{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,30]],"date-time":"2026-10-30T14:54:08Z","timestamp":1793372048732,"version":"4.5.0"},"reference-count":60,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T00:00:00Z","timestamp":1770940800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T00:00:00Z","timestamp":1770940800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"Vellore Institute of Technology, Vellore"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Eye disease is one of the most conspicuous reasons of optical diminishing and, in certain cases, the prime cause of complete sightlessness. So, there is an urgent need to innovate systems that are capable of spotting eye sicknesses such as glaucoma, cataracts and diabetic retinopathy (DR). To solve this, motivating the necessity for accurate systematized assessment systems, we have advanced a two-backbone deep learning (DL) structure that systematically conglomerates EfficientNetB0 with three harmonizing architectures: ResNet50, InceptionV3, and AlexNet, exercising four different fusion strategies: concatenation, element-wise summation, weighted and majority voting. Using a stable dataset of 4,217 High Resolution retina images across the four symptomatic classes, we have educated and evaluated 12 fusion model arrangements to recognize ideal feature assimilation methodologies. Internal validation exhibited that concatenation fusion attained the great baseline performance, with EfficientNetB0\u2009+\u2009ResNet50 (Exp01) triumph 95.26% accuracy (AUROC: 0.993) and EfficientNetB0\u2009+\u2009InceptionV3 getting 94.79% accuracy (AUROC: 0.989). External validation on 400 images from Messidor-2 and ODIR datasets disclosed significant performance increases, with accuracies oscillating from 94.99% to 97.99% and AUROC values between 0.991 and 0.999, confirmatory authentic cross-dataset generalization rather than overfitting. Weighted and sum fusion strategies evidenced particularly effective for the external dataset, with EfficientNetB0\u2009+\u2009ResNet50 (Exp03) weighted fusion reaching 97.49% accuracy, and EfficientNetB0\u2009+\u2009AlexNet (Exp09) sum fusion accomplished an MCC of 0.980, signifying that intelligent feature combination can counterbalance for architectural boundaries and enhance domain robustness. Class-wise heatmap analysis displayed that while DR triumphed near-perfect detection across all configurations, glaucoma detection improved considerably with weighted, sum, and voting fusion, and reduced misclassifications with normal eye images. Explainability and interpretability examination using Score-CAM (disclosed steady anatomical attention patterns across both datasets: glaucoma models concentrated on the optic nerve head and peripapillary area, DR models emphasized macular zones and vascular structures, and cataract models focused on lens denseness all aligning with traditional medical checkups standards and proven that model decisions are based in pathophysiological relevant features rather than spurious connections. Our findings are that the dual-backbone fusion architectures with improved feature integration strategies, remarkably weighted and sum fusion, produce not only higher analytical accuracy but also strong simplification and clear quick decision-making essential for actual clinical implementation across various imaging locations.<\/jats:p>","DOI":"10.1038\/s41598-026-35357-0","type":"journal-article","created":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T04:32:58Z","timestamp":1770957178000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":13,"title":["Multi-class eye disease classification using deep learning EfficientNetB0 fusion techniques"],"prefix":"10.1038","volume":"16","author":[{"given":"Uday Kumar","family":"Sah","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jyotir Moy","family":"Chatterjee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"R.","family":"Sujatha","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,2,13]]},"reference":[{"key":"35357_CR1","unstructured":"Organizations, W. H. Blindness and vision impairment, 