{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,10]],"date-time":"2026-11-10T18:50:22Z","timestamp":1794336622097,"version":"4.9.0"},"reference-count":51,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100006606","name":"Natural Science Foundation of Tianjin Municipality","doi-asserted-by":"publisher","award":["23JCYBJC00520"],"award-info":[{"award-number":["23JCYBJC00520"]}],"id":[{"id":"10.13039\/501100006606","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62371340"],"award-info":[{"award-number":["62371340"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Medical Image Analysis"],"published-print":{"date-parts":[[2025,5]]},"DOI":"10.1016\/j.media.2025.103511","type":"journal-article","created":{"date-parts":[[2025,2,24]],"date-time":"2025-02-24T11:31:26Z","timestamp":1740396686000},"page":"103511","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":38,"special_numbering":"C","title":["MSTNet: Multi-scale spatial-aware transformer with multi-instance learning for diabetic retinopathy classification"],"prefix":"10.1016","volume":"102","author":[{"given":"Xin","family":"Wei","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanbei","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fang","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lei","family":"Geng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chunyan","family":"Shan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiangyu","family":"Cao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhitao","family":"Xiao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.media.2025.103511_b1","series-title":"APTOS 2019 blindness detection","author":"APTOS 2019 blindness detection","year":"2019"},{"key":"10.1016\/j.media.2025.103511_b2","doi-asserted-by":"crossref","first-page":"4911","DOI":"10.1109\/TIP.2020.2975718","article-title":"A multiple-instance densely-connected ConvNet for aerial scene classification","volume":"29","author":"Bi","year":"2020","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.media.2025.103511_b3","doi-asserted-by":"crossref","DOI":"10.1016\/j.jvcir.2023.103956","article-title":"MIL-ViT: A multiple instance vision transformer for fundus image classification","volume":"97","author":"Bi","year":"2023","journal-title":"J. Vis. Commun. Image Represent."},{"key":"10.1016\/j.media.2025.103511_b4","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":"55","article-title":"Local-global dual perception based deep multiple instance learning for retinal disease classification","author":"Bi","year":"2021"},{"key":"10.1016\/j.media.2025.103511_b5","doi-asserted-by":"crossref","DOI":"10.1016\/j.media.2023.102837","article-title":"E2EFP-MIL: End-to-end and high-generalizability weakly supervised deep convolutional network for lung cancer classification from whole slide image","volume":"88","author":"Cao","year":"2023","journal-title":"Med. Image Anal."},{"key":"10.1016\/j.media.2025.103511_b6","doi-asserted-by":"crossref","DOI":"10.1016\/j.media.2023.102894","article-title":"MuSiC-ViT: A multi-task siamese convolutional vision transformer for differentiating change from no-change in follow-up chest radiographs","volume":"89","author":"Cho","year":"2023","journal-title":"Med. Image Anal."},{"issue":"10","key":"10.1016\/j.media.2025.103511_b7","doi-asserted-by":"crossref","first-page":"2598","DOI":"10.1109\/TMI.2022.3167808","article-title":"ResViT: residual vision transformers for multimodal medical image synthesis","volume":"41","author":"Dalmaz","year":"2022","journal-title":"IEEE Trans. Med. Imaging"},{"key":"10.1016\/j.media.2025.103511_b8","series-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"issue":"7","key":"10.1016\/j.media.2025.103511_b9","doi-asserted-by":"crossref","first-page":"2492","DOI":"10.1093\/rheumatology\/keac541","article-title":"Vision transformer assisting rheumatologists in screening for capillaroscopy changes in systemic sclerosis: an artificial intelligence model","volume":"62","author":"Garaiman","year":"2023","journal-title":"Rheumatology"},{"key":"10.1016\/j.media.2025.103511_b10","article-title":"A lightweight CNN for diabetic retinopathy classification from fundus images","volume":"62","author":"Gayathri","year":"2020","journal-title":"Biomed. Signal Process. Control."