{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,13]],"date-time":"2026-11-13T03:39:58Z","timestamp":1794541198095,"version":"4.9.1"},"reference-count":74,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T00:00:00Z","timestamp":1779926400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T00:00:00Z","timestamp":1786060800000},"content-version":"vor","delay-in-days":71,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>As the major cause of sight impairment in working age adults is diabetic retinopathy (DR) which requires timely and proper diagnosis to avoid the irreversible vision loss. Traditional retinal fundus image based manual diagnosis is time consuming, subjective, and requires highly skilled ophthalmologists, and therefore is not scalable in resource constrained environments. Automated DR grading systems are essential to overcome this issue especially in underserved areas. Although Convolutional Neural Networks (CNNs) are suitable in capturing the fine grained local features namely Microaneurysms and exudates, they are incapable of considering the global retinal context, which is required to accurately grade the severity. Transformer models, on the other hand, are more effective in capturing long range dependencies, at the cost of low spatial resolution. To address these shortcomings, this research suggests Fusion Net a hybrid DL model that combines a CNN branch that extracts local features in the form of GoogLeNet with a Vision Transformer (ViT) branch that captures global context. This is a dual stream architecture that combines complementary embeddings to categorize DR into five ordinal levels of severity. The model has been trained on a mixed dataset of APTOS 2019 and Messidor-2 and tested on three datasets that are not used during training. Fusion Net had overall accuracy percent of 98.85, AUC-ROC of 0.981 and weighted F1-score percent of 97.62. It was also highly sensitive in detecting early stage DR and balanced in all the severity levels. The thorough ablation experiments, ordinal assessment scales, and feature map confirms the strength and clarity of the suggested framework. The findings indicate that Fusion Net is an effective, explainable, and computationally efficient system to use in grading automated DR with a high chance of implementation into clinical practice and tele-ophthalmology systems.<\/jats:p>","DOI":"10.1038\/s41598-026-50608-w","type":"journal-article","created":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T01:35:15Z","timestamp":1779932115000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["AI driven Hybrid CNN transformer model for early detection and severity assessment of diabetic retinopathy"],"prefix":"10.1038","volume":"16","author":[{"given":"Priyadharshini","family":"Sekar","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kanaga Suba Raja","family":"S","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,5,28]]},"reference":[{"issue":"4","key":"50608_CR1","doi-asserted-by":"publisher","first-page":"293","DOI":"10.4103\/0974-9233.120007","volume":"20","author":"P Scanlon","year":"2013","unstructured":"Scanlon, P., Aldington, S. & Stratton, I. Epidemiological issues in diabetic retinopathy. Middle East Afr. J. Ophthalmol. 20(4), 293. https:\/\/doi.org\/10.4103\/0974-9233.120007 (2013).","journal-title":"Middle East Afr. J. Ophthalmol."},{"issue":"5","key":"50608_CR2","doi-asserted-by":"publisher","first-page":"306","DOI":"10.1016\/j.jdiacomp.2006.08.002","volume":"21","author":"SD Candrilli","year":"2007","unstructured":"Candrilli, S. D., Davis, K. L., Kan, H. J., Lucero, M. A. & Rousculp, M. D. Prevalence and the associated burden of illness of symptoms of diabetic peripheral neuropathy and diabetic retinopathy. J. Diabetes Complic. 21(5), 306\u2013314. https:\/\/doi.org\/10.1016\/j.jdiacomp.2006.08.002 (2007).","journal-title":"J. Diabetes Complic."},{"issue":"3","key":"50608_CR3","doi-asserted-by":"publisher","first-page":"467","DOI":"10.1111\/dom.13550","volume":"21","author":"I Pearce","year":"2019","unstructured":"Pearce, I., Sim\u00f3, R., L\u00f6vestam-Adrian, M., Wong, D. T. & Evans, M. Association between diabetic eye disease and other complications of diabetes: Implications for care. A systematic review. Diabetes Obes. Metab. 21(3), 467\u2013478. https:\/\/doi.org\/10.1111\/dom.13550 (2019).","journal-title":"Diabetes Obes. Metab."