10 August 2023. [Online]. Available: https:\/\/www.who.int\/news-room\/fact-sheets\/detail\/blindness-and-visual-impairment"},{"key":"35357_CR2","unstructured":"Georgia Eye Associates. Diabetic Retinopathy, 24 December 2024. [Online]. Available: https:\/\/www.georgiaeyeassociates.com\/retina-atlanta\/diabetic-retinopathy\/"},{"key":"35357_CR3","first-page":"109507","volume":"185","author":"XL Chao Chen","year":"2025","unstructured":"Chao Chen, X. L. A review of convolutional neural network-based methods for medical image classification. ELSEVIER 185, 109507 (2025).","journal-title":"ELSEVIER"},{"issue":"100216","key":"35357_CR4","first-page":"2772","volume":"4","author":"Pawan Kumar","year":"2023","unstructured":"Kumar, Pawan. Pawan Kumar Mall, A comprehensive review of deep neural networks for medical image processing: recent developments and future opportunities. ELSEVIER (Healthcare Analytics) 4(100216), 2772\u20134425 (2023).","journal-title":"ELSEVIER (Healthcare Analytics)"},{"issue":"1","key":"35357_CR5","first-page":"24","volume":"10","author":"Hamza Hamza Riaz","year":"2020","unstructured":"Hamza Riaz, Hamza. Deep and densely connected networks for classification of diabetic retinopathy. MDPI (Artificial Intell. Diagnostics) 10(1), 24 (2020).","journal-title":"MDPI (Artificial Intell. Diagnostics)"},{"issue":"112194","key":"35357_CR6","first-page":"0031","volume":"171","author":"L Zhao","year":"2026","unstructured":"Zhao, L. Oken pyramid pooling-driven style adapter learning with dual-view balanced loss for imbalanced diabetic retinopathy grading. Elsevier (Pattern recognition) 171(112194), 0031\u20133203 (2026).","journal-title":"Elsevier (Pattern recognition)"},{"issue":"9459","key":"35357_CR7","first-page":"599","volume":"365","author":"A Penny","year":"2005","unstructured":"Penny, A. Age-related cataract. Elsevier (The Lancet) 365(9459), 599\u2013609 (2005).","journal-title":"Elsevier (The Lancet)"},{"issue":"102499","key":"35357_CR8","first-page":"1361","volume":"80","author":"ZXHFYH ,","year":"2022","unstructured":",., Z. X. H. F. Y. H., Y., J. Y., X., R. H., ,., J. L. & Xiaoqing Zhang Attention to region: Region-based integration-and-recalibration networks for nuclear cataract classification using AS-OCT images author links open overlay panel. ELSEVIER (Medical Image Analysis). 80 (102499), 1361\u20138415 (2022).","journal-title":"ELSEVIER (Medical Image Analysis)"},{"issue":"10094","key":"35357_CR9","first-page":"600","volume":"390","author":"Liu Yu-Chi","year":"2017","unstructured":"Yu-Chi, Liu. Cataracts. Elsevier (The Lancet) 390(10094), 600\u2013612 (2017).","journal-title":"Elsevier (The Lancet)"},{"issue":"102926","key":"35357_CR10","first-page":"0933","volume":"154","author":"Xiaoqing Zhang","year":"2024","unstructured":"Zhang, Xiaoqing. Efficient pyramid channel attention network for pathological myopia recognition with pretraining and finetuning. Elsevier (Artificial Intell. Medicine) 154(102926), 0933\u20133657 (2024).","journal-title":"Elsevier (Artificial Intell. Medicine)"},{"issue":"5","key":"35357_CR11","first-page":"1036","volume":"123","author":"TRF D. A. W. M. J","year":"2016","unstructured":"D. A. W. M. J., T. R. F. K. S. N. P. S. T. Y. W. T. J. N. S. R. Brien A. Holden, global prevalence of myopia and high myopia and Temporal trends from 2000 through 2050. ELSEVIER (Ophthalmology). 123 (5), 1036\u20131042 (2016).","journal-title":"ELSEVIER (Ophthalmology)"},{"issue":"105395","key":"35357_CR12","first-page":"0169","volume":"192","author":"Zhang Ziang","year":"2020","unstructured":"Ziang, Zhang. DENSE-INception U-net for medical image segmentation,. Elsevier 192(105395), 0169\u20132607 (2020).","journal-title":"Elsevier"},{"key":"35357_CR13","unstructured":"Tan, Mingxing. EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks. \u00a0ICML 6105\u20136114 (2019)."},{"key":"35357_CR14","unstructured":"I. J., V. V. S. S. Z. W. Christian Szegedy, rethinking the inception architecture for computer vision. IEEE Explore, pp. 1\u20139, (2016)."