},{"key":"10.1016\/j.media.2025.103511_b11","series-title":"Medical Image Computing and Computer Assisted Intervention\u2013MICCAI 2020: 23rd International Conference, Lima, Peru, October 4\u20138, 2020, Proceedings, Part II 23","first-page":"591","article-title":"Distractor-aware neuron intrinsic learning for generic 2D medical image classifications","author":"Gong","year":"2020"},{"issue":"3","key":"10.1016\/j.media.2025.103511_b12","first-page":"236","article-title":"Correlation between non-proliferative diabetic retinopathy and macular edema: An observational study","volume":"33","author":"Han","year":"2015","journal-title":"Chin. J. Pr. Ophthalmol. (Zhongguo Shiyong Yanke Zazhi)"},{"key":"10.1016\/j.media.2025.103511_b13","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J., 2016. Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 770\u2013778.","DOI":"10.1109\/CVPR.2016.90"},{"issue":"4","key":"10.1016\/j.media.2025.103511_b14","doi-asserted-by":"crossref","first-page":"183","DOI":"10.1097\/XCE.0000000000000210","article-title":"Estimating life years lost to diabetes: outcomes from analysis of national diabetes audit and office of national statistics data","volume":"9","author":"Heald","year":"2020","journal-title":"Cardiovasc. Endocrinol. Metab."},{"key":"10.1016\/j.media.2025.103511_b15","doi-asserted-by":"crossref","first-page":"8747","DOI":"10.1007\/s12652-020-02647-y","article-title":"Classification of retinal fundus image using MS-DRLBP features and CNN-RBF classifier","volume":"12","author":"Hemalakshmi","year":"2021","journal-title":"J. Ambient. Intell. Humaniz. Comput."},{"key":"10.1016\/j.media.2025.103511_b16","doi-asserted-by":"crossref","DOI":"10.1016\/j.media.2024.103143","article-title":"Cellvit: Vision transformers for precise cell segmentation and classification","volume":"94","author":"H\u00f6rst","year":"2024","journal-title":"Med. Image Anal."},{"key":"10.1016\/j.media.2025.103511_b17","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., Van Der Maaten, L., Weinberger, K.Q., 2017. Densely connected convolutional networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 4700\u20134708.","DOI":"10.1109\/CVPR.2017.243"},{"key":"10.1016\/j.media.2025.103511_b18","series-title":"International Conference on Machine Learning","first-page":"2127","article-title":"Attention-based deep multiple instance learning","author":"Ilse","year":"2018"},{"key":"10.1016\/j.media.2025.103511_b19","unstructured":"Indian Diabetic Retinopathy Image Dataset (IDRiD), ., Indian Diabetic Retinopathy Image Dataset (IDRiD). Available: https:\/\/ieee-dataport.org\/open-access\/indian-diabetic-retinopathy-image-dataset-idrid. IEEE Dataport."},{"issue":"5","key":"10.1016\/j.media.2025.103511_b20","doi-asserted-by":"crossref","first-page":"1483","DOI":"10.1109\/TMI.2019.2951844","article-title":"CANet: cross-disease attention network for joint diabetic retinopathy and diabetic macular edema grading","volume":"39","author":"Li","year":"2019","journal-title":"IEEE Trans. Med. Imaging"},{"key":"10.1016\/j.media.2025.103511_b21","doi-asserted-by":"crossref","DOI":"10.1016\/j.artmed.2022.102259","article-title":"Lesion-attention pyramid network for diabetic retinopathy grading","volume":"126","author":"Li","year":"2022","journal-title":"Artif. Intell. Med."},{"key":"10.1016\/j.media.2025.103511_b22","article-title":"Lvit: language meets vision transformer in medical image segmentation","author":"Li","year":"2023","journal-title":"IEEE Trans. Med. Imaging"},{"issue":"6","key":"10.1016\/j.media.2025.103511_b23","doi-asserted-by":"crossref","DOI":"10.1167\/tvst.8.6.4","article-title":"Automatic detection of diabetic retinopathy in retinal fundus photographs based on deep learning algorithm","volume":"8","author":"Li","year":"2019","journal-title":"Transl. Vis. Sci. Technol."},{"key":"10.1016\/j.media.2025.103511_b24","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Goyal, P., Girshick, R., He, K., Doll\u00e1r, P., 2017. Focal loss for dense object detection. In: Proceedings of the IEEE International