{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,17]],"date-time":"2025-11-17T02:30:44Z","timestamp":1763346644337,"version":"3.45.0"},"reference-count":43,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,11,17]],"date-time":"2025-11-17T00:00:00Z","timestamp":1763337600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,11,17]],"date-time":"2025-11-17T00:00:00Z","timestamp":1763337600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Med Syst"],"DOI":"10.1007\/s10916-025-02292-y","type":"journal-article","created":{"date-parts":[[2025,11,17]],"date-time":"2025-11-17T02:27:11Z","timestamp":1763346431000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Efficient Vision Transformers for Ophthalmic Images Classification: A Comparative Study of Supervised, Semi-Supervised, and Unsupervised Learning Approaches"],"prefix":"10.1007","volume":"49","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4624-9659","authenticated-orcid":false,"given":"Ahmed Shakir","family":"Al-Wassiti","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9699-4665","authenticated-orcid":false,"given":"Mohammed Tareq","family":"Mutar","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0006-7740-1453","authenticated-orcid":false,"given":"Ahmed Sermed","family":"Al Sakini","sequence":"additional","affiliation":[]},{"given":"Luay Salim","family":"Rasheed","sequence":"additional","affiliation":[]},{"given":"Wissam","family":"Yosif","sequence":"additional","affiliation":[]},{"given":"Mohammad Asaad","family":"Abbas","sequence":"additional","affiliation":[]},{"given":"Nissar Riad","family":"Raouf","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4298-5456","authenticated-orcid":false,"given":"Ali Saad","family":"Al-Shammari","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,11,17]]},"reference":[{"key":"2292_CR1","doi-asserted-by":"publisher","unstructured":"V. Gulshan et al., \u201cDevelopment and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs.,\u201d JAMA, vol. 316, no. 22, pp. 2402\u20132410, Dec. 2016, doi: https:\/\/doi.org\/10.1001\/jama.2016.17216.","DOI":"10.1001\/jama.2016.17216"},{"key":"2292_CR2","doi-asserted-by":"publisher","unstructured":"D. S. W. Ting et al., \u201cDevelopment and validation of a deep learning system for diabetic retinopathy and related eye diseases using retinal images from multiethnic populations with diabetes.,\u201d JAMA, vol. 318, no. 22, pp. 2211\u20132223, Dec. 2017,\u00a0doi: https:\/\/doi.org\/10.1001\/jama.2017.18152.","DOI":"10.1001\/jama.2017.18152"},{"key":"2292_CR3","doi-asserted-by":"publisher","unstructured":"K. Sohn et al., \u201cFixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence,\u201d arXiv, 2020,\u00a0doi: https:\/\/doi.org\/10.48550\/arxiv.2001.07685.","DOI":"10.48550\/arxiv.2001.07685"},{"key":"2292_CR4","doi-asserted-by":"publisher","unstructured":"T. Chen, S. Kornblith, M. Norouzi, and G. Hinton, \u201cA Simple Framework for Contrastive Learning of Visual Representations,\u201d arXiv, 2020,\u00a0doi: https:\/\/doi.org\/10.48550\/arxiv.2002.05709.","DOI":"10.48550\/arxiv.2002.05709"},{"key":"2292_CR5","doi-asserted-by":"publisher","unstructured":"J. De Fauw et al., \u201cClinically applicable deep learning for diagnosis and referral in retinal disease.,\u201d Nat. Med., vol. 24, no. 9, pp. 1342\u20131350, Sep. 2018,\u00a0doi: https:\/\/doi.org\/10.1038\/s41591-018-0107-6.","DOI":"10.1038\/s41591-018-0107-6"},{"key":"2292_CR6","doi-asserted-by":"publisher","unstructured":"S. Li, P. Kou, M. Ma, H. Yang, S. Huang, and Z. Yang, \u201cApplication of Semi-Supervised Learning in Image