org\/10.3389\/fmed.2025.1596726","relation":{},"ISSN":["2296-858X"],"issn-type":[{"value":"2296-858X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7,2]]},"article-number":"1596726"}}