},{"key":"35357_CR15","unstructured":"Alex Krizhevsky, I. S. G. E. H. ImageNet classification with deep convolutional neural networks, LSVRC-, pp. 1\u20139, 2012., pp. 1\u20139, 2012. (2010)."},{"key":"35357_CR16","unstructured":"Kaiming He, X. Z. S. R. J. S. Deep residual learning for image recognition. IEEE Explore, pp. 1\u20139, (2016)."},{"key":"35357_CR17","unstructured":"Doddi, G. V. eye_diseases_classification, 1 May 2022. [Online]. Available: https:\/\/www.kaggle.com\/datasets\/gunavenkatdoddi\/eye-diseases-classification\/data"},{"key":"35357_CR18","unstructured":"Larxel, O. D. Recognition, Larxel, 01 01 2020. [Online]. Available: https:\/\/www.kaggle.com\/datasets\/andrewmvd\/ocular-disease-recognition-odir5k. [Accessed 12 06 2025]."},{"key":"35357_CR19","unstructured":"MariaHerreroT Messidor-2, Kaggle, 1 January 2021. [Online]. Available: https:\/\/www.kaggle.com\/datasets\/mariaherrerot\/messidor2preprocess. [Accessed 15 November 2025]."},{"key":"35357_CR20","unstructured":",., Z. W. M. D. F. Y. & Haofan Wang, Z. Z. S. D. P. M. X. H. Score-CAM: Score-Weighted Visual Explanations for Convolutional Neural Networks, in IEEE Xplore, Seattle, (2020)."},{"key":"35357_CR21","doi-asserted-by":"crossref","unstructured":"Averkin, E. N. V. A. A. N. Gradient-based Explainable Artificial Intelligence Methods for Eye Disease Classification, International Conference on Neural Networks and Neurotechnologies (NeuroNT), pp. 6\u20139, (2023).","DOI":"10.1109\/NeuroNT58640.2023.10175855"},{"key":"35357_CR22","doi-asserted-by":"crossref","unstructured":"A. H. A. K., M. A. M. R. R. & Abu Kowshir Bitto, M. M. Explainable AI Based Transfer Learning for Multiclass Eye Disease Classification from External Eye Images, International Conference on Quantum Photonics, Artificial Intelligence, and Networking (QPAIN), pp. 1\u20137, 2025. pp. 1\u20137, 2025. (2025).","DOI":"10.1109\/QPAIN66474.2025.11171713"},{"issue":"100402","key":"35357_CR23","first-page":"2590","volume":"26","author":"Moniruzzaman Hemal","year":"2025","unstructured":"Hemal, Moniruzzaman. Explainable deep learning-based meta-classifier approach for multi-label classification of retinal diseases. Elsevier (Array) 26(100402), 2590\u20130056 (2025).","journal-title":"Elsevier (Array)"},{"key":"35357_CR24","doi-asserted-by":"crossref","unstructured":"Marcello Di, A. S. M. C. F. M. F. M. & Giammarco Explainable retinal disease classification and localization through Convolutional Neural Networks, ELSEVIER (Image and Vision Computing), vol. 162, no. 105667, pp. 0262\u20138856, (2025).","DOI":"10.1016\/j.imavis.2025.105667"},{"key":"35357_CR25","unstructured":"Santhosh Kumar, G. N. K. S. B. B N, Machine learning algorithms for ocular disease from fundus images using LBP and HOG. International J. Intell. Syst. Appl. Engineering pp. 3791\u20133798, (2024)."},{"key":"35357_CR26","doi-asserted-by":"crossref","unstructured":"Raghavendra, U. Deep convolution neural network for accurate diagnosis of glaucoma using digital fundus images Author links open overlay panel. Elsevier 41\u201349 (2018).","DOI":"10.1016\/j.ins.2018.01.051"},{"issue":"7","key":"35357_CR27","first-page":"17","volume":"14","author":"Francesco Saverio Sorrentino","year":"2024","unstructured":"Sorrentino, Francesco Saverio. Novel approaches for early detection of retinal diseases using artificial intelligence. PubMed Cent. 14(7), 17 (2024).","journal-title":"PubMed Cent."},{"issue":"1051","key":"35357_CR28","first-page":"1","volume":"10","author":"Ahmed Aizaldeen Abdullah","year":"2024","unstructured":"Abdullah, Ahmed Aizaldeen. Review of eye diseases detection and classification using deep learning techniques. EDP Sci. 10(1051), 1\u201320 (2024).","journal-title":"EDP Sci."},{"key":"35357_CR29","doi-asserted-by":"crossref","unstructured":"L. P. M. P. C. P. e. a. Varun Gulshan PhD. Development and Validation of a Deep Learning Algorithm for Detection of Diabetic Retinopathy in Retinal Fundus Photographs.  