Classification: Research on Fusion of Labeled and Unlabeled Data,\u201d IEEE Access, vol. 12, pp. 27331\u201327343, 2024, doi: https:\/\/doi.org\/10.1109\/ACCESS.2024.3367772.","DOI":"10.1109\/ACCESS.2024.3367772"},{"key":"2292_CR7","doi-asserted-by":"publisher","unstructured":"S. Shim et al., \u201cDevelopment and validation of a multi-stage self-supervised learning model for optical coherence tomography image classification.,\u201d J. Am. Med. Inform. Assoc., vol. 32, no. 5, pp. 800\u2013810, May 2025,\u00a0doi: https:\/\/doi.org\/10.1093\/jamia\/ocaf021.","DOI":"10.1093\/jamia\/ocaf021"},{"key":"2292_CR8","doi-asserted-by":"publisher","unstructured":"A. Dosovitskiy et al., \u201cAn Image is Worth 16x16 Words: Transformers for Image Recognition at Scale,\u201d arXiv, 2020,\u00a0doi: https:\/\/doi.org\/10.48550\/arxiv.2010.11929.","DOI":"10.48550\/arxiv.2010.11929"},{"key":"2292_CR9","unstructured":"H. Touvron, M. Cord, and M. Douze, \u201cTraining data-efficient image transformers & distillation through attention.,\u201d 2021, vol. 10347\u201310357."},{"key":"2292_CR10","doi-asserted-by":"crossref","unstructured":"Z. Tu, H. Talebi, and H. Zhang, \u201cMaxViT: Multi-axis vision transformer,\u201d 2022, pp. 459\u2013479.","DOI":"10.1007\/978-3-031-20053-3_27"},{"key":"2292_CR11","doi-asserted-by":"publisher","unstructured":"S. Pachade et al., \u201cRetinal Fundus Multi-Disease Image Dataset (RFMiD): A Dataset for Multi-Disease Detection Research,\u201d Data (Basel), vol. 6, no. 2, p. 14, Feb. 2021,\u00a0doi: https:\/\/doi.org\/10.3390\/data6020014.","DOI":"10.3390\/data6020014"},{"key":"2292_CR12","doi-asserted-by":"publisher","unstructured":"O. S. Naren, \u201cDiabetic Macular Edema OCT Images for Anti-VEGF Treatment Outcomes [dataset],\u201d Kaggle, 2021, doi: https:\/\/doi.org\/10.34740\/kaggle\/dsv\/2736749.","DOI":"10.34740\/kaggle\/dsv\/2736749"},{"key":"2292_CR13","doi-asserted-by":"publisher","unstructured":"S. Das, K. Kharbanda, S. M, R. Raman, and E. D. D, \u201cDeep learning architecture based on segmented fundus image features for classification of diabetic retinopathy,\u201d Biomed. Signal Process. Control, vol. 68, p. 102600, Jul. 2021,\u00a0doi: https:\/\/doi.org\/10.1016\/j.bspc.2021.102600.","DOI":"10.1016\/j.bspc.2021.102600"},{"key":"2292_CR14","doi-asserted-by":"publisher","unstructured":"F. Li et al., \u201cDeep learning-based automated detection for diabetic retinopathy and diabetic macular oedema in retinal fundus photographs.,\u201d Eye, vol. 36, no. 7, pp. 1433\u20131441, Jul. 2022,\u00a0doi: https:\/\/doi.org\/10.1038\/s41433-021-01552-8.","DOI":"10.1038\/s41433-021-01552-8"},{"key":"2292_CR15","doi-asserted-by":"crossref","unstructured":"A. Panwar, G. Semwal, S. Goel, and S. Gupta, \u201cStratification of the lesions in color fundus images of diabetic retinopathy patients using deep learning models and machine learning classifiers,\u201d in Edge analytics: select proceedings of 26th international conference\u2014adcom 2020, vol. 869, R. Patgiri, S. Bandyopadhyay, M. D. Borah, and V. Emilia Balas, Eds. Singapore: Springer Singapore, 2022, pp. 653\u2013666.","DOI":"10.1007\/978-981-19-0019-8_49"},{"key":"2292_CR16","doi-asserted-by":"publisher","unstructured":"A. S. A. Sakini et al., \u201cDiabetic macular edema (DME): dissecting pathogenesis, prognostication, diagnostic modalities along with current and futuristic therapeutic insights.,\u201d Int. J. Retina Vitreous, vol. 10, no. 1, p. 83, Oct. 2024, doi: https:\/\/doi.org\/10.1186\/s40942-024-00603-y.","DOI":"10.1186\/s40942-024-00603-y"},{"key":"2292_CR17","doi-asserted-by":"publisher","unstructured":"J. Lachure, A. V. Deorankar, S. Lachure, S. Gupta, and