{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,22]],"date-time":"2026-10-22T17:00:09Z","timestamp":1792688409122,"version":"4.5.0"},"reference-count":55,"publisher":"MDPI AG","issue":"8","license":[{"start":{"date-parts":[[2025,8,3]],"date-time":"2025-08-03T00:00:00Z","timestamp":1754179200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Bioengineering"],"abstract":"<jats:p>The retina offers a unique window into both ocular and systemic health, motivating the development of AI-based tools for disease screening and risk assessment. In this study, we present a comprehensive evaluation of six state-of-the-art deep neural networks, including convolutional neural networks and vision transformer architectures, on the Brazilian Multilabel Ophthalmological Dataset (BRSET), comprising 16,266 fundus images annotated for multiple clinical and demographic labels. We explored seven classification tasks: Diabetes, Diabetic Retinopathy (2-class), Diabetic Retinopathy (3-class), Hypertension, Hypertensive Retinopathy, Drusen, and Sex classification. Models were evaluated using precision, recall, F1-score, accuracy, and AUC. Among all models, the Swin-L generally delivered the best performance across scenarios for Diabetes (AUC = 0.88, weighted F1-score = 0.86), Diabetic Retinopathy (2-class) (AUC = 0.98, weighted F1-score = 0.95), Diabetic Retinopathy (3-class) (macro AUC = 0.98, weighted F1-score = 0.95), Hypertension (AUC = 0.85, weighted F1-score = 0.79), Hypertensive Retinopathy (AUC = 0.81, weighted F1-score = 0.97), Drusen detection (AUC = 0.93, weighted F1-score = 0.90), and Sex classification (AUC = 0.87, weighted F1-score = 0.80). These results reflect excellent to outstanding diagnostic performance. We also employed gradient-based saliency maps to enhance explainability and visualize decision-relevant retinal features. Our findings underscore the potential of deep learning, particularly vision transformer models, to deliver accurate, interpretable, and clinically meaningful screening tools for retinal and systemic disease detection.<\/jats:p>","DOI":"10.3390\/bioengineering12080840","type":"journal-article","created":{"date-parts":[[2025,8,7]],"date-time":"2025-08-07T08:33:06Z","timestamp":1754555586000},"page":"840","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":14,"title":["Deep Learning for Comprehensive Analysis of Retinal Fundus Images: Detection of Systemic and Ocular Conditions"],"prefix":"10.3390","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-7352-6230","authenticated-orcid":false,"given":"Mohammad Mahdi","family":"Aghabeigi Alooghareh","sequence":"first","affiliation":[{"name":"Department of Electrical and Computer Engineering, Lorestan University, Khorramabad 68151-44316, Iran"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8543-7425","authenticated-orcid":false,"given":"Mohammad Mohsen","family":"Sheikhey","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Lorestan University, Khorramabad 68151-44316, Iran"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9360-9103","authenticated-orcid":false,"given":"Ali","family":"Sahafi","sequence":"additional","affiliation":[{"name":"Institute of Mechanical and Electrical Engineering, University of Southern Denmark, 5230 Odense, Denmark"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9284-5702","authenticated-orcid":false,"given":"Habibollah","family":"Pirnejad","sequence":"additional","affiliation":[{"name":"Department of Family Medicine, Amsterdam University Medical Center, 1105 Amsterdam, The Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4501-4310","authenticated-orcid":false,"given":"Amin","family":"Naemi","sequence":"additional","affiliation":[{"name":"Nordcee, Department of Biology, University of Southern Denmark, 5230 Odense, Denmark"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2025,8,3]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1007\/s13167-023-00314-8","article-title":"Diabetic retinopathy as the leading cause of blindness and early predictor of cascading complications\u2014Risks and mitigation","volume":"14","author":"Kropp","year":"2023","journal-title":"Epma J."},{"key":"ref_2","unstructured":"Sadda, S.R., Schachat, A.P., Wilkinson, C.P., Hinton, D.R., Wiedemann, P., Freund, K.B., and Sarraf, D. (2022). Ryan\u2019s Retina E-Book, Elsevier Health Sciences."},{"key":"ref_3","first-page":"200180","article-title":"Hypertensive retinopathy and cardiovascular disease risk: 6 population-based cohorts meta-analysis","volume":"17","author":"Liew","year":"2023","journal-title":"Int. J. Cardiol. Cardiovasc. Risk Prev."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"6","DOI":"10.1167\/iovs.65.10.6","article-title":"Long-term impact of diabetic retinopathy on response to anti-VEGF treatment in neovascular AMD","volume":"65","author":"Boscia","year":"2024","journal-title":"Investig. Ophthalmol. Vis. Sci."