{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,19]],"date-time":"2026-02-19T23:01:51Z","timestamp":1771542111469,"version":"3.50.1"},"reference-count":48,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100018542","name":"Natural Science Foundation of Sichuan Province","doi-asserted-by":"publisher","award":["2023NSFSC0468"],"award-info":[{"award-number":["2023NSFSC0468"]}],"id":[{"id":"10.13039\/501100018542","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100018542","name":"Natural Science Foundation of Sichuan Province","doi-asserted-by":"publisher","award":["2023NSFSC0031"],"award-info":[{"award-number":["2023NSFSC0031"]}],"id":[{"id":"10.13039\/501100018542","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":["Artificial Intelligence in Medicine"],"published-print":{"date-parts":[[2026,4]]},"DOI":"10.1016\/j.artmed.2026.103376","type":"journal-article","created":{"date-parts":[[2026,2,4]],"date-time":"2026-02-04T07:58:56Z","timestamp":1770191936000},"page":"103376","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Towards more efficient and better multi-view and multi-modal retinopathy assisted diagnosis"],"prefix":"10.1016","volume":"174","author":[{"given":"Yonghao","family":"Huang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7700-7188","authenticated-orcid":false,"given":"Chuan","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Leiting","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"issue":"4","key":"10.1016\/j.artmed.2026.103376_b1","doi-asserted-by":"crossref","first-page":"e489","DOI":"10.1016\/S2214-109X(20)30488-5","article-title":"The lancet global health commission on global eye health: vision beyond 2020","volume":"9","author":"Burton","year":"2021","journal-title":"Lancet Glob Health"},{"key":"10.1016\/j.artmed.2026.103376_b2","doi-asserted-by":"crossref","DOI":"10.1016\/j.media.2021.101971","article-title":"Applications of deep learning in fundus images: A review","volume":"69","author":"Li","year":"2021","journal-title":"Med Image Anal"},{"key":"10.1016\/j.artmed.2026.103376_b3","series-title":"2021 IEEE international conference on bioinformatics and biomedicine","first-page":"2970","article-title":"Automatic medical lesion annotation via feature fusion correlation network","author":"Zhou","year":"2021"},{"key":"10.1016\/j.artmed.2026.103376_b4","series-title":"Primary eye examination","author":"Lee","year":"2019"},{"key":"10.1016\/j.artmed.2026.103376_b5","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2021.108104","article-title":"MVDRNet: Multi-view diabetic retinopathy detection by combining dcnns and attention mechanisms","volume":"120","author":"Luo","year":"2021","journal-title":"Pattern Recognit"},{"key":"10.1016\/j.artmed.2026.103376_b6","series-title":"Medical image computing and computer assisted intervention\u2013mICCAI 2019: 22nd international conference, shenzhen, China, October 13\u201317, 2019, proceedings, part i 22","first-page":"156","article-title":"Two-stream CNN with loose pair training for multi-modal amd categorization","author":"Wang","year":"2019"},{"key":"10.1016\/j.artmed.2026.103376_b7","series-title":"2021 IEEE international conference on bioinformatics and biomedicine","first-page":"945","article-title":"Automatic report generation based on multi-modal and multi-view model for fundus images","author":"Lan","year":"2021"},{"key":"10.1016\/j.artmed.2026.103376_b8","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2023.110544","article-title":"Model long-range dependencies for multi-modality and multi-view retinopathy diagnosis through transformers","volume":"271","author":"Huang","year":"2023","journal-title":"Knowl-Based Syst"},{"issue":"8","key":"10.1016\/j.artmed.2026.103376_b9","doi-asserted-by":"crossref","first-page":"1384","DOI":"10.3390\/diagnostics11081384","article-title":"Transmed: Transformers advance multi-modal medical image classification","volume":"11","author":"Dai","year":"2021","journal-title":"Diagnostics"},{"key":"10.1016\/j.artmed.2026.103376_b10","series-title":"On the automatic generation of medical imaging reports","author":"Jing","year":"2017"},{"key":"10.1016\/j.artmed.2026.103376_b11","article-title":"Act like a radiologist: Towards reliable multi-view correspondence reasoning for mammogram mass detection","author":"Liu","year":"2021","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"10.1016\/j.artmed.2026.103376_b12","series-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"issue":"10","key":"10.1016\/j.artmed.2026.103376_b13","doi-asserted-by":"crossref","first-page":"1993","DOI":"10.1109\/TMI.2014.2377694","article-title":"The multimodal brain tumor image segmentation benchmark (BRATS)","volume":"34","author":"Menze","year":"2014","journal-title":"IEEE Trans Med Imaging"},{"issue":"1","key":"10.1016\/j.artmed.2026.103376_b14","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/sdata.2017.117","article-title":"Advancing