R. Jadhav, \u201cDiabetic Retinopathy using morphological operations and machine learning,\u201d in 2015 IEEE International Advance Computing Conference (IACC), Jun. 2015, pp. 617\u2013622,\u00a0doi: https:\/\/doi.org\/10.1109\/IADCC.2015.7154781.","DOI":"10.1109\/IADCC.2015.7154781"},{"key":"2292_CR18","doi-asserted-by":"publisher","unstructured":"K. Bhatia, S. Arora, and R. Tomar, \u201cDiagnosis of diabetic retinopathy using machine learning classification algorithm,\u201d in 2016 2nd International Conference on Next Generation Computing Technologies (NGCT), Oct. 2016, pp. 347\u2013351,\u00a0doi: https:\/\/doi.org\/10.1109\/NGCT.2016.7877439.","DOI":"10.1109\/NGCT.2016.7877439"},{"key":"2292_CR19","doi-asserted-by":"publisher","unstructured":"M. H. Malik, Z. Wan, Y. Gao, and D.-W. Ding, \u201cEfficient diagnosis of retinal disorders using dual-branch semi-supervised learning (DB-SSL): An enhanced multi-class classification approach.,\u201d Comput. Med. Imaging Graph., vol. 121, p. 102494, Apr. 2025, doi: https:\/\/doi.org\/10.1016\/j.compmedimag.2025.102494.","DOI":"10.1016\/j.compmedimag.2025.102494"},{"key":"2292_CR20","doi-asserted-by":"publisher","unstructured":"Z. Dai, Z. Yang, F. Yang, W. W. Cohen, and R. Salakhutdinov, \u201cGood Semi-supervised Learning that Requires a Bad GAN,\u201d arXiv, 2017,\u00a0doi: https:\/\/doi.org\/10.48550\/arxiv.1705.09783.","DOI":"10.48550\/arxiv.1705.09783"},{"key":"2292_CR21","doi-asserted-by":"publisher","unstructured":"A. Kumar, P. Sattigeri, and P. T. Fletcher, \u201cSemi-supervised Learning with GANs: Manifold Invariance with Improved Inference,\u201d arXiv, 2017,\u00a0doi: https:\/\/doi.org\/10.48550\/arxiv.1705.08850.","DOI":"10.48550\/arxiv.1705.08850"},{"key":"2292_CR22","doi-asserted-by":"publisher","unstructured":"S. Wu, G. Deng, J. Li, R. Li, Z. Yu, and H.-S. Wong, \u201cEnhancing TripleGAN for Semi-Supervised Conditional Instance Synthesis and Classification,\u201d in 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Jun. 2019, pp. 10083\u201310092, pp. 10083\u201310092, doi: https:\/\/doi.org\/10.1109\/CVPR.2019.01033.","DOI":"10.1109\/CVPR.2019.01033"},{"key":"2292_CR23","doi-asserted-by":"publisher","unstructured":"M. N. Rizve, K. Duarte, Y. S. Rawat, and M. Shah, \u201cIn Defense of Pseudo-Labeling: An Uncertainty-Aware Pseudo-label Selection Framework for Semi-Supervised Learning,\u201d arXiv, 2021,\u00a0doi: https:\/\/doi.org\/10.48550\/arxiv.2101.06329.","DOI":"10.48550\/arxiv.2101.06329"},{"key":"2292_CR24","doi-asserted-by":"publisher","unstructured":"F. Liu, Y. Tian, Y. Chen, Y. Liu, V. Belagiannis, and G. Carneiro, \u201cACPL: Anti-curriculum Pseudo-labelling for Semi-supervised Medical Image Classification,\u201d arXiv, 2021, doi: https:\/\/doi.org\/10.48550\/arxiv.2111.12918.","DOI":"10.48550\/arxiv.2111.12918"},{"key":"2292_CR25","doi-asserted-by":"publisher","unstructured":"D. Berthelot, N. Carlini, I. Goodfellow, N. Papernot, A. Oliver, and C. Raffel, \u201cMixMatch: A Holistic Approach to Semi-Supervised Learning,\u201d arXiv, 2019, doi: https:\/\/doi.org\/10.48550\/arxiv.1905.02249.","DOI":"10.48550\/arxiv.1905.02249"},{"key":"2292_CR26","doi-asserted-by":"publisher","unstructured":"Y. Luo, J. Zhu, M. Li, Y. Ren, and B. Zhang, \u201cSmooth Neighbors on Teacher Graphs for Semi-supervised Learning,\u201d arXiv, 2017,\u00a0doi: https:\/\/doi.org\/10.48550\/arxiv.1711.00258.","DOI":"10.48550\/arxiv.1711.00258"},{"key":"2292_CR27","doi-asserted-by":"publisher","unstructured":"T. N. Kipf and