{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,24]],"date-time":"2026-10-24T16:10:44Z","timestamp":1792858244711,"version":"4.5.0"},"reference-count":35,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T00:00:00Z","timestamp":1782950400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,7,6]],"date-time":"2026-07-06T00:00:00Z","timestamp":1783296000000},"content-version":"vor","delay-in-days":4,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100009367","name":"Mansoura University","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100009367","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Ophthalmic diagnosis relies heavily on the interpretation of fundus images to identify a range of debilitating diseases. However, the presence of multiple, co-existing pathologies and the subtle visual cues associated with early-stage disease pose a significant challenge, necessitating the development of advanced diagnostic tools. We present DFD-Net (Dual-Branch Fundus Deep Learning Network), a deep learning solution that performs multi-label classification of various ocular diseases. The system achieves this by integrating the attribute maps from bilateral retinal photographs, like those from the right and left eyes. This study starts with a thorough pre-processing operation on the fundus images, represented in image rescaling, black border image cropping, contrast enhancement, and data augmentation of retinal photographs. Following this, the processing pipeline begins with a dual-branch feature extraction framework. A part of the system employs a ConvNeXt architecture to obtain complex semantic characteristics, while the parallel branch employs a U-Net encoder to capture fine-grained, structural characteristics across several scales. These complementary feature representations are then combined via a fusion mechanism. The fused feature representations are subsequently enhanced by a SENet Block for greater robustness through channel-wise recalibration. The resulting feature maps are reduced via Global Average Pooling, and then passed through a Dense layer for feature refinement. Finally, the features are classified by a Softmax output layer, consistent with the single-label multi-class formulation adopted in this work, to identify one of eight possible categories. The testing was implemented on the Ocular Disease Intelligent Recognition-Ophthalmic Image analysis (OIA-ODIR) dataset, which has retinal photographs that represent six distinct ophthalmic categories, macular degeneration, cataracts, glaucoma, hypertension, diabetic retinopathy, and myopia, images that present normal cases, and images that represent multiple other diseases, depicting eight different categories. The proposed DFD-Net system established precision, recall, F1- scores, and overall accuracy of 92.75%, 93.17%, 94.45%, and 93.77% on the On-Site testing collection and 91.50%, 93.19%, 92.11%, and 92.97% on the Off-Site testing collection, respectively. Ultimately, the suggested DFD-Net system proved high efficiency in precisely classifying multiple ocular diseases, offering a novel and outstanding approach for early detection of fundus diseases.<\/jats:p>","DOI":"10.1038\/s41598-026-58277-5","type":"journal-article","created":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T16:10:29Z","timestamp":1783008629000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Dual branch fundus deep learning network as an enhanced multi classification system for ocular disease detection via hybrid feature fusion"],"prefix":"10.1038","volume":"16","author":[{"given":"Naglaa","family":"Samra","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hossam","family":"Moustafa","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mohamed","family":"Aouf","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Waleed