},{"key":"50608_CR4","doi-asserted-by":"publisher","DOI":"10.3389\/fmed.2023.1293019","volume":"10","author":"H Xu","year":"2024","unstructured":"Xu, H., Shao, X., Fang, D. & Huang, F. A hybrid neural network approach for classifying diabetic retinopathy subtypes. Front. Med. 10, 1293019. https:\/\/doi.org\/10.3389\/fmed.2023.1293019 (2024).","journal-title":"Front. Med."},{"issue":"22","key":"50608_CR5","doi-asserted-by":"publisher","DOI":"10.3390\/app142210658","volume":"14","author":"H-J Kim","year":"2024","unstructured":"Kim, H.-J., Eesaar, H. & Chong, K. T. Transformer-enhanced retinal vessel segmentation for diabetic retinopathy detection using attention mechanisms and multi-scale fusion. Applied Sciences 14(22), 10658. https:\/\/doi.org\/10.3390\/app142210658 (2024).","journal-title":"Applied Sciences"},{"issue":"3","key":"50608_CR6","doi-asserted-by":"publisher","first-page":"608","DOI":"10.1109\/TBME.2017.2707578","volume":"65","author":"SS Kar","year":"2018","unstructured":"Kar, S. S. & Maity, S. P. Automatic detection of retinal lesions for screening of diabetic retinopathy. IEEE Trans. Biomed. Eng. 65(3), 608\u2013618. https:\/\/doi.org\/10.1109\/TBME.2017.2707578 (2018).","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"50608_CR7","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1016\/j.neucom.2018.04.034","volume":"303","author":"C Bai","year":"2018","unstructured":"Bai, C., Huang, L., Pan, X., Zheng, J. & Chen, S. Optimization of deep convolutional neural network for large scale image retrieval. Neurocomputing 303, 60\u201367. https:\/\/doi.org\/10.1016\/j.neucom.2018.04.034 (2018).","journal-title":"Neurocomputing"},{"issue":"12","key":"50608_CR8","doi-asserted-by":"publisher","first-page":"10297","DOI":"10.1109\/TPAMI.2024.3445463","volume":"46","author":"C Chen","year":"2024","unstructured":"Chen, C. et al. A survey on graph neural networks and graph transformers in computer vision: A task-oriented perspective. IEEE Trans. Pattern Anal. Mach. Intell. 46(12), 10297\u201310318 (2024).","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"5","key":"50608_CR9","doi-asserted-by":"publisher","first-page":"187","DOI":"10.3390\/computers14050187","volume":"14","author":"W Zhang","year":"2025","unstructured":"Zhang, W., Belcheva, V. & Ermakova, T. Interpretable deep learning for diabetic retinopathy: A comparative study of CNN, ViT, and hybrid architectures. Computers 14(5), 187. https:\/\/doi.org\/10.3390\/computers14050187 (2025).","journal-title":"Computers"},{"key":"50608_CR10","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2024.10735","volume":"103","author":"Y Liu","year":"2025","unstructured":"Liu, Y. et al. STMF-DRNet: A multi-branch fine-grained classification model for diabetic retinopathy using Swin-TransformerV2. Biomed. Signal Process. Control 103, 107352. https:\/\/doi.org\/10.1016\/j.bspc.2024.10735 (2025).","journal-title":"Biomed. Signal Process. Control"},{"key":"50608_CR11","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3326528","volume":"11","author":"W Nazih","year":"2023","unstructured":"Nazih, W., Aseeri, A. O., Atallah, O. Y. & El-Sappagh, S. Vision transformer model for predicting the severity of diabetic retinopathy in fundus photography-based retina images. IEEE Access 11, 117546 117561. https:\/\/doi.org\/10.1109\/ACCESS.2023.3326528 (2023).","journal-title":"IEEE Access"},{"issue":"22","key":"50608_CR12","doi-asserted-by":"publisher","first-page":"2402","DOI":"10.1001\/jama.2016.17216","volume":"316","author":"V Gulshan","year":"2016","unstructured":"Gulshan, V. et al. Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs. JAMA 316(22), 2402\u20132410. https:\/\/doi.org\/10.1001\/jama.2016.17216 (2016).","journal-title":"JAMA"},{"key":"50608_CR13","doi-asserted-by":"publisher","first-page":"40019","DOI":"10.1109\/ACCESS.2024.3373467","volume":"12","author":"A Jabbar","year":"2024","unstructured":"Jabbar, A. et al. A lesion-based diabetic retinopathy detection through hybrid deep learning model. IEEE Access 12, 40019\u201340036. https:\/\/doi.org\/10.1109\/ACCESS.2024.3373467 (2024).","journal-title":"IEEE Access"},{"key":"50608_CR14","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-25399-1","volume":"15","author":"R Bhoopalan","year":"2025","unstructured":"Bhoopalan, R. et al. Task optimized vision transformer for diabetic retinopathy detection and classification in resource constrained early diagnosis settings. Sci. Rep. 15, 39047. https:\/\/doi.org\/10.1038\/s41598-025-25399-1 (2025).","journal-title":"Sci. Rep."