M. Welling, \u201cSemi-Supervised Classification with Graph Convolutional Networks,\u201d arXiv, 2016, 2016, doi: https:\/\/doi.org\/10.48550\/arxiv.1609.02907.","DOI":"10.48550\/arxiv.1609.02907"},{"key":"2292_CR28","doi-asserted-by":"publisher","unstructured":"A. Iscen, G. Tolias, Y. Avrithis, and O. Chum, \u201cLabel Propagation for Deep Semi-supervised Learning,\u201d arXiv, 2019,\u00a0doi: https:\/\/doi.org\/10.48550\/arxiv.1904.04717.","DOI":"10.48550\/arxiv.1904.04717"},{"key":"2292_CR29","doi-asserted-by":"publisher","unstructured":"C. Zhang, P. Chen, and T. Lei, \u201cMulti-point attention-based semi-supervised learning for diabetic retinopathy classification,\u201d Biomed. Signal Process. Control, vol. 80, p. 104412, Feb. 2023, doi: https:\/\/doi.org\/10.1016\/j.bspc.2022.104412.","DOI":"10.1016\/j.bspc.2022.104412"},{"key":"2292_CR30","doi-asserted-by":"publisher","unstructured":"A. Smitha and P. Jidesh, \u201cClassification of Multiple Retinal Disorders from Enhanced Fundus Images Using Semi-supervised GAN,\u201d SN COMPUT. SCI., vol. 3, no. 1, p. 59, Jan. 2022,\u00a0doi: https:\/\/doi.org\/10.1007\/s42979-021-00945-6.","DOI":"10.1007\/s42979-021-00945-6"},{"key":"2292_CR31","doi-asserted-by":"publisher","unstructured":"J. Wang et al., \u201cSSVT: Self-Supervised Vision Transformer For Eye Disease Diagnosis Based On Fundus Images,\u201d in 2024 IEEE International Symposium on Biomedical Imaging (ISBI), May 2024, pp. 1\u20134,\u00a0doi: https:\/\/doi.org\/10.1109\/ISBI56570.2024.10635531.","DOI":"10.1109\/ISBI56570.2024.10635531"},{"key":"2292_CR32","doi-asserted-by":"publisher","unstructured":"Z. Cheng, B. Li, A. Altmann, P. A. Keane, and Y. Zhou, \u201cEnhancing Contrastive Learning for Retinal Imaging via Adjusted Augmentation Scales,\u201d arXiv, 2025, doi: https:\/\/doi.org\/10.48550\/arxiv.2501.02451.","DOI":"10.48550\/arxiv.2501.02451"},{"key":"2292_CR33","doi-asserted-by":"publisher","unstructured":"B. Yellapragada, S. Hornauer, K. Snyder, S. Yu, and G. Yiu, \u201cSelf-Supervised Feature Learning and Phenotyping for Assessing Age-Related Macular Degeneration Using Retinal Fundus Images.,\u201d Ophthalmol. Retina, vol. 6, no. 2, pp. 116\u2013129, Feb. 2022,\u00a0doi: https:\/\/doi.org\/10.1016\/j.oret.2021.06.010.","DOI":"10.1016\/j.oret.2021.06.010"},{"key":"2292_CR34","doi-asserted-by":"publisher","unstructured":"S.-C. Huang, A. Pareek, M. Jensen, M. P. Lungren, S. Yeung, and A. S. Chaudhari, \u201cSelf-supervised learning for medical image classification: a systematic review and implementation guidelines.,\u201d npj Digital Med., vol. 6, no. 1, p. 74, Apr. 2023,\u00a0doi: https:\/\/doi.org\/10.1038\/s41746-023-00811-0.","DOI":"10.1038\/s41746-023-00811-0"},{"key":"2292_CR35","unstructured":"Y. Shi, N. Siddharth, P. H. S. Torr, and A. R. Kosiorek, \u201c Adversarial masking for self-supervised learning,\u201d 2022, pp. 20026\u201320040."},{"key":"2292_CR36","doi-asserted-by":"publisher","unstructured":"N. Dong and I. Voiculescu, \u201cFederated Contrastive Learning for Decentralized Unlabeled Medical Images,\u201d arXiv, 2021,\u00a0doi: https:\/\/doi.org\/10.48550\/arxiv.2109.07504.","DOI":"10.48550\/arxiv.2109.07504"},{"key":"2292_CR37","doi-asserted-by":"publisher","unstructured":"Y. Sharma, L. Ehsan, S. Syed, and D. E. Brown, \u201cHistoTransfer: Understanding Transfer Learning for Histopathology,\u201d arXiv, 2021,\u00a0doi: https:\/\/doi.org\/10.48550\/arxiv.2106.07068.","DOI":"10.48550\/arxiv.2106.07068"},{"key":"2292_CR38","doi-asserted-by":"publisher","unstructured":"G. Li, R. Togo, T. Ogawa, and M. Haseyama, \u201cTriplet