Abou","family":"Samra","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mohamed M.","family":"Abdelslam","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,2]]},"reference":[{"key":"58277_CR1","doi-asserted-by":"crossref","unstructured":"Morales-Torre, R., Wing, E. A., Deng, L., Davis, S. W. & Cabeza, R. Visual Recognition Memory of Scenes Is Driven by Categorical, Not Sensory, Visual Representations. Journal Neuroscience 44, (2024).","DOI":"10.1523\/JNEUROSCI.1479-23.2024"},{"key":"58277_CR2","doi-asserted-by":"crossref","unstructured":"Al-Fahdawi, S. et al. Fundus-DeepNet: Multi-label deep learning classification system for enhanced detection of multiple ocular diseases through data fusion of fundus images. Information Fusion 102, (2024).","DOI":"10.1016\/j.inffus.2023.102059"},{"key":"58277_CR3","doi-asserted-by":"publisher","first-page":"367","DOI":"10.1002\/ima.22379","volume":"30","author":"B Keerthiveena","year":"2020","unstructured":"Keerthiveena, B., Esakkirajan, S., Selvakumar, K. & Yogesh, T. Computer-aided diagnosis of retinal diseases using multidomain feature fusion. Int. J. Imaging Syst. Technol. 30, 367\u2013379 (2020).","journal-title":"Int. J. Imaging Syst. Technol."},{"key":"58277_CR4","doi-asserted-by":"publisher","unstructured":"Lim, G. et al. Different fundus imaging modalities and technical factors in AI screening for diabetic retinopathy: a review. Eye and Vision vol. 7 Preprint at (2020). https:\/\/doi.org\/10.1186\/s40662-020-00182-7","DOI":"10.1186\/s40662-020-00182-7"},{"key":"58277_CR5","doi-asserted-by":"crossref","unstructured":"Li, N., Li, T., Hu, C., Wang, K. & Kang, H. A. Benchmark of Ocular Disease Intelligent Recognition: One Shot for Multi-disease Detection. (2021). http:\/\/arxiv.org\/abs\/2102.07978","DOI":"10.1007\/978-3-030-71058-3_11"},{"key":"58277_CR6","doi-asserted-by":"crossref","unstructured":"Tamim, N., Elshrkawey, M., Azim, G. A. & Nassar, H. Retinal blood vessel segmentation using hybrid features and multi-layer perceptron neural networks. Symmetry (Basel) 12, (2020).","DOI":"10.3390\/sym12060894"},{"key":"58277_CR7","doi-asserted-by":"crossref","unstructured":"Gour, N. & Khanna, P. Multi-class multi-label ophthalmological disease detection using transfer learning based convolutional neural network. Biomed Signal. Process. Control 66, (2021).","DOI":"10.1016\/j.bspc.2020.102329"},{"key":"58277_CR8","doi-asserted-by":"crossref","unstructured":"Dobrzycki, A. D., Bernardos, A. M. & Casar, J. R. An Analysis of Layer-Freezing Strategies for Enhanced Transfer Learning in YOLO Architectures. Mathematics 13, (2025).","DOI":"10.3390\/math13152539"},{"key":"58277_CR9","doi-asserted-by":"crossref","unstructured":"Kavita, M., Shinde, D. & Wankhade, N. R. Deep Learning-Based Detection of Diabetic Retinopathy Using Retina Images. Journal of Information Systems Engineering and Management 10 (2024). (2025).","DOI":"10.52783\/jisem.v10i37s.6760"},{"key":"58277_CR10","doi-asserted-by":"publisher","first-page":"86657","DOI":"10.1007\/s11042-024-19687-7","volume":"83","author":"SP Singh","year":"2024","unstructured":"Singh, S. P., Gupta, P. & Dung, R. Diabetic retinopathy detection by fundus images using fine tuned deep learning model. Multimed Tools Appl. 83, 86657\u201386679 (2024).","journal-title":"Multimed Tools Appl."