JAMA, pp. 2402\u20132410 (2016).","DOI":"10.1001\/jama.2016.17216"},{"key":"35357_CR30","doi-asserted-by":"crossref","unstructured":"Tao, Y. G. K. W. S. G. H. L. H. K. & Li, Diagnostic assessment of deep learning algorithms for diabetic retinopathy screening, ELSEVIER, pp. 511\u2013522 (2019).","DOI":"10.1016\/j.ins.2019.06.011"},{"key":"35357_CR31","first-page":"233339282412348","volume":"11","author":"Khosravi Mohsen","year":"2024","unstructured":"Mohsen, Khosravi. Artificial intelligence and decision-making in healthcare: a thematic analysis of a systematic review of reviews. PubMed Central 11, 23333928241234864 (2024).","journal-title":"PubMed Central"},{"issue":"4","key":"35357_CR32","doi-asserted-by":"crossref","first-page":"309","DOI":"10.1016\/j.jcjo.2018.04.019","volume":"53","author":"T Parampal","year":"2018","unstructured":"Parampal, T. & Grewal, S. Deep learning and computer vision for glaucoma detection: a review. Can. J. Ophthalmol. 53(4), 309\u2013313 (2018).","journal-title":"Can. J. Ophthalmol."},{"issue":"3","key":"35357_CR33","first-page":"101971","volume":"69","author":"Li Tao","year":"2021","unstructured":"Tao, Li. Applications of deep learning in fundus images: a review. Elsevier B V 69(3), 101971 (2021).","journal-title":"Elsevier B V"},{"issue":"14715","key":"35357_CR34","first-page":"1","volume":"2505","author":"OM Zubair","year":"2025","unstructured":"Zubair, O. M. A comprehensive review of techniques, algorithms, advancements, challenges, and clinical applications of multi-modal medical image fusion for improved diagnosis. arXiv preprint 2505(14715), 1\u201333 (2025).","journal-title":"arXiv preprint"},{"key":"35357_CR35","doi-asserted-by":"publisher","first-page":"106959","DOI":"10.1016\/j.compbiomed.2023.106959","volume":"150","author":"Z Tao Zhou","year":"2023","unstructured":"Tao Zhou, Z. Deep learning methods for medical image fusion: a review. Computers in Biology and Medicine 150, 106959 (2023).","journal-title":"Computers in Biology and Medicine"},{"issue":"1","key":"35357_CR36","doi-asserted-by":"publisher","first-page":"7972","DOI":"10.1038\/s41598-024-58665-9","volume":"14","author":"N Liang","year":"2024","unstructured":"Liang, N. Medical image fusion with deep neural networks. Scientific Reports 14(1), 7972 (2024).","journal-title":"Scientific Reports"},{"key":"35357_CR37","doi-asserted-by":"publisher","first-page":"105253","DOI":"10.1016\/j.compbiomed.2022.105253","volume":"144","author":"Adeel Muhammad","year":"2022","unstructured":"Muhammad, Adeel. A review on multimodal medical image fusion: compendious analysis of medical modalities, multimodal databases, fusion techniques and quality metrics. Comput. Biol. Med. 144, 105253 (2022).","journal-title":"Comput. Biol. Med."},{"key":"35357_CR38","doi-asserted-by":"crossref","unstructured":"Y. H. Z. J. X. J. S. F. R. H. J. L. X. Q. Zhang, Machine Learning for Cataract Classification\/Grading on Ophthalmic Imaging Modalities: A Survey,  Springer 19(3), 184\u2013208 (2022).","DOI":"10.1007\/s11633-022-1329-0"},{"key":"35357_CR39","unstructured":"Z. X. J. M. X. W. J. Z. S. Z. R. L. Y. P. J. L. Xiaoqing Zhang, Adaptive Dual-Axis Style-based Recalibration Network with Class-Wise Statistics Loss for Imbalanced Medical Image Classification, IEEE Transactions on Image Processing, 14(8), 1\u201316 (2021)."},{"key":"35357_CR40","doi-asserted-by":"crossref","unstructured":"Prasanna Porwal, S. P. R. K. M. K. G. D. V. S. F. M. Indian Diabetic Retinopathy Image Dataset (IDRiD): A Database for Diabetic Retinopathy Screening Research, Licensee MDPI, Basel, Switzerland, pp. 1\u20138, (2018).","DOI":"10.3390\/data3030025"},{"issue":"4s","key":"35357_CR41","first-page":"4023","volume":"27","author":"BRTS Sathyanarayanan","year":"2024","unstructured":"Sathyanarayanan, B. R. T. S. Confusion Matrix-Based performance evaluation metrics. Afr. J. Bio Med. Res. 27 (4s), 4023\u20134031 (2024).","journal-title":"Afr. J. Bio Med. Res."},{"key":"35357_CR42","unstructured":"M. B. L. \u0160. D. B.-\u0160. Damir Krstini\u0107, Multi-label classifier performance evaluation with confusion matrix, University of Split (ViO - Vision Based Intelligent Observers), University of Split, R. Bo\u0161kovi\u0107a 32, Split 21000, Croatia, 2023."