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"100759","DOI":"10.1016\/j.preteyeres.2019.04.003","article-title":"Deep learning in ophthalmology: The technical and clinical considerations","volume":"72","author":"Ting","year":"2019","journal-title":"Prog. Retin. Eye Res."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"35","DOI":"10.1007\/s11892-021-01403-6","article-title":"Laser therapy in the treatment of diabetic retinopathy and diabetic macular edema","volume":"21","author":"Everett","year":"2021","journal-title":"Curr. Diabetes Rep."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Leng, X., Shi, R., Wu, Y., Zhu, S., Cai, X., Lu, X., and Liu, R. (2023). Deep learning for detection of age-related macular degeneration: A systematic review and meta-analysis of diagnostic test accuracy studies. PLoS ONE, 18.","DOI":"10.1371\/journal.pone.0284060"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"2159","DOI":"10.2147\/OPTH.S92359","article-title":"Geographic atrophy in patients with advanced dry age-related macular degeneration: Current challenges and future prospects","volume":"9","author":"Danis","year":"2015","journal-title":"Clin. Ophthalmol."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"26","DOI":"10.1016\/j.neuron.2012.06.018","article-title":"Mechanisms of age-related macular degeneration","volume":"75","author":"Ambati","year":"2012","journal-title":"Neuron"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"e052663","DOI":"10.1136\/bmjopen-2021-052663","article-title":"Machine learning techniques for mortality prediction in emergency departments: A systematic review","volume":"11","author":"Naemi","year":"2021","journal-title":"BMJ Open"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Sahafi, A., Koulaouzidis, A., and Lalinia, M. (2024). Polypoid lesion segmentation using YOLO-V8 network in wireless video capsule endoscopy images. Diagnostics, 14.","DOI":"10.3390\/diagnostics14050474"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Sahafi, A., Wang, Y., Rasmussen, C., Bollen, P., Baatrup, G., Blanes-Vidal, V., Herp, J., and Nadimi, E. (2022). Edge artificial intelligence wireless video capsule endoscopy. Sci. Rep., 12.","DOI":"10.1038\/s41598-022-17502-7"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"2047","DOI":"10.1007\/s11760-023-02835-1","article-title":"Colorectal polyp detection in colonoscopy images using YOLO-V8 network","volume":"18","author":"Lalinia","year":"2024","journal-title":"Signal Image Video Process."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"2402","DOI":"10.1001\/jama.2016.17216","article-title":"Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs","volume":"316","author":"Gulshan","year":"2016","journal-title":"JAMA"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"2211","DOI":"10.1001\/jama.2017.18152","article-title":"Development and validation of a deep learning system for diabetic retinopathy and related eye diseases using retinal images from multiethnic populations with diabetes","volume":"318","author":"Ting","year":"2017","journal-title":"JAMA"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"1533","DOI":"10.1016\/j.ophtha.2019.06.005","article-title":"A deep learning approach for automated detection of geographic atrophy from color fundus photographs","volume":"126","author":"Keenan","year":"2019","journal-title":"Ophthalmology"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"1674","DOI":"10.1016\/j.ophtha.2020.05.036","article-title":"Deep learning automated detection of reticular pseudodrusen from fundus autofluorescence images or color fundus photographs in AREDS2","volume":"127","author":"Keenan","year":"2020","journal-title":"Ophthalmology"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Pham, Q.T., Ahn, S., Song, S.J., and Shin, J. (2020). Automatic drusen segmentation for age-related macular degeneration in fundus images using deep learning. Electronics, 9.","DOI":"10.3390\/electronics9101617"},{"key":"ref_19","unstructured":"Sadek, I., Elawady, M., and Shabayek, A.E.R. (2017). Automatic classification of bright retinal lesions via deep network features. arXiv."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"39","DOI":"10.1038\/s41746-018-0040-6","article-title":"Pivotal trial of an autonomous AI-based diagnostic system for detection of diabetic retinopathy in primary care offices","volume":"1","author":"Lavin","year":"2018","journal-title":"NPJ Digit. Med."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"158","DOI":"10.1038\/s41551-018-0195-0","article-title":"Prediction of cardiovascular risk factors from retinal fundus photographs via deep learning","volume":"2","author":"Poplin","year":"2018","journal-title":"Nat. Biomed. Eng."