the cancer genome atlas glioma MRI collections with expert segmentation labels and radiomic features","volume":"4","author":"Bakas","year":"2017","journal-title":"Sci Data"},{"key":"10.1016\/j.artmed.2026.103376_b15","article-title":"Identifying the best machine learning algorithms for brain tumor segmentation","volume":"vol. 10","author":"Bakas","year":"2018"},{"key":"10.1016\/j.artmed.2026.103376_b16","article-title":"A review: Deep learning for medical image segmentation using multi-modality fusion","volume":"3","author":"Zhou","year":"2019","journal-title":"Array"},{"key":"10.1016\/j.artmed.2026.103376_b17","series-title":"TransBTSV2: Towards better and more efficient volumetric segmentation of medical images","author":"Li","year":"2022"},{"key":"10.1016\/j.artmed.2026.103376_b18","series-title":"2023 China automation congress","first-page":"8347","article-title":"Attention-TransBTS: A novel transformer-unet architecture for MRI brain tumor segmentation","author":"Li","year":"2023"},{"key":"10.1016\/j.artmed.2026.103376_b19","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Adv Neural Inf Process Syst"},{"key":"10.1016\/j.artmed.2026.103376_b20","first-page":"2","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","volume":"vol. 1","author":"Kenton","year":"2019"},{"key":"10.1016\/j.artmed.2026.103376_b21","doi-asserted-by":"crossref","unstructured":"Liu Z, Lin Y, Cao Y, Hu H, Wei Y, Zhang Z, Lin S, Guo B. Swin transformer: Hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF international conference on computer vision. 2021, p. 10012\u201322.","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"10.1016\/j.artmed.2026.103376_b22","doi-asserted-by":"crossref","unstructured":"Hassani A, Walton S, Li J, Li S, Shi H. Neighborhood attention transformer. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 2023, p. 6185\u201394.","DOI":"10.1109\/CVPR52729.2023.00599"},{"key":"10.1016\/j.artmed.2026.103376_b23","doi-asserted-by":"crossref","unstructured":"Zheng S, Lu J, Zhao H, Zhu X, Luo Z, Wang Y, Fu Y, Feng J, Xiang T, Torr PH, et al. Rethinking semantic segmentation from a sequence-to-sequence perspective with transformers. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 2021, p. 6881\u201390.","DOI":"10.1109\/CVPR46437.2021.00681"},{"key":"10.1016\/j.artmed.2026.103376_b24","series-title":"Dilated neighborhood attention transformer","author":"Hassani","year":"2022"},{"key":"10.1016\/j.artmed.2026.103376_b25","series-title":"CAT: cross-attention transformer for one-shot object detection","author":"Lin","year":"2021"},{"key":"10.1016\/j.artmed.2026.103376_b26","doi-asserted-by":"crossref","unstructured":"Ren S, Zhou D, He S, Feng J, Wang X. Shunted self-attention via multi-scale token aggregation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 2022, p. 10853\u201362.","DOI":"10.1109\/CVPR52688.2022.01058"},{"key":"10.1016\/j.artmed.2026.103376_b27","series-title":"Mobilenets: Efficient convolutional neural networks for mobile vision applications","author":"Howard","year":"2017"},{"key":"10.1016\/j.artmed.2026.103376_b28","series-title":"Gaussian error linear units (gelus)","author":"Hendrycks","year":"2016"},{"key":"10.1016\/j.artmed.2026.103376_b29","article-title":"Imagenet classification with deep convolutional neural networks","volume":"25","author":"Krizhevsky","year":"2012","journal-title":"Adv Neural Inf Process Syst"},{"key":"10.1016\/j.artmed.2026.103376_b30","series-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014"},{"key":"10.1016\/j.artmed.2026.103376_b31","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition. 2016, p. 770\u20138.","DOI":"10.1109\/CVPR.2016.90"},{"key":"10.1016\/j.artmed.2026.103376_b32","doi-asserted-by":"crossref","unstructured":"Huang G, Liu Z, Van Der Maaten L, Weinberger KQ. Densely connected convolutional networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition. 2017, p. 4700\u20138.","DOI":"10.1109\/CVPR.2017.243"},{"key":"10.1016\/j.artmed.2026.103376_b33","first-page":"8291","article-title":"Vision gnn: An image is worth graph of nodes","volume":"35","author":"Han","year":"2022","journal-title":"Adv Neural Inf Process Syst"},{"key":"10.1016\/j.artmed.2026.103376_b34","doi-asserted-by":"crossref","unstructured":"Qiu Z, Yao T, Mei T. Learning spatio-temporal representation with pseudo-3d residual networks. In: Proceedings of the IEEE international conference on computer vision. 2017, p. 5533\u201341.","DOI":"10.1109\/ICCV.2017.590"},{"key":"10.1016\/j.artmed.2026.103376_b35","series-title":"Convnet architecture search for spatiotemporal feature learning","author":"Tran","year":"2017"},{"key":"10.1016\/j.artmed.2026.103376_b36","doi-asserted-by":"crossref","unstructured":"Su H, Maji S, Kalogerakis E, Learned-Miller E. Multi-view convolutional neural networks for 3d shape recognition. In: Proceedings of the IEEE international conference on computer vision. 