{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,27]],"date-time":"2026-10-27T19:37:37Z","timestamp":1793129857947,"version":"4.5.0"},"reference-count":51,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62273035"],"award-info":[{"award-number":["62273035"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004826","name":"Beijing Natural Science Foundation","doi-asserted-by":"publisher","award":["4252045"],"award-info":[{"award-number":["4252045"]}],"id":[{"id":"10.13039\/501100004826","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["clinicalkey.com","clinicalkey.com.au","clinicalkey.es","clinicalkey.fr","clinicalkey.jp","elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Computerized Medical Imaging and Graphics"],"published-print":{"date-parts":[[2026,2]]},"DOI":"10.1016\/j.compmedimag.2026.102701","type":"journal-article","created":{"date-parts":[[2026,1,9]],"date-time":"2026-01-09T00:14:50Z","timestamp":1767917690000},"page":"102701","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":6,"special_numbering":"C","title":["A hybrid Transformer-CNN framework for uncertainty-guided semi-supervised multiclass eye disease classification with enhanced interpretability"],"prefix":"10.1016","volume":"128","author":[{"given":"Muhammad Hammad","family":"Malik","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zishuo","family":"Wan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yingying","family":"Ren","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Da-Wei","family":"Ding","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"20","key":"10.1016\/j.compmedimag.2026.102701_bib1","doi-asserted-by":"crossref","first-page":"3165","DOI":"10.3390\/diagnostics13203165","article-title":"Deep-Ocular: improved transfer learning architecture using self-attention and dense layers for recognition of ocular diseases","volume":"13","author":"Abbas","year":"2023","journal-title":"Diagnostics"},{"issue":"1","key":"10.1016\/j.compmedimag.2026.102701_bib2","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":"Abr\u00e0moff","year":"2018","journal-title":"NPJ Digit. Med."},{"key":"10.1016\/j.compmedimag.2026.102701_bib3","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2023.102059","article-title":"Fundus-deepnet: multi-label deep learning classification system for enhanced detection of multiple ocular diseases through data fusion of fundus images","volume":"102","author":"Al-Fahdawi","year":"2024","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.compmedimag.2026.102701_bib4","doi-asserted-by":"crossref","first-page":"23894","DOI":"10.1109\/ACCESS.2021.3056641","article-title":"A comparative study of deep learning models for diagnosing glaucoma from fundus images","volume":"9","author":"Alghamdi","year":"2021","journal-title":"IEEE Access"},{"key":"10.1016\/j.compmedimag.2026.102701_bib5","unstructured":"Babaqi, T., Jaradat, M., Yildirim, A.E., Al-Nimer, S.H., Won, D., 2023. Eye disease classification using deep learning techniques. arXiv preprint arXiv:2307.10501. \u3008https:\/\/doi.org\/10.48550\/arXiv.2307.10501\u3009."},{"key":"10.1016\/j.compmedimag.2026.102701_bib6","doi-asserted-by":"crossref","DOI":"10.1016\/j.cosrev.2019.100203","article-title":"Application of deep learning for retinal image analysis: a review","volume":"35","author":"Badar","year":"2020","journal-title":"Comput. Sci. Rev."},{"key":"10.1016\/j.compmedimag.2026.102701_bib7","unstructured":"Berthelot, D., et al., 2019. MixMatch: A holistic approach to semi-supervised learning. arXiv preprint arXiv:1905.02249. \u3008https:\/\/doi.org\/10.48550\/arXiv.1905.02249\u3009."},{"issue":"1","key":"10.1016\/j.compmedimag.2026.102701_bib8","doi-asserted-by":"crossref","first-page":"26","DOI":"10.1186\/s44147-023-00335-0","article-title":"Automatic multi-disease classification on retinal images using multilevel glowworm swarm convolutional neural network","volume":"71","author":"Chavan","year":"2024","journal-title":"J. Eng. Appl. Sci."},{"key":"10.1016\/j.compmedimag.2026.102701_bib9","unstructured":"Chen, J., et al., 2021. TransUNet: Transformers make strong encoders for medical image segmentation. arXiv preprint arXiv:2102.04306. \u3008https:\/\/doi.org\/10.48550\/arXiv.2102.04306\u3009."