Self-Supervised Learning for Gastritis Detection with Scarce Annotations,\u201d in 2021 IEEE 10th Global Conference on Consumer Electronics (GCCE), Oct. 2021, pp. 787\u2013788,\u00a0doi: https:\/\/doi.org\/10.1109\/GCCE53005.2021.9622100.","DOI":"10.1109\/GCCE53005.2021.9622100"},{"key":"2292_CR39","doi-asserted-by":"publisher","unstructured":"B. Dufumier et al., \u201cContrastive Learning with Continuous Proxy Meta-Data for 3D MRI Classification,\u201d arXiv, 2021,\u00a0doi: https:\/\/doi.org\/10.48550\/arxiv.2106.08808.","DOI":"10.48550\/arxiv.2106.08808"},{"key":"2292_CR40","doi-asserted-by":"publisher","unstructured":"Z. Tan et al., \u201cOCT Retinopathy Classification via a Semi-Supervised Pseudo-Label Sub-Domain Adaptation and Fine-Tuning Method,\u201d Mathematics, vol. 12, no. 2, p. 347, Jan. 2024,\u00a0doi: https:\/\/doi.org\/10.3390\/math12020347.","DOI":"10.3390\/math12020347"},{"key":"2292_CR41","doi-asserted-by":"publisher","unstructured":"W. Song, Y. Cao, Z. Qiao, Q. Wang, and J.-J. Yang, \u201cAn Improved Semi-Supervised Learning Method on Cataract Fundus Image Classification,\u201d in 2019 IEEE 43rd Annual Computer Software and Applications Conference (COMPSAC), Jul. 2019,\u00a0doi: https:\/\/doi.org\/10.1109\/COMPSAC.2019.10233.","DOI":"10.1109\/COMPSAC.2019.10233"},{"key":"2292_CR42","doi-asserted-by":"publisher","unstructured":"J. M. A. Ramos, O. Perd\u00f3mo, and F. A. Gonz\u00e1lez, \u201cDeep Semi-Supervised and Self-Supervised Learning for Diabetic Retinopathy Detection,\u201d arXiv, 2022,\u00a0doi: https:\/\/doi.org\/10.48550\/arxiv.2208.02408.","DOI":"10.48550\/arxiv.2208.02408"},{"key":"2292_CR43","doi-asserted-by":"publisher","unstructured":"W. Du et al., \u201cImproving the Classification Performance of Esophageal Disease on Small Dataset by Semi-supervised Efficient Contrastive Learning.,\u201d J. Med. Syst., vol. 46, no. 1, p. 4, Nov. 2021, doi: https:\/\/doi.org\/10.1007\/s10916-021-01782-z.","DOI":"10.1007\/s10916-021-01782-z"}],"container-title":["Journal of Medical Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10916-025-02292-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10916-025-02292-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10916-025-02292-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,17]],"date-time":"2025-11-17T02:27:15Z","timestamp":1763346435000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10916-025-02292-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,17]]},"references-count":43,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["2292"],"URL":"https:\/\/doi.org\/10.1007\/s10916-025-02292-y","relation":{},"ISSN":["1573-689X"],"issn-type":[{"value":"1573-689X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,17]]},"assertion":[{"value":"2 July 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 October 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 November 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Ethics approval was guaranteed by scientific committee in University of Baghdad, College of Medicine. This study used anonymized data, and no identifiable patient information is included in this publication.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics Approval and Consent to Participate"}},{"value":"Not applicable, as this study used anonymized data, and no identifiable patient information is included in this publication.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for Publication"}},{"value":"The authors declare no competing interests.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing Interests"}}],"article-number":"160"}}