},{"key":"58277_CR11","doi-asserted-by":"publisher","first-page":"3089","DOI":"10.1016\/j.ygeno.2020.05.017","volume":"112","author":"B Kishore","year":"2020","unstructured":"Kishore, B. & Ananthamoorthy, N. P. Glaucoma classification based on intra-class and extra-class discriminative correlation and consensus ensemble classifier. Genomics 112, 3089\u20133096 (2020).","journal-title":"Genomics"},{"key":"58277_CR12","doi-asserted-by":"publisher","unstructured":"Marques, R. et al. Automatic Segmentation of the Optic Nerve Head Region in Optical Coherence Tomography: A Methodological Review. Computer Methods and Programs in Biomedicine vol. 220 Preprint at (2022). https:\/\/doi.org\/10.1016\/j.cmpb.2022.106801","DOI":"10.1016\/j.cmpb.2022.106801"},{"key":"58277_CR13","doi-asserted-by":"crossref","unstructured":"Xiong, H., Liu, S., Sharan, R. V., Coiera, E. & Berkovsky, S. Weak label based Bayesian U-Net for optic disc segmentation in fundus images. Artif Intell. Med 126, (2022).","DOI":"10.1016\/j.artmed.2022.102261"},{"key":"58277_CR14","doi-asserted-by":"crossref","unstructured":"Rauf, N., Gilani, S. O. & Waris, A. Automatic detection of pathological myopia using machine learning. Sci Rep 11, (2021).","DOI":"10.1038\/s41598-021-95205-1"},{"key":"58277_CR15","doi-asserted-by":"crossref","unstructured":"Ishtiaq, U., Abdullah, E. R. M. F. & Ishtiaque, Z. A Hybrid Technique for Diabetic Retinopathy Detection Based on Ensemble-Optimized CNN and Texture Features. Diagnostics 13, (2023).","DOI":"10.3390\/diagnostics13101816"},{"key":"58277_CR16","doi-asserted-by":"publisher","unstructured":"Li, Z. et al. Artificial intelligence in ophthalmology: The path to the real-world clinic. Cell Reports Medicine vol. 4 Preprint at (2023). https:\/\/doi.org\/10.1016\/j.xcrm.2023.101095","DOI":"10.1016\/j.xcrm.2023.101095"},{"key":"58277_CR17","first-page":"1379","volume":"48","author":"JEW Koh","year":"2018","unstructured":"Koh, J. E. W., Ng, E. Y. K., Bhandary, S. V. & Laude, A. Acharya, U. R. Automated detection of retinal health using PHOG and SURF features extracted from fundus images. Appl. Intell. 48, 1379\u20131393 (2018).","journal-title":"Appl. Intell."},{"key":"58277_CR18","doi-asserted-by":"publisher","unstructured":"Islam, M. T., Imran, S. A., Arefeen, A., Hasan, M. & Shahnaz, C. Source and Camera Independent Ophthalmic Disease Recognition from Fundus Image Using Neural Network. in IEEE International Conference on Signal Processing, Information, Communication and Systems, SPICSCON 2019 59\u201363 (Institute of Electrical and Electronics Engineers Inc., 2019). 59\u201363 (Institute of Electrical and Electronics Engineers Inc., 2019). (2019). https:\/\/doi.org\/10.1109\/SPICSCON48833.2019.9065162","DOI":"10.1109\/SPICSCON48833.2019.9065162"},{"key":"58277_CR19","doi-asserted-by":"publisher","unstructured":"Yang, X. & Yi, S. li. Multi-classification of fundus diseases based on DSRA-CNN. Biomedical Signal Processing and Control vol. 77 Preprint at (2022). https:\/\/doi.org\/10.1016\/j.bspc.2022.103763","DOI":"10.1016\/j.bspc.2022.103763"},{"key":"58277_CR20","doi-asserted-by":"crossref","unstructured":"Zhang, H. et al. BCU-Net: Bridging ConvNeXt and U-Net for medical image segmentation. Comput Biol. Med 159, (2023).","DOI":"10.1016\/j.compbiomed.2023.106960"},{"key":"58277_CR21","doi-asserted-by":"crossref","unstructured":"Huang, X. et al. A 3D ConvLSTM-CNN network based on multi-channel color extraction for ultra-short-term solar irradiance forecasting. Energy 272, (2023).","DOI":"10.1016\/j.energy.2023.127140"},{"key":"58277_CR22","doi-asserted-by":"publisher","first-page":"57","DOI":"10.1016\/j.procs.2022.12.111","volume":"216","author":"M Hayati","year":"2022","unstructured":"Hayati, M. et al. Impact of CLAHE-based image enhancement for diabetic retinopathy classification through deep learning. Procedia Comput. Sci. 216, 57\u201366 (2022). Elsevier B.V.","journal-title":"Procedia Comput. Sci."