},{"key":"35357_CR43","doi-asserted-by":"publisher","first-page":"40692","DOI":"10.1109\/ACCESS.2023.3267672","volume":"11","author":"L\u0160IS Damir","year":"2023","unstructured":"Damir, L. \u0160I. S. Comments on MLCM: Multi-Label confusion matrix. IEEE Access. 11, 40692\u201340697 (2023).","journal-title":"IEEE Access."},{"key":"35357_CR44","doi-asserted-by":"publisher","first-page":"820","DOI":"10.1162\/tacl_a_00675","volume":"12","author":"J Opitz","year":"2024","unstructured":"Opitz, J. A closer look at classification evaluation metrics and a critical reflection of common evaluation practice. Trans. Association Comput. Linguistics. 12, 820\u2013836 (2024).","journal-title":"Trans. Association Comput. Linguistics"},{"key":"35357_CR45","unstructured":"Szelogowski, D. J. Hebbian Memory-Augmented recurrent networks: engram neurons in deep Learning, arXiv, pp. 2\u201320, (2025)."},{"key":"35357_CR46","unstructured":"Marco Tulio Ribeiro, Sameer Singh, Carlos Guestrin. \u201cWhy Should I Trust You?\u201d Explaining the Predictions of Any Classifier. arXiv 1602(04938v3),1-10 (2016)."},{"key":"35357_CR47","doi-asserted-by":"publisher","first-page":"411","DOI":"10.1016\/j.procs.2024.03.231","volume":"233","author":"RB Ankur Biswasa","year":"2024","unstructured":"Ankur Biswasa, R. B. & Fusion, C. N. N. A promising technique for ophthalmic disorder cnn fusion: a promising technique for ophthalmic disorder diagnosis, elsevier,. Procedia computer science 233, 411\u2013421 (2024).","journal-title":"Procedia computer science"},{"issue":"15","key":"35357_CR48","first-page":"228","volume":"11","author":"CNN Customized","year":"2023","unstructured":"Customized, C. N. N., Models,Wang, Nan-Han. & Lu, Wei-Chang. Classification of color fundus photographs using fusion extracted features and & customized. Healthcare 11(15), 228 (2023).","journal-title":"Healthcare"},{"key":"35357_CR49","doi-asserted-by":"publisher","first-page":"14251","DOI":"10.1007\/s00521-024-09820-w","volume":"36","author":"MA Orhan Sivaz","year":"2024","unstructured":"Orhan Sivaz, M. A. Combining EfficientNet with ML-Decoder classification head for multi-label retinal disease classification. Neural Comput. Appl. 36, 14251\u201314261 (2024).","journal-title":"Neural Comput. Appl."},{"issue":"1","key":"35357_CR50","first-page":"92","volume":"1","author":"HKA Xo\u2019jayev","year":"2024","unstructured":"Xo\u2019jayev, H. K. A. & Qadamboyevich, O. Classification of eye diseases with mobilenetv3 and efficientnetb0 models. Digit. Transformation Artif. Intell. 1(1), 92\u201396 (2024).","journal-title":"Digit. Transformation Artif. Intell."},{"issue":"2","key":"35357_CR51","first-page":"28","volume":"6","author":"I Qureshi","year":"2025","unstructured":"Qureshi, I. AdaptiveSwin-CNN: adaptive Swin-CNN framework with Self-Attention fusion for robust Multi-Class retinal disease diagnosis. MDPI AI. 6 (2), 28 (2025).","journal-title":"MDPI AI"},{"issue":"10","key":"35357_CR52","doi-asserted-by":"publisher","first-page":"1706","DOI":"10.3390\/diagnostics13101706","volume":"13","author":"EMSSAS Ahlam Shamsan","year":"2023","unstructured":"Ahlam Shamsan, E. M. S. S. A. S. Automatic classification of colour fundus images for prediction of eye disease types based on hybrid features. Diagnostics MDPI. 13 (10), 1706 (2023).","journal-title":"Diagnostics MDPI"},{"issue":"23","key":"35357_CR53","doi-asserted-by":"publisher","first-page":"2679","DOI":"10.3390\/diagnostics14232679","volume":"14","author":"MZSY A. K.","year":"2024","unstructured":"A. K., M. Z. S. Y. CAD-EYE: an automated system for multi-eye disease classification using feature fusion with deep learning models and fluorescence imaging for enhanced interpretability. Diagnostics 14(23), 2679 (2024).","journal-title":"Diagnostics"},{"issue":"8","key":"35357_CR54","first-page":"48","volume":"12","author":"MM Rakib","year":"2024","unstructured":"Rakib, M. M. EfficientNet-based model for automated classification of retinal diseases using fundus images. Eur. J. Comput. Sci. Inform. Technol. 12(8), 48\u201361 (2024).","journal-title":"Eur. J. Comput. Sci. Inform. Technol."