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"205","DOI":"10.1038\/s41746-025-01588-0","article-title":"Vision transformer based interpretable metabolic syndrome classification using retinal Images","volume":"8","author":"Lee","year":"2025","journal-title":"NPJ Digit. Med."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"100552","DOI":"10.1016\/j.xops.2024.100552","article-title":"Comparative analysis of vision transformers and conventional convolutional neural networks in detecting referable diabetic retinopathy","volume":"4","author":"Goh","year":"2024","journal-title":"Ophthalmol. Sci."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Wang, D., Lian, J., and Jiao, W. (2024). Multi-label classification of retinal disease via a novel vision transformer model. Front. Neurosci., 17.","DOI":"10.3389\/fnins.2023.1290803"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"156","DOI":"10.1038\/s41586-023-06555-x","article-title":"A foundation model for generalizable disease detection from retinal images","volume":"622","author":"Zhou","year":"2023","journal-title":"Nature"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Nakayama, L.F., Goncalves, M., Zago Ribeiro, L., Santos, H., Ferraz, D., Malerbi, F., Celi, L.A., and Regatieri, C. (2023). A Brazilian multilabel ophthalmological dataset (BRSET) (version 1.0.1). PhysioNet. RRID:SCR-007345. PhysioNet.","DOI":"10.1101\/2024.01.23.24301660"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"1677","DOI":"10.1016\/S0161-6420(03)00475-5","article-title":"Proposed international clinical diabetic retinopathy and diabetic macular edema disease severity scales","volume":"110","author":"Wilkinson","year":"2003","journal-title":"Ophthalmology"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Nakayama, L.F., Restrepo, D., Matos, J., Ribeiro, L.Z., Malerbi, F.K., Celi, L.A., and Regatieri, C.S. (2024). BRSET: A Brazilian multilabel ophthalmological dataset of retina fundus photos. PLoS Digit. Health, 3.","DOI":"10.1101\/2024.01.23.24301660"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"425","DOI":"10.1016\/S0140-6736(07)60198-6","article-title":"The eye in hypertension","volume":"369","author":"Wong","year":"2007","journal-title":"Lancet"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"e106","DOI":"10.1016\/S2214-109X(13)70145-1","article-title":"Global prevalence of age-related macular degeneration and disease burden projection for 2020 and 2040: A systematic review and meta-analysis","volume":"2","author":"Wong","year":"2014","journal-title":"Lancet Glob. Health"},{"key":"ref_31","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., and Gelly, S. (2020). An image is worth 16x16 words: Transformers for image recognition at scale. arXiv."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., and Sun, G. (2018, January 18\u201322). Squeeze-and-excitation networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Radosavovic, I., Kosaraju, R.P., Girshick, R., He, K., and Doll\u00e1r, P. (2020, January 14\u201319). Designing network design spaces. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.01044"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., and Guo, B. (2021, January 11\u201317). Swin transformer: Hierarchical vision transformer using shifted windows. Proceedings of the IEEE\/CVF International Conference on Computer Vision, Montreal, QC, Canada.","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref_35","first-page":"9355","article-title":"Twins: Revisiting the design of spatial attention in vision transformers","volume":"34","author":"Chu","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Dong, X., Bao, J., Chen, D., Zhang, W., Yu, N., Yuan, L., Chen, D., and Guo, B. (2022, January 18\u201324). Cswin transformer: A general vision transformer backbone with cross-shaped windows. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, USA.","DOI":"10.1109\/CVPR52688.2022.01181"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"415","DOI":"10.1007\/s41095-022-0274-8","article-title":"Pvt v2: Improved baselines with pyramid vision transformer","volume":"8","author":"Wang","year":"2022","journal-title":"Comput. Vis. Media"},{"key":"ref_38","unstructured":"Kingma, D.P., and Ba, J. (2014). A method for stochastic optimization. arXiv."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s40537-019-0197-0","article-title":"A survey on image data augmentation for deep learning","volume":"6","author":"Shorten","year":"2019","journal-title":"J. Big Data"},{"key":"ref_40","unstructured":"Nair, V., and Hinton, G.E. (2010, January 21\u201324). Rectified linear units improve restricted boltzmann machines. Proceedings of the 27th International Conference on Machine Learning (ICML-10), Haifa, Israel."