},{"key":"50608_CR15","doi-asserted-by":"publisher","DOI":"10.1016\/j.measurement.2022.111485","volume":"2022","author":"M Murugappan","year":"2022","unstructured":"Murugappan, M., Prakash, N., Jeya, R., Mohanarathinam, A. & Hemalakshmi, G. A novel attention based few-shot classification framework for diabetic retinopathy detection and grading. Measurement 2022, 111485. https:\/\/doi.org\/10.1016\/j.measurement.2022.111485 (2022).","journal-title":"Measurement"},{"key":"50608_CR16","doi-asserted-by":"publisher","first-page":"79793","DOI":"10.1109\/ACCESS.2025.3566073","volume":"13","author":"KV Naveen","year":"2025","unstructured":"Naveen, K. V., Anoop, B. N., Siju, K. S., Kar, M. K. & Venugopal, V. EffNet-SVM: A hybrid model for diabetic retinopathy classification using retinal fundus images. IEEE Access 13, 79793\u201379804. https:\/\/doi.org\/10.1109\/ACCESS.2025.3566073 (2025).","journal-title":"IEEE Access"},{"key":"50608_CR17","doi-asserted-by":"publisher","first-page":"38901","DOI":"10.1109\/ACCESS.2025.3546359","volume":"13","author":"AM Mutawa","year":"2025","unstructured":"Mutawa, A. M., Hemalakshmi, G. R., Prakash, N. B. & Murugappan, M. Randomization-driven hybrid deep learning for diabetic retinopathy detection. IEEE Access 13, 38901\u201338913. https:\/\/doi.org\/10.1109\/ACCESS.2025.3546359 (2025).","journal-title":"IEEE Access"},{"key":"50608_CR18","doi-asserted-by":"publisher","first-page":"28642","DOI":"10.1109\/ACCESS.2022.3157632","volume":"10","author":"MZ Atwany","year":"2022","unstructured":"Atwany, M. Z., Sahyoun, A. H. & Yaqub, M. Deep learning techniques for diabetic retinopathy classification: A survey. IEEE Access 10, 28642\u201328655. https:\/\/doi.org\/10.1109\/ACCESS.2022.3157632 (2022).","journal-title":"IEEE Access"},{"key":"50608_CR19","doi-asserted-by":"publisher","first-page":"123220","DOI":"10.1109\/ACCESS.2021.3109240","volume":"9","author":"S Majumder","year":"2021","unstructured":"Majumder, S. & Kehtarnavaz, N. Multitasking deep learning model for detection of five stages of diabetic retinopathy. IEEE Access 9, 123220\u2013123230. https:\/\/doi.org\/10.1109\/ACCESS.2021.3109240 (2021).","journal-title":"IEEE Access"},{"key":"50608_CR20","doi-asserted-by":"publisher","unstructured":"Hua, C. H. et al. Convolutional Network With Twofold Feature Augmentation for Diabetic Retinopathy Recognition From Multi-Modal Images. IEEE J. Biomedical Health Inf. 25 (7), 2686\u20132697. https:\/\/doi.org\/10.1109\/JBHI.2020.3041848 (2021).","DOI":"10.1109\/JBHI.2020.3041848"},{"key":"50608_CR21","doi-asserted-by":"publisher","first-page":"55522","DOI":"10.1109\/ACCESS.2022.3177651","volume":"10","author":"MD Alahmadi","year":"2022","unstructured":"Alahmadi, M. D. Texture attention network for diabetic retinopathy classification. IEEE. Access 10, 55522\u201355532. https:\/\/doi.org\/10.1109\/ACCESS.2022.3177651 (2022).","journal-title":"IEEE. Access"},{"issue":"1","key":"50608_CR22","doi-asserted-by":"publisher","first-page":"143","DOI":"10.1109\/TMI.2020.3023463","volume":"40","author":"A He","year":"2021","unstructured":"He, A., Li, T., Li, N., Wang, K. & Fu, H. CABNet: Category attention block for imbalanced diabetic retinopathy grading. IEEE Trans. Med. Imaging. 40(1), 143\u2013153. https:\/\/doi.org\/10.1109\/TMI.2020.3023463 (2021).","journal-title":"IEEE Trans. Med. Imaging."},{"key":"50608_CR23","doi-asserted-by":"publisher","first-page":"146173","DOI":"10.1109\/ACCESS.2023.3343642","volume":"11","author":"M Siebert","year":"2023","unstructured":"Siebert, M., Gra\u00dfhoff, J. & Rostalski, P. Uncertainty analysis of deep kernel learning methods on diabetic retinopathy grading. IEEE. Access 11, 146173\u2013146184. https:\/\/doi.org\/10.1109\/ACCESS.2023.3343642 (2023).","journal-title":"IEEE. Access"},{"key":"50608_CR24","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2024.106960","volume":"100","author":"M Gargi","year":"2025","unstructured":"Gargi, M., Eluri, R. K., Samantray, O. P. & Hajarathaiah, K. Compact pyramidal dense mixed attention network for diabetic retinopathy severity prediction under deep learning. Biomed. Signal Process. Control. 100, 106960 (2025).","journal-title":"Biomed. Signal Process. Control."