},{"key":"35357_CR55","doi-asserted-by":"crossref","unstructured":"Dominik M\u00fcller, I. S. R. F. K. Multi-disease detection in retinal imaging based on ensembling heterogeneous deep learning models. Preprint P 6, (2021).","DOI":"10.3233\/SHTI210537"},{"key":"35357_CR56","doi-asserted-by":"publisher","first-page":"77","DOI":"10.5566\/ias.2857","volume":"42","author":"Afsana ahsan jeny","year":"2023","unstructured":"Afsana ahsan jeny. Deep neural network-based ensemble & model for eye diseases detection and classification. Image Anal. Stereol. 42, 77\u201391 (2023).","journal-title":"Image Anal. Stereol."},{"issue":"4","key":"35357_CR57","doi-asserted-by":"publisher","first-page":"480","DOI":"10.25271\/sjuoz.2025.13.4.1593","volume":"13","author":"Oluwasey i Ezekiel Olorunshola","year":"2025","unstructured":"i Ezekiel Olorunshola, Oluwasey, Multi-classification of eye diseases using a cnn-haralick hybrid framework. Sci. J. Univ. Zakho 13(4), 480\u2013489 (2025).","journal-title":"Sci. J. Univ. Zakho"},{"issue":"2","key":"35357_CR58","first-page":"264","volume":"16","author":"A. Ali Alqutayfi","year":"2025","unstructured":"Ali Alqutayfi, A. . Explainable disease classification: exploring grad-CAM analysis of CNNs and ViTs. Journal Adv. Inform. Technol. 16(2), 264\u2013273 (2025).","journal-title":"Journal Adv. Inform. Technol."},{"key":"35357_CR59","unstructured":"a., M. A. B. S. & SamadZamini, K. Explainable deep learning for cataract detection in retinal images: A Dual-Eye and knowledge distillation Approach, arXiv, pp. 1\u201313, (2025)."},{"key":"35357_CR60","first-page":"761","volume":"17","author":"DZBMYLLL Jing","year":"2022","unstructured":"Jing, D. Z. B. M. Y. L. L. L. & Li FIMF score-CAM: fast score-CAM based on local multi-feature integration for visual interpretation of CNNS. IET Image Proc. 17, 761\u2013772 (2022).","journal-title":"IET Image Proc."}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-35357-0","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-35357-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-35357-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T18:12:50Z","timestamp":1781633570000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-35357-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,13]]},"references-count":60,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["35357"],"URL":"https:\/\/doi.org\/10.1038\/s41598-026-35357-0","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,13]]},"assertion":[{"value":"7 August 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 January 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 February 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 March 2026","order":6,"name":"change_date","label":"Change Date","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Update","order":7,"name":"change_type","label":"Change Type","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The original online version of this Article was revised: In this article references  29, 30, 38 and 39, was incorrect and should have been 'Reference 29 should be L. P. M. P. C. P. e. a. Varun Gulshan PhD, \"Development and Validation of a Deep Learning Algorithm for Detection of Diabetic Retinopathy in Retinal Fundus Photographs,\" JAMA, pp. 2402-2410, 2016. Reference 30 should be Tao, Y. G. K. W. S. G. H. L. H. K. & Li, Diagnostic assessment of deep learning algorithms for diabetic retinopathy screening, ELSEVIER, pp. 511 to 522, (2019).  Reference 38 should be Y. H. Z. J. X. J. S. F. R. H. J. L. X. Q. Zhang, \"Machine Learning for Cataract Classification\/Grading on Ophthalmic Imaging Modalities: A Survey,\" Springer, vol. 19, no. 3, p. 184\u2013208, 2022. Reference 39 should be Z. X. J. M. X. W. J. Z. S. Z. R. L. Y. P. J. L. Xiaoqing Zhang, \"Adaptive Dual-Axis Style-based Recalibration Network with Class-Wise Statistics Loss for Imbalanced Medical Image Classification,\" IEEE Transactions on Image Processing, vol. 14, no. 8, pp. 1-16, 2021.' The original article has been corrected.","order":8,"name":"change_details","label":"Change Details","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"}}],"article-number":"6368"}}