2015, p. 945\u201353.","DOI":"10.1109\/ICCV.2015.114"},{"key":"10.1016\/j.artmed.2026.103376_b37","series-title":"Medical image computing and computer assisted intervention\u2013mICCAI 2021: 24th international conference, strasbourg, France, September 27\u2013October 1, 2021, proceedings, part VIII 24","first-page":"45","article-title":"Mil-vt: Multiple instance learning enhanced vision transformer for fundus image classification","author":"Yu","year":"2021"},{"key":"10.1016\/j.artmed.2026.103376_b38","doi-asserted-by":"crossref","unstructured":"Wang X, Peng Y, Lu L, Lu Z, Summers RM. Tienet: Text-image embedding network for common thorax disease classification and reporting in chest x-rays. In: Proceedings of the IEEE conference on computer vision and pattern recognition. 2018, p. 9049\u201358.","DOI":"10.1109\/CVPR.2018.00943"},{"key":"10.1016\/j.artmed.2026.103376_b39","series-title":"Adam: a method for stochastic optimization","author":"Kingma","year":"2014"},{"issue":"8","key":"10.1016\/j.artmed.2026.103376_b40","doi-asserted-by":"crossref","first-page":"1819","DOI":"10.1109\/TKDE.2013.39","article-title":"A review on multi-label learning algorithms","volume":"26","author":"Zhang","year":"2013","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"10.1016\/j.artmed.2026.103376_b41","doi-asserted-by":"crossref","unstructured":"Selvaraju RR, Cogswell M, Das A, Vedantam R, Parikh D, Batra D. Grad-cam: Visual explanations from deep networks via gradient-based localization. In: Proceedings of the IEEE international conference on computer vision. 2017, p. 618\u201326.","DOI":"10.1109\/ICCV.2017.74"},{"key":"10.1016\/j.artmed.2026.103376_b42","doi-asserted-by":"crossref","unstructured":"Vinyals O, Toshev A, Bengio S, Erhan D. Show and tell: A neural image caption generator. In: Proceedings of the IEEE conference on computer vision and pattern recognition. 2015, p. 3156\u201364.","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"10.1016\/j.artmed.2026.103376_b43","doi-asserted-by":"crossref","unstructured":"Donahue J, Anne Hendricks L, Guadarrama S, Rohrbach M, Venugopalan S, Saenko K, Darrell T. Long-term recurrent convolutional networks for visual recognition and description. In: Proceedings of the IEEE conference on computer vision and pattern recognition. 2015, p. 2625\u201334.","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"10.1016\/j.artmed.2026.103376_b44","series-title":"International conference on machine learning","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"Xu","year":"2015"},{"key":"10.1016\/j.artmed.2026.103376_b45","doi-asserted-by":"crossref","unstructured":"Papineni K, Roukos S, Ward T, Zhu W-J. Bleu: a method for automatic evaluation of machine translation. In: Proceedings of the 40th annual meeting of the association for computational linguistics. 2002, p. 311\u20138.","DOI":"10.3115\/1073083.1073135"},{"key":"10.1016\/j.artmed.2026.103376_b46","series-title":"Text summarization branches out","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","author":"Lin","year":"2004"},{"key":"10.1016\/j.artmed.2026.103376_b47","doi-asserted-by":"crossref","unstructured":"Denkowski M, Lavie A. Meteor universal: Language specific translation evaluation for any target language. In: Proceedings of the ninth workshop on statistical machine translation. 2014, p. 376\u201380.","DOI":"10.3115\/v1\/W14-3348"},{"key":"10.1016\/j.artmed.2026.103376_b48","doi-asserted-by":"crossref","unstructured":"Vedantam R, Lawrence Zitnick C, Parikh D. Cider: Consensus-based image description evaluation. In: Proceedings of the IEEE conference on computer vision and pattern recognition. 2015, p. 4566\u201375.","DOI":"10.1109\/CVPR.2015.7299087"}],"container-title":["Artificial Intelligence in Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S093336572600028X?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S093336572600028X?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,2,19]],"date-time":"2026-02-19T22:01:45Z","timestamp":1771538505000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S093336572600028X"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4]]},"references-count":48,"alternative-id":["S093336572600028X"],"URL":"https:\/\/doi.org\/10.1016\/j.artmed.2026.103376","relation":{},"ISSN":["0933-3657"],"issn-type":[{"value":"0933-3657","type":"print"}],"subject":[],"published":{"date-parts":[[2026,4]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Towards more efficient and better multi-view and multi-modal retinopathy assisted diagnosis","name":"articletitle","label":"Article Title"},{"value":"Artificial Intelligence in Medicine","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.artmed.2026.103376","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"103376"}}