},{"key":"58277_CR23","doi-asserted-by":"publisher","unstructured":"Al-Ameen, Z. & Mahmood, B. Sharpness Enhancement of Archaeological Images Using Gr\u00fcnwald-Letnikov Weights with Unsharp Masking. https:\/\/doi.org\/10.18420\/inf2025_71 doi:10.18420\/inf2025_71.","DOI":"10.18420\/inf2025_71"},{"key":"58277_CR24","unstructured":"Segu, M., Tonioni, A. & Tombari, F. Batch Normalization Embeddings for Deep Domain Generalization. (2021). http:\/\/arxiv.org\/abs\/2011.12672"},{"key":"58277_CR25","unstructured":"Hendrycks, D. & Gimpel, K. Gaussian Error Linear Units (GELUs). (2023). http:\/\/arxiv.org\/abs\/1606.08415"},{"key":"58277_CR26","unstructured":"Li, M. et al. Ms-senet: Enhancing Speech Emotion Recognition Through Multi-scale Feature Fusion With Squeeze-and-excitation Blocks. (2023). http:\/\/arxiv.org\/abs\/2312.11974"},{"key":"58277_CR27","doi-asserted-by":"crossref","unstructured":"Zhao, L. & Zhang, Z. A improved pooling method for convolutional neural networks. Sci Rep 14, (2024).","DOI":"10.1038\/s41598-024-51258-6"},{"key":"58277_CR28","unstructured":"Shen, K. et al. A Study on ReLU and Softmax in Transformer. (2023). http:\/\/arxiv.org\/abs\/2302.06461"},{"key":"58277_CR29","doi-asserted-by":"crossref","unstructured":"Yilmaz, A. E. & Demirhan, H. Weighted kappa measures for ordinal multi-class classification performance. Appl Soft Comput 134, (2023).","DOI":"10.1016\/j.asoc.2023.110020"},{"key":"58277_CR30","doi-asserted-by":"publisher","first-page":"1","DOI":"10.21608\/ijt.2025.411907.1130","volume":"05","author":"IAA Mohammed","year":"2025","unstructured":"Mohammed, I. A. A., Bakr, N. S., Moustafa, H., Moustafa, A. F. M. & Amer, H. M. Leveraging Nature-Inspired Search to Boost CNN Performance in Colorectal Cancer Classification. Int. J. Telecommunications. 05, 1\u201320 (2025).","journal-title":"Int. J. Telecommunications"},{"key":"58277_CR31","unstructured":"Tabachnick, B. G. & Fidell, L. S. Experimental Designs Using ANOVA (Thomson\/Brooks\/Cole, 2007)."},{"key":"58277_CR32","doi-asserted-by":"crossref","unstructured":"Mcnemar, Q. NOTE ON THE SAMPLING ERROR OF THE DIFFERENCE BETWEEN CORRELATED PROPORTIONS OR PERCENTAGES. rS\u2019YCHOM\u2009~\u2009m.XKA vol. 12.","DOI":"10.1007\/BF02295996"},{"key":"58277_CR33","doi-asserted-by":"publisher","first-page":"261","DOI":"10.1038\/s41592-019-0686-2","volume":"17","author":"P Virtanen","year":"2020","unstructured":"Virtanen, P. et al. SciPy 1.0: fundamental algorithms for scientific computing in Python. Nat. Methods. 17, 261\u2013272 (2020).","journal-title":"Nat. Methods"},{"key":"58277_CR34","doi-asserted-by":"crossref","unstructured":"He, J., Li, C., Ye, J., Qiao, Y. & Gu, L. Multi-label ocular disease classification with a dense correlation deep neural network. Biomed Signal. Process. Control 63, (2021).","DOI":"10.1016\/j.bspc.2020.102167"},{"key":"58277_CR35","doi-asserted-by":"crossref","unstructured":"Ou, X. et al. BFENet: A two-stream interaction CNN method for multi-label ophthalmic diseases classification with bilateral fundus images. Comput Methods Programs Biomed 219, (2022).","DOI":"10.1016\/j.cmpb.2022.106739"}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-58277-5","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-58277-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-58277-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,6]],"date-time":"2026-07-06T15:05:33Z","timestamp":1783350333000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-58277-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,2]]},"references-count":35,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["58277"],"URL":"https:\/\/doi.org\/10.1038\/s41598-026-58277-5","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,2]]},"assertion":[{"value":"26 March 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 June 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 July 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}},{"value":"This research involved no studies requiring the participation of human subjects or animals by any of the contributing authors.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}}],"article-number":"20794"}}