},{"key":"ref_41","unstructured":"Hendrycks, D., and Gimpel, K. (2016). Gaussian error linear units (gelus). arXiv."},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., and Fei-Fei, L. (2009, January 20\u201325). Imagenet: A large-scale hierarchical image database. Proceedings of the 2009 IEEE Conference on Computer Vision and Pattern Recognition, Miami, FL, USA.","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref_43","unstructured":"Simonyan, K., Vedaldi, A., and Zisserman, A. (2013). Deep inside convolutional networks: Visualising image classification models and saliency maps. arXiv."},{"key":"ref_44","unstructured":"Sundararajan, M., Taly, A., and Yan, Q. (2017, January 6\u201311). Axiomatic attribution for deep networks. Proceedings of the International Conference on Machine Learning, PMLR, Sydney, NSW, Australia."},{"key":"ref_45","unstructured":"Kokhlikyan, N., Miglani, V., Martin, M., Wang, E., Alsallakh, B., Reynolds, J., Melnikov, A., Kliushkina, N., Araya, C., and Yan, S. (2020). Captum: A unified and generic model interpretability library for pytorch. arXiv."},{"key":"ref_46","first-page":"4768","article-title":"A unified approach to interpreting model predictions","volume":"30","author":"Lundberg","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"84","DOI":"10.1007\/s10916-024-02105-8","article-title":"Comparison of vision transformers and convolutional neural networks in medical image analysis: A systematic review","volume":"48","author":"Takahashi","year":"2024","journal-title":"J. Med. Syst."},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"1315","DOI":"10.1097\/JTO.0b013e3181ec173d","article-title":"Receiver operating characteristic curve in diagnostic test assessment","volume":"5","author":"Mandrekar","year":"2010","journal-title":"J. Thorac. Oncol."},{"key":"ref_49","doi-asserted-by":"crossref","unstructured":"Naemi, A., Tashk, A., Azar, A.S., Samimi, T., Tavassoli, G., Mohasefi, A.B., Khanshan, E.N., Najafabad, M.H., Tarighi, V., and Wiil, U.K. (2025). Applications of Artificial Intelligence for Metastatic Gastrointestinal Cancer: A Systematic Literature Review. Cancers, 17.","DOI":"10.3390\/cancers17030558"},{"key":"ref_50","doi-asserted-by":"crossref","unstructured":"Szymkowski, M. (2023, January 22\u201324). Neural Networks and Saliency Maps in Diabetic Retinopathy Diagnosis. Proceedings of the International Conference on Computer Information Systems and Industrial Management, Tokyo, Japan.","DOI":"10.1007\/978-3-031-42823-4_22"},{"key":"ref_51","doi-asserted-by":"crossref","first-page":"102364","DOI":"10.1016\/j.media.2022.102364","article-title":"Clinical validation of saliency maps for understanding deep neural networks in ophthalmology","volume":"77","author":"Ayhan","year":"2022","journal-title":"Med Image Anal."},{"key":"ref_52","doi-asserted-by":"crossref","first-page":"012110","DOI":"10.1088\/1742-6596\/1108\/1\/012110","article-title":"Exudate segmentation in retinal images of diabetic retinopathy using saliency method based on region","volume":"1108","author":"Nur","year":"2018","journal-title":"J. Phys. Conf. Ser."},{"key":"ref_53","doi-asserted-by":"crossref","first-page":"4531","DOI":"10.1002\/mp.13746","article-title":"Automated retinal lesion detection via image saliency analysis","volume":"46","author":"Yan","year":"2019","journal-title":"Med. Phys."},{"key":"ref_54","doi-asserted-by":"crossref","unstructured":"Gould, D.S., Yang, J., and Clifton, D.A. (2024). Deep learning for multi-label disease classification of retinal images: Insights from brazilian data for ai development in lower-middle income countries. medRxiv.","DOI":"10.1101\/2024.02.12.24302676"},{"key":"ref_55","doi-asserted-by":"crossref","unstructured":"Wu, C., Yang, X., Gilkes, E.G., Cui, H., Choi, J., Sun, N., Liao, Z., Fan, B., Santillana, M., and Celi, L. (2023, January 8\u201312). De-identification and obfuscation of gender attributes from retinal scans. Proceedings of the Workshop on Clinical Image-Based Procedures, Vancouver, BC, Canada.","DOI":"10.1007\/978-3-031-45249-9_9"}],"container-title":["Bioengineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2306-5354\/12\/8\/840\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T18:22:08Z","timestamp":1760034128000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2306-5354\/12\/8\/840"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,3]]},"references-count":55,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2025,8]]}},"alternative-id":["bioengineering12080840"],"URL":"https:\/\/doi.org\/10.3390\/bioengineering12080840","relation":{},"ISSN":["2306-5354"],"issn-type":[{"value":"2306-5354","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8,3]]}}}