},{"key":"10.1016\/j.compmedimag.2026.102701_bib10","doi-asserted-by":"crossref","first-page":"280","DOI":"10.1016\/j.media.2019.03.009","article-title":"Not-so-supervised: a survey of semi-supervised, multi-instance, and transfer learning in medical image analysis","volume":"54","author":"Cheplygina","year":"2019","journal-title":"Med. Image Anal."},{"key":"10.1016\/j.compmedimag.2026.102701_bib11","series-title":"IEEE 3rd Int. Conf. Pattern Recognit. Mach. Learn. (PRML)","first-page":"167","article-title":"Towards semi-supervised segmentation of retinal fundus images via self-training","author":"Deng","year":"2022"},{"key":"10.1016\/j.compmedimag.2026.102701_bib12","unstructured":"Dosovitskiy, A., et al., 2021. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929. \u3008https:\/\/doi.org\/10.48550\/arXiv.2010.11929\u3009."},{"key":"10.1016\/j.compmedimag.2026.102701_bib13","unstructured":"Gal, Y., Ghahramani, Z., 2016. Dropout as a Bayesian approximation: Representing model uncertainty in deep learning. arXiv preprint arXiv:1506.02142. \u3008https:\/\/doi.org\/10.48550\/arXiv.1506.02142\u3009."},{"key":"10.1016\/j.compmedimag.2026.102701_bib14","series-title":"IEEE Int. Conf. Adv. Comput. Technol. Appl. (ICACTA)","first-page":"1","article-title":"Deep classification of fundus images using semi-supervised GAN","author":"Gobinath","year":"2022"},{"issue":"2","key":"10.1016\/j.compmedimag.2026.102701_bib15","doi-asserted-by":"crossref","first-page":"892","DOI":"10.1364\/BOE.10.000892","article-title":"Automatic glaucoma classification using color fundus images based on convolutional neural networks and transfer learning","volume":"10","author":"G\u00f3mez-Valverde","year":"2019","journal-title":"Biomed. Opt. Express"},{"issue":"22","key":"10.1016\/j.compmedimag.2026.102701_bib16","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","volume":"316","author":"Gulshan","year":"2016","journal-title":"JAMA"},{"key":"10.1016\/j.compmedimag.2026.102701_bib17","first-page":"74","article-title":"UNETR: transformers for 3D medical image segmentation","author":"Hatamizadeh","year":"2022","journal-title":"IEEE\/CVF Winter Conf. Appl. Comput. Vis. (WACV)"},{"key":"10.1016\/j.compmedimag.2026.102701_bib18","series-title":"In: Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR)","first-page":"770","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"key":"10.1016\/j.compmedimag.2026.102701_bib19","first-page":"1","article-title":"Semi-supervised learning with out-of-distribution unlabeled samples for retinal image classification","author":"Jia","year":"2023","journal-title":"IEEE20th Int. Symp. Biomed. Imaging (ISBI)"},{"key":"10.1016\/j.compmedimag.2026.102701_bib20","series-title":"In: IEEE 4th Annual Flagship India Council International Subsections Conference (INDISCON), Mysore, India","first-page":"1","article-title":"Classification of eye diseases using multi-model CNN","author":"Kaushik","year":"2023"},{"issue":"5","key":"10.1016\/j.compmedimag.2026.102701_bib21","doi-asserted-by":"crossref","first-page":"1122","DOI":"10.1016\/j.cell.2018.02.010","article-title":"Identifying medical diagnoses and treatable diseases by image-based deep learning","volume":"172","author":"Kermany","year":"2018","journal-title":"Cell"},{"key":"10.1016\/j.compmedimag.2026.102701_bib22","series-title":"IEEE World Conf. Commun. Comput. (WCONF)","first-page":"1","article-title":"Retinal fundus image classification using hybrid deep learning model","author":"Lakhera","year":"2023"},{"key":"10.1016\/j.compmedimag.2026.102701_bib23","unstructured":"Lakshminarayanan, B., et al., 2017. Simple and scalable predictive uncertainty estimation using deep ensembles. arXiv preprint arXiv:1612.01474. \u3008https:\/\/doi.org\/10.48550\/arXiv.1612.01474\u3009."},{"key":"10.1016\/j.compmedimag.2026.102701_bib24","doi-asserted-by":"crossref","first-page":"27331","DOI":"10.1109\/ACCESS.2024.3367772","article-title":"Application of semi-supervised learning in image classification: research on fusion of labeled and unlabeled data","volume":"12","author":"Li","year":"2024","journal-title":"IEEE Access"},{"key":"10.1016\/j.compmedimag.2026.102701_bib25","doi-asserted-by":"crossref","first-page":"454","DOI":"10.1109\/LSP.2021.3057548","article-title":"Multi-label classification of fundus images with graph convolutional network and self-supervised learning","volume":"28","author":"Lin","year":"2021","journal-title":"IEEE Signal Process. Lett."