},{"key":"50608_CR25","doi-asserted-by":"publisher","first-page":"74799","DOI":"10.1109\/ACCESS.2025.3564529","volume":"13","author":"A Zedadra","year":"2025","unstructured":"Zedadra, A., Zedadra, O., Salah-Salah, M. Y. & Guerrieri, A. Graph-aware multimodal deep learning for classification of diabetic retinopathy images. IEEE. Access 13, 74799\u201374810. https:\/\/doi.org\/10.1109\/ACCESS.2025.3564529 (2025).","journal-title":"IEEE. Access"},{"key":"50608_CR26","doi-asserted-by":"publisher","first-page":"104292","DOI":"10.1109\/ACCESS.2020.2993937","volume":"8","author":"L Qiao","year":"2020","unstructured":"Qiao, L., Zhu, Y. & Zhou, H. Diabetic retinopathy detection using prognosis of microaneurysm and early diagnosis system for non-proliferative diabetic retinopathy based on deep learning algorithms. IEEE. Access 8, 104292\u2013104302. https:\/\/doi.org\/10.1109\/ACCESS.2020.2993937 (2020).","journal-title":"IEEE. Access"},{"key":"50608_CR27","doi-asserted-by":"publisher","first-page":"2081","DOI":"10.1109\/TIP.2025.3551128","volume":"34","author":"X Zhang","year":"2025","unstructured":"Zhang, X. et al. Adaptive dual-axis style-based recalibration network with class-wise statistics loss for imbalanced medical image classification. IEEE Trans. Image Process. 34, 2081\u20132096. https:\/\/doi.org\/10.1109\/TIP.2025.3551128 (2025).","journal-title":"IEEE Trans. Image Process."},{"issue":"12","key":"50608_CR28","doi-asserted-by":"publisher","first-page":"8940","DOI":"10.1109\/JBHI.2024.3377592","volume":"29","author":"H Jiang","year":"2025","unstructured":"Jiang, H. et al. GlanceSeg: Real-time microaneurysm lesion segmentation with gaze-map-guided foundation model for early detection of diabetic retinopathy. IEEE J. Biomed. Health Inform. 29(12), 8940\u20138953. https:\/\/doi.org\/10.1109\/JBHI.2024.3377592 (2025).","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"50608_CR29","doi-asserted-by":"publisher","unstructured":"Wu, X. et al. Expert-Like Reparameterization of Heterogeneous Pyramid Receptive Fields in Efficient CNNs for Fair Medical Image Classification. in IEEE Trans. Med. Imaging, https:\/\/doi.org\/10.1109\/TMI.2025.3641192","DOI":"10.1109\/TMI.2025.3641192"},{"key":"50608_CR30","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2025.112194","volume":"171","author":"J Zhao","year":"2026","unstructured":"Zhao, J. et al. Token pyramid pooling-driven style adapter learning with dual-view balanced loss for imbalanced diabetic retinopathy grading. Pattern Recogn. 171, 112194. https:\/\/doi.org\/10.1016\/j.patcog.2025.112194 (2026).","journal-title":"Pattern Recogn."},{"issue":"6","key":"50608_CR31","doi-asserted-by":"publisher","first-page":"1225","DOI":"10.26599\/BDMA.2025.9020020","volume":"8","author":"X Chen","year":"2025","unstructured":"Chen, X. et al. Retinal fusion network with contrastive learning for imbalanced multi-class retinal disease recognition in FFA. Big Data Min. Anal. 8(6), 1225\u20131244. https:\/\/doi.org\/10.26599\/BDMA.2025.9020020 (2025).","journal-title":"Big Data Min. Anal."},{"key":"50608_CR32","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2022.102499","volume":"80","author":"X Zhang","year":"2022","unstructured":"Zhang, X. et al. Attention to region: Region-based integration-and-recalibration networks for nuclear cataract classification using AS-OCT images. Med. Image Anal. 80, 102499. https:\/\/doi.org\/10.1016\/j.media.2022.102499 (2022).","journal-title":"Med. Image Anal."},{"key":"50608_CR33","doi-asserted-by":"publisher","unstructured":"Pandey, A. et al. Automatic detection of red lesions in Diabetic Retinopathy using Shape based extraction technique in fundus image, 39th International Conference on Telecommunications and Signal Processing (TSP), Vienna, Austria, 2016, pp. 538\u2013542, Vienna, Austria, 2016, pp. 538\u2013542, (2016). https:\/\/doi.org\/10.1109\/TSP.2016.7760938","DOI":"10.1109\/TSP.2016.7760938"},{"issue":"3","key":"50608_CR34","doi-asserted-by":"publisher","first-page":"818","DOI":"10.1109\/TMI.2020.3037771","volume":"40","author":"Y Zhou","year":"2021","unstructured":"Zhou, Y., Wang, B., Huang, L., Cui, S. & Shao, L. A benchmark for studying diabetic retinopathy: Segmentation, grading, and transferability. IEEE Trans. Med. Imaging. 40(3), 818\u2013828. https:\/\/doi.org\/10.1109\/TMI.2020.3037771 (2021).","journal-title":"IEEE Trans. Med. Imaging."