},{"key":"10.1016\/j.compmedimag.2026.102701_bib26","doi-asserted-by":"crossref","first-page":"60","DOI":"10.1016\/j.media.2017.07.005","article-title":"A survey on deep learning in medical image analysis","volume":"42","author":"Litjens","year":"2017","journal-title":"Med. Image Anal."},{"key":"10.1016\/j.compmedimag.2026.102701_bib27","series-title":"Ophthalmic Medical Image Analysis: 6th International Workshop, OMIA 2019, Held in Conjunction with MICCAI 2019, Shenzhen, China","first-page":"60","article-title":"Semi-supervised adversarial learning for diabetic retinopathy screening","author":"Liu","year":"2019"},{"issue":"4","key":"10.1016\/j.compmedimag.2026.102701_bib28","doi-asserted-by":"crossref","first-page":"2731","DOI":"10.1109\/JBHI.2024.3457232","article-title":"Label-aware dual graph neural networks for multi-label fundus image classification","volume":"29","author":"Liu","year":"2025","journal-title":"IEEE J. Biomed. Health Inf."},{"issue":"6","key":"10.1016\/j.compmedimag.2026.102701_bib29","doi-asserted-by":"crossref","first-page":"3699","DOI":"10.1364\/BOE.516764","article-title":"Cross-modal attention network for retinal disease classification based on multi-modal images","volume":"15","author":"Liu","year":"2024","journal-title":"Biomed. Opt. Express"},{"key":"10.1016\/j.compmedimag.2026.102701_bib30","doi-asserted-by":"crossref","unstructured":"Liu, Z., Mao, H., Wu, C.Y., Feichtenhofer, C., Darrell, T., Xie, S., 2022. A ConvNet for the 2020s. arXiv preprint arXiv:2201.03545. \u3008https:\/\/doi.org\/10.48550\/arXiv.2201.03545\u3009.","DOI":"10.1109\/CVPR52688.2022.01167"},{"issue":"8","key":"10.1016\/j.compmedimag.2026.102701_bib31","doi-asserted-by":"crossref","first-page":"1979","DOI":"10.1109\/TPAMI.2018.2858821","article-title":"Virtual adversarial training: a regularization method for supervised and semi-supervised learning","volume":"41","author":"Miyato","year":"2019","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"3","key":"10.1016\/j.compmedimag.2026.102701_bib32","first-page":"70","article-title":"Clinical decision support systems in ophthalmology: a systematic search and a narrative review","volume":"46","author":"Motamed Shariati","year":"2024","journal-title":"Appl. Med. Inf."},{"issue":"5","key":"10.1016\/j.compmedimag.2026.102701_bib33","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s10462-024-10770-x","article-title":"Diabetic retinopathy detection using supervised and unsupervised deep learning: a review study","volume":"57","author":"Naz","year":"2024","journal-title":"Artif. Intell. Rev."},{"issue":"1","key":"10.1016\/j.compmedimag.2026.102701_bib34","doi-asserted-by":"crossref","first-page":"1897","DOI":"10.1038\/s41598-021-81539-3","article-title":"Early detection of diabetic retinopathy based on deep learning and ultra-wide-field fundus images","volume":"11","author":"Oh","year":"2021","journal-title":"Sci. Rep."},{"key":"10.1016\/j.compmedimag.2026.102701_bib35","doi-asserted-by":"crossref","DOI":"10.3389\/fphys.2023.1126780","article-title":"Fundus image classification using Inception V3 and ResNet-50 for the early diagnostics of fundus diseases","volume":"14","author":"Pan","year":"2023","journal-title":"Front. Physiol."},{"key":"10.1016\/j.compmedimag.2026.102701_bib36","doi-asserted-by":"crossref","DOI":"10.1016\/j.bspc.2019.04.010","article-title":"Computer-aided diagnosis of cataract using deep transfer learning","volume":"53","author":"Pratap","year":"2019","journal-title":"Biomed. Signal Process. Control"},{"key":"10.1016\/j.compmedimag.2026.102701_bib37","doi-asserted-by":"crossref","DOI":"10.1016\/j.bspc.2024.106120","article-title":"An evaluation of AI-based methods for papilledema detection in retinal fundus images","volume":"92","author":"Salaheldin","year":"2024","journal-title":"Biomed. Signal Process. Control"},{"key":"10.1016\/j.compmedimag.2026.102701_bib38","article-title":"Explainable AI: interpreting, explaining and visualizing deep learning","volume":"11700","author":"Samek","year":"2019"},{"key":"10.1016\/j.compmedimag.2026.102701_bib39","series-title":"In: Proc. IEEE Int. Conf. Comput. Vis. (ICCV)","first-page":"618","article-title":"Grad-CAM: visual explanations from deep networks via gradient-based localization","author":"Selvaraju","year":"2017"},{"issue":"1","key":"10.1016\/j.compmedimag.2026.102701_bib40","doi-asserted-by":"crossref","first-page":"59","DOI":"10.1007\/s42979-021-00945-6","article-title":"Classification of multiple retinal disorders from enhanced fundus images using semi-supervised GAN","volume":"3","author":"Smitha","year":"2022","journal-title":"SN Comput. Sci."},{"key":"10.1016\/j.compmedimag.2026.102701_bib41","unstructured":"Sohn, K., et al., 2020. FixMatch: Simplifying semi-supervised learning with consistency and confidence. arXiv preprint arXiv:2001.07685. \u3008https:\/\/doi.org\/10.48550\/arXiv.2001.07685\u3009."},{"key":"10.1016\/j.compmedimag.2026.102701_bib42","first-page":"362","article-title":"An improved semi-supervised learning method on cataract fundus image classification","volume":"2","author":"Song","year":"2019","journal-title":"IEEE43rd Annu. Comput. Softw. Appl. Conf. (COMPSAC)"},{"key":"10.1016\/j.compmedimag.2026.102701_bib43","unstructured":"Tarvainen, A., Valpola, H., 2017. Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results. arXiv preprint arXiv:1703.01780. \u3008https:\/\/doi.org\/10.48550\/arXiv.1703.01780\u3009."},{"key":"10.1016\/j.compmedimag.2026.102701_bib44","article-title":"A deep neural network and machine learning approach for retinal fundus image classification","volume":"3","author":"Thanki","year":"2023","journal-title":"Healthc. Anal."},{"issue":"10","key":"10.1016\/j.compmedimag.2026.102701_bib45","first-page":"1088","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":"135","author":"Ting","year":"2017","journal-title":"JAMA Ophthalmol."},{"key":"10.1016\/j.compmedimag.2026.102701_bib46","unstructured":"Vaswani, A., et al., 2017. Attention is all you need. arXiv preprint arXiv:1706.03762. \u3008https:\/\/doi.org\/10.48550\/arXiv.1706.03762\u3009."},{"issue":"9","key":"10.1016\/j.compmedimag.2026.102701_bib47","doi-asserted-by":"crossref","first-page":"2714","DOI":"10.1109\/TMI.2023.3263216","article-title":"Fundus image-label pairs synthesis and retinopathy screening via GANs with class-imbalanced semi-supervised learning","volume":"42","author":"Xie","year":"2023","journal-title":"IEEE Trans. Med. Imaging"},{"issue":"12","key":"10.1016\/j.compmedimag.2026.102701_bib48","doi-asserted-by":"crossref","first-page":"2054","DOI":"10.3390\/molecules22122054","article-title":"Deep convolutional neural network-based early automated detection of diabetic retinopathy using fundus image","volume":"22","author":"Xu","year":"2017","journal-title":"Molecules"},{"key":"10.1016\/j.compmedimag.2026.102701_bib49","doi-asserted-by":"crossref","DOI":"10.1155\/2023\/2973836","article-title":"Automatic cataract severity detection and grading using deep learning","volume":"2023","author":"Yadav","year":"2023","journal-title":"J. Sens"},{"key":"10.1016\/j.compmedimag.2026.102701_bib50","first-page":"35778","article-title":"Hybrid graph convolutional network for semi-supervised retinal image classification","volume":"9","author":"Zhang","year":"2021","journal-title":"IEEE"},{"issue":"3","key":"10.1016\/j.compmedimag.2026.102701_bib51","doi-asserted-by":"crossref","first-page":"1901","DOI":"10.3390\/app13031901","article-title":"A wrapped approach using unlabeled data for diabetic retinopathy diagnosis","volume":"13","author":"Zhang","year":"2023","journal-title":"Appl. Sci."}],"container-title":["Computerized Medical Imaging and Graphics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0895611126000042?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0895611126000042?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T21:44:36Z","timestamp":1785447876000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0895611126000042"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2]]},"references-count":51,"alternative-id":["S0895611126000042"],"URL":"https:\/\/doi.org\/10.1016\/j.compmedimag.2026.102701","relation":{},"ISSN":["0895-6111"],"issn-type":[{"value":"0895-6111","type":"print"}],"subject":[],"published":{"date-parts":[[2026,2]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"A hybrid Transformer-CNN framework for uncertainty-guided semi-supervised multiclass eye disease classification with enhanced interpretability","name":"articletitle","label":"Article Title"},{"value":"Computerized Medical Imaging and Graphics","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.compmedimag.2026.102701","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"102701"}}