},{"issue":"5","key":"50608_CR35","doi-asserted-by":"publisher","first-page":"306","DOI":"10.1016\/j.jdiacomp.2006.08.002","volume":"21","author":"SD Candrilli","year":"2007","unstructured":"Candrilli, S. D., Davis, K. L., Kan, H. J., Lucero, M. A. & Rousculp, M. D. Prevalence and the associated burden of illness of symptoms of diabetic peripheral neuropathy and diabetic retinopathy. J. Diabetes Complic. 21(5), 306\u2013314. https:\/\/doi.org\/10.1016\/j.jdiacomp.2006.08.002 (2007).","journal-title":"J. Diabetes Complic."},{"issue":"3","key":"50608_CR36","doi-asserted-by":"publisher","first-page":"1091","DOI":"10.1109\/JBHI.2021.3108169","volume":"26","author":"Q Liu","year":"2022","unstructured":"Liu, Q., Liu, H., Zhao, Y. & Liang, Y. Dual-branch network with dual-sampling modulated Dice loss for hard exudate segmentation in color fundus images. IEEE J. Biomed. Health Inform. 26(3), 1091\u20131102. https:\/\/doi.org\/10.1109\/JBHI.2021.3108169 (2022).","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"50608_CR37","doi-asserted-by":"publisher","first-page":"23544","DOI":"10.1109\/ACCESS.2021.3056186","volume":"9","author":"A Bilal","year":"2021","unstructured":"Bilal, A., Sun, G., Li, Y., Mazhar, S. & Khan, A. Q. Diabetic retinopathy detection and classification using mixed models for a disease grading database. IEEE. Access 9, 23544\u201323553. https:\/\/doi.org\/10.1109\/ACCESS.2021.3056186 (2021).","journal-title":"IEEE. Access"},{"issue":"6","key":"50608_CR38","doi-asserted-by":"publisher","first-page":"1789","DOI":"10.1109\/TPDS.2023.3264473","volume":"34","author":"NJ Mohan","year":"2023","unstructured":"Mohan, N. J., Murugan, R., Goel, T. & Roy, P. DRFL: Federated learning in diabetic retinopathy grading using fundus images. IEEE Trans. Parallel Distrib. Syst. 34(6), 1789\u20131801. https:\/\/doi.org\/10.1109\/TPDS.2023.3264473 (2023).","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"key":"50608_CR39","doi-asserted-by":"publisher","first-page":"96530","DOI":"10.1109\/ACCESS.2023.3311264","volume":"11","author":"X Ou","year":"2023","unstructured":"Ou, X. et al. Complex scene segmentation with local to global self-attention module and feature alignment module. IEEE Access 11, 96530\u201396542. https:\/\/doi.org\/10.1109\/ACCESS.2023.3311264 (2023).","journal-title":"IEEE Access"},{"key":"50608_CR40","doi-asserted-by":"publisher","first-page":"222611","DOI":"10.1109\/ACCESS.2020.3043413","volume":"8","author":"H Wang","year":"2020","unstructured":"Wang, H. et al. Combining statistical features and local pattern features for texture image retrieval. IEEE Access 8, 222611\u2013222624. https:\/\/doi.org\/10.1109\/ACCESS.2020.3043413 (2020).","journal-title":"IEEE Access"},{"key":"50608_CR41","doi-asserted-by":"publisher","first-page":"120554","DOI":"10.1109\/ACCESS.2023.3327900","volume":"11","author":"H Naz","year":"2023","unstructured":"Naz, H. et al. Ensembled deep convolutional generative adversarial network for grading imbalanced Diabetic Retinopathy recognition. IEEE Access 11, 120554\u2013120568. https:\/\/doi.org\/10.1109\/ACCESS.2023.3327900 (2023).","journal-title":"IEEE Access"},{"key":"50608_CR42","doi-asserted-by":"publisher","unstructured":"V, R. B. S., S, P. A. A. & Sabapathy, S. and P. S, A Novel Deep Learning Framework for Autonomous Classification of Diabetic Maculopathy using Subtle Features, 2025 4th International Conference on Automation, Computing and Renewable Systems (ICACRS), Pudukkottai, India, 2025, pp. 897\u2013902. https:\/\/doi.org\/10.1109\/ICACRS67045.2025.11324176","DOI":"10.1109\/ICACRS67045.2025.11324176"},{"key":"50608_CR43","doi-asserted-by":"publisher","unstructured":"Bhoopalan, R., Anbalagan, P. S. S., Mathu, V. & Sabpathy, S. An Efficient AI Based System for the Detection of Diabetic Maculopathy Using Colour Fundus Images, International Conference on Signal Processing, Computation, Electronics, Power and Telecommunication (IConSCEPT), Karaikal, India, 2024, pp. 1\u20138, Karaikal, India, 2024, pp. 1\u20138, (2024). https:\/\/doi.org\/10.1109\/IConSCEPT61884.2024.10627839","DOI":"10.1109\/IConSCEPT61884.2024.10627839"},{"issue":"6","key":"50608_CR44","doi-asserted-by":"publisher","first-page":"1789","DOI":"10.1109\/TPDS.2023.3264473","volume":"34","author":"NJ Mohan","year":"2023","unstructured":"Mohan, N. J., Murugan, R., Goel, T. & Roy, P. DRFL: Federated learning in Diabetic Retinopathy grading using fundus images. IEEE Trans. Parallel Distrib. Syst. 34(6), 1789\u20131801. https:\/\/doi.org\/10.1109\/TPDS.2023.3264473 (2023).","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"key":"50608_CR45","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-21337-3","volume":"15","author":"P Sekar","year":"2025","unstructured":"Sekar, P., Suba Raja, K. S. & Krishnaraj, R. DRCNN-Lesion Proxy: A hybrid CNN with lesion-inspired feature simulation for diabetic retinopathy severity classification. Sci. Rep. 15, 37954. https:\/\/doi.org\/10.1038\/s41598-025-21337-3 (2025).","journal-title":"Sci. Rep."},{"key":"50608_CR46","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-89262-z","volume":"15","author":"R Bhoopalan","year":"2025","unstructured":"Bhoopalan, R. & Priyadharshini, S. A novel approach for the segmentation of retinal images by integration K-means clustering algorithm with graph cut for image segmentation. Sci. Rep. 15, 35950. https:\/\/doi.org\/10.1038\/s41598-025-89262-z (2025).","journal-title":"Sci. Rep."},{"key":"50608_CR47","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-23234-1","volume":"15","author":"P Sekar","year":"2025","unstructured":"Sekar, P. et al. D-TNet: A hybrid dense net-transformer model for robust diabetic retinopathy detection. Sci. Rep. 15, 39594. https:\/\/doi.org\/10.1038\/s41598-025-23234-1 (2025).","journal-title":"Sci. Rep."},{"key":"50608_CR48","doi-asserted-by":"publisher","DOI":"10.1007\/s11227-025-07775-w","volume":"81","author":"\u0130 Kayadibi","year":"2025","unstructured":"Kayadibi, \u0130, K\u00f6se, U., G\u00fcraks\u0131n, G. E. & \u00c7etin, B. E-MTMYOLO: An explainable YOLOv5-based architecture for accurate detection of mandibular third molar using a novel expert-annotated dataset. J. Supercomput. 81, 1286. https:\/\/doi.org\/10.1007\/s11227-025-07775-w (2025).","journal-title":"J. Supercomput."},{"key":"50608_CR49","doi-asserted-by":"publisher","first-page":"230","DOI":"10.37965\/jait.2025.0645","volume":"5","author":"KR Niranjan","year":"2025","unstructured":"Niranjan, K. R., Srinivasa Rao, N., Rangahanumaiah, N., Beena Ullala Mata, B. N. & Anantharamaiah, V. A hybrid vision transformer and graph neural network model with attention mechanisms for diabetic retinopathy detection. J. Artif. Intell. Technol. 5, 230\u2013241. https:\/\/doi.org\/10.37965\/jait.2025.0645 (2025).","journal-title":"J. Artif. Intell. Technol."},{"key":"50608_CR50","unstructured":"Qiu, J., Chen, Y., Zheng, H., Huang, Y. & Li, Y. A Hybrid Framework Bridging CNN and ViT Based on Theory of Evidence for Diabetic Retinopathy Grading arXiv preprint. arXiv:2510.26315 (2025)."},{"key":"50608_CR51","doi-asserted-by":"publisher","unstructured":"Sekar, P. & Multi-Scale, K. S. R. S. A. Attention-Driven Deep Learning Model for Accurate and Interpretable Diabetic Retinopathy Severity Classification, 2025 9th International Artificial Intelligence and Data Processing Symposium (IDAP), Malatya, Turkiye, 2025, pp. 1\u20137. https:\/\/doi.org\/10.1109\/IDAP68205.2025.11222195","DOI":"10.1109\/IDAP68205.2025.11222195"},{"key":"50608_CR52","doi-asserted-by":"publisher","first-page":"20247","DOI":"10.1109\/ACCESS.2022.3151644","volume":"10","author":"MCS Tang","year":"2022","unstructured":"Tang, M. C. S., Teoh, S. S., Ibrahim, H. & Embong, Z. A deep learning approach for the detection of neovascularization in fundus images using transfer learning. IEEE Access 10, 20247\u201320258. https:\/\/doi.org\/10.1109\/ACCESS.2022.3151644 (2022).","journal-title":"IEEE Access"},{"key":"50608_CR53","doi-asserted-by":"publisher","first-page":"8988","DOI":"10.1109\/ACCESS.2024.3525154","volume":"13","author":"SK Henge","year":"2025","unstructured":"Henge, S. K. et al. Detection of diabetic retinopathy using a multi-decision Inception-ResNet-Blended hybrid model. IEEE Access 13, 8988\u20139005. https:\/\/doi.org\/10.1109\/ACCESS.2024.3525154 (2025).","journal-title":"IEEE Access"},{"key":"50608_CR54","doi-asserted-by":"publisher","first-page":"83004","DOI":"10.1109\/ACCESS.2023.3301618","volume":"11","author":"WK Wong","year":"2023","unstructured":"Wong, W. K., Juwono, F. H. & Apriono, C. Diabetic retinopathy detection and grading: A transfer learning approach using simultaneous parameter optimization and feature-weighted ECOC ensemble. IEEE Access 11, 83004\u201383016. https:\/\/doi.org\/10.1109\/ACCESS.2023.3301618 (2023).","journal-title":"IEEE Access"},{"key":"50608_CR55","doi-asserted-by":"publisher","first-page":"194750","DOI":"10.1109\/ACCESS.2024.3519361","volume":"12","author":"AJ Kadhim","year":"2024","unstructured":"Kadhim, A. J., Seyedarabi, H., Afrouzian, R. & Hasan, F. S. Diabetic retinopathy classification using hybrid color-based CLAHE and blood vessel in deep convolution neural network. IEEE Access 12, 194750\u2013194761. https:\/\/doi.org\/10.1109\/ACCESS.2024.3519361 (2024).","journal-title":"IEEE Access"},{"key":"50608_CR56","doi-asserted-by":"publisher","first-page":"55522","DOI":"10.1109\/ACCESS.2022.3177651","volume":"10","author":"MD Alahmadi","year":"2022","unstructured":"Alahmadi, M. D. Texture attention network for diabetic retinopathy classification. IEEE Access 10, 55522\u201355532. https:\/\/doi.org\/10.1109\/ACCESS.2022.3177651 (2022).","journal-title":"IEEE Access"},{"key":"50608_CR57","unstructured":"Dosovitskiy, A. et al. An image is worth 16\u00d716 words: Transformers for image recognition at scale, arXiv:2010.11929. (2020)."},{"issue":"12","key":"50608_CR58","doi-asserted-by":"publisher","first-page":"7109","DOI":"10.1109\/TGRS.2018.2848473","volume":"56","author":"Y Liu","year":"2018","unstructured":"Liu, Y., Zhong, Y. & Qin, Q. Scene classification based on multiscale convolutional neural network. IEEE Trans. Geosci. Remote Sens. 56 (12), 7109\u20137121 (2018).","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"issue":"8","key":"50608_CR59","doi-asserted-by":"publisher","first-page":"1264","DOI":"10.1016\/j.ophtha.2018.01.034","volume":"125","author":"J Krause","year":"2018","unstructured":"Krause, J. et al. Grader variability and the importance of reference standards for evaluating machine learning models for diabetic retinopathy. Ophthalmology 125 (8), 1264\u20131272 (2018).","journal-title":"Ophthalmology"},{"key":"50608_CR60","doi-asserted-by":"crossref","unstructured":"Devanshi, S. K., Baliarsingh & Dev, P. P. An early diagnosis of diabetic retinopathy using ConvNeXt, in Proc. 10th Int. Conf. Signal Process. Integr. Netw. (SPIN), pp. 739\u2013743. (2023).","DOI":"10.1109\/SPIN57001.2023.10116214"},{"key":"50608_CR61","unstructured":"Tan, M. & Le, Q. V. EfficientNetv2: Smaller models and faster training, in Proc. Int. Conf. Mach. Learn., pp. 10096\u201310106. (2021)."},{"key":"50608_CR62","doi-asserted-by":"crossref","unstructured":"Radosavovic, I., Kosaraju, R. P., Girshick, R., He, K. & Doll\u00e1r, P. Designing network design spaces, in Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR), Jun. pp. 10425\u201310433. (2020).","DOI":"10.1109\/CVPR42600.2020.01044"},{"issue":"17","key":"50608_CR63","doi-asserted-by":"publisher","DOI":"10.3390\/electronics11172740","volume":"11","author":"A-O Asia","year":"2022","unstructured":"Asia, A.-O. et al. Detection of diabetic retinopathy in retinal fundus images using CNN classification models. Electronics 11(17), 2740 (2022).","journal-title":"Electronics"},{"key":"50608_CR64","doi-asserted-by":"publisher","unstructured":"Abidalkareem, A. J. et al. Diabetic Retinopathy (DR) Severity Level Classification Using Multimodel Convolutional Neural Networks, 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), Montreal, QC, Canada, 2020, pp. 1404\u20131407, Montreal, QC, Canada, 2020, pp. 1404\u20131407, (2020). https:\/\/doi.org\/10.1109\/EMBC44109.2020.9175606","DOI":"10.1109\/EMBC44109.2020.9175606"},{"key":"50608_CR65","doi-asserted-by":"publisher","first-page":"341","DOI":"10.1109\/JTEHM.2023.3282104","volume":"11","author":"G Ali","year":"2023","unstructured":"Ali, G., Dastgir, A., Iqbal, M. W., Anwar, M. & Faheem, M. A hybrid convolutional neural network model for automatic diabetic retinopathy classification from fundus images. IEEE J. Transl. Eng. Health Med. 11, 341\u2013350. https:\/\/doi.org\/10.1109\/JTEHM.2023.3282104 (2023).","journal-title":"IEEE J. Transl. Eng. Health Med."},{"key":"50608_CR66","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-13155-4","volume":"15","author":"S Priyadharshini","year":"2025","unstructured":"Priyadharshini, S. et al. A successive framework for brain tumor interpretation using Yolo variants. Sci. Rep. 15, 27973. https:\/\/doi.org\/10.1038\/s41598-025-13155-4 (2025).","journal-title":"Sci. Rep."},{"key":"50608_CR67","doi-asserted-by":"publisher","first-page":"202454","DOI":"10.1109\/ACCESS.2025.3637311","volume":"13","author":"DK Salluri","year":"2025","unstructured":"Salluri, D. K., Atthuluri, M. S. S. C., Sistla, V. & Kolli, V. K. K. A synergistic stacked ensemble deep learning model for predicting diabetic retinopathy severity. IEEE. Access 13, 202454\u2013202466. https:\/\/doi.org\/10.1109\/ACCESS.2025.3637311 (2025).","journal-title":"IEEE. Access"},{"issue":"3","key":"50608_CR68","doi-asserted-by":"publisher","first-page":"1115","DOI":"10.1109\/TMI.2024.3485064","volume":"44","author":"Y Ma","year":"2025","unstructured":"Ma, Y. et al. Grade-skewed domain adaptation via asymmetric bi-classifier discrepancy minimization for diabetic retinopathy grading. IEEE Trans. Med. Imaging 44(3), 1115\u20131126. https:\/\/doi.org\/10.1109\/TMI.2024.3485064 (2025).","journal-title":"IEEE Trans. Med. Imaging"},{"key":"50608_CR69","doi-asserted-by":"publisher","first-page":"38726","DOI":"10.1109\/ACCESS.2025.3545873","volume":"13","author":"N Mukherjee","year":"2025","unstructured":"Mukherjee, N. et al. Bi-directional hybrid attention feature pyramid network for detecting diabetic macular edema in retinal fundus images. IEEE. Access 13, 38726\u201338744. https:\/\/doi.org\/10.1109\/ACCESS.2025.3545873 (2025).","journal-title":"IEEE. Access"},{"key":"50608_CR70","doi-asserted-by":"publisher","first-page":"25503","DOI":"10.1109\/ACCESS.2026.3663765","volume":"14","author":"NAR Mohamed","year":"2026","unstructured":"Mohamed, N. A. R., El-Sakhawy, M. A. & Shaaban, A. R. Optimizing deep learning architectures for diabetic retinopathy detection: A comparative study of CNN and ResNet-50 with ADAM and SGDM. IEEE. Access 14, 25503\u201325514. https:\/\/doi.org\/10.1109\/ACCESS.2026.3663765 (2026).","journal-title":"IEEE. Access"},{"key":"50608_CR71","doi-asserted-by":"publisher","first-page":"28819","DOI":"10.1109\/ACCESS.2026.3665564","volume":"14","author":"GP Reddy","year":"2026","unstructured":"Reddy, G. P. et al. A hybrid deep learning approach with explainable AI for diabetic retinopathy classification. IEEE. Access 14, 28819\u201328839. https:\/\/doi.org\/10.1109\/ACCESS.2026.3665564 (2026).","journal-title":"IEEE. Access"},{"key":"50608_CR72","doi-asserted-by":"publisher","first-page":"199728","DOI":"10.1109\/ACCESS.2025.3631556","volume":"13","author":"I Ahmad","year":"2025","unstructured":"Ahmad, I. & Alshammari, K. GCViT-EffNet: Global context vision transformer and EfficientNet fusion for classification of ocular diseases in CLAHE-enhanced fundus images. IEEE. Access 13, 199728\u2013199736. https:\/\/doi.org\/10.1109\/ACCESS.2025.3631556 (2025).","journal-title":"IEEE. Access"},{"key":"50608_CR73","doi-asserted-by":"publisher","first-page":"34486","DOI":"10.1038\/s41598-025-06973-z","volume":"15","author":"M Gandor","year":"2025","unstructured":"Gandor, M., Pa\u0142ka, F., Ksi\u0105\u017cek, W. et al. Diagnostics of diabetic retinopathy based on fundus photos using machine learning methods with advanced feature engineering algorithms. Sci Rep 15, 34486. https:\/\/doi.org\/10.1038\/s41598-025-06973-z (2025).","journal-title":"Sci. Rep."},{"key":"50608_CR74","doi-asserted-by":"publisher","unstructured":"Akter Z, Ahad JI, Farhan MM, Khan R. Graph-enhanced deep learning for diabetic retinopathy diagnosis: A quality-aware and uncertainty-driven approach. PLoS Comput Biol 21(12): e1013745. https:\/\/doi.org\/10.1371\/journal.pcbi.1013745 (2025).","DOI":"10.1371\/journal.pcbi.1013745"}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-50608-w","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-50608-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-50608-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,6]],"date-time":"2026-08-06T22:55:02Z","timestamp":1786056902000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-50608-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,28]]},"references-count":74,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["50608"],"URL":"https:\/\/doi.org\/10.1038\/s41598-026-50608-w","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,28]]},"assertion":[{"value":"5 February 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 April 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 May 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","label":"Competing interests","group":{"name":"EthicsHeading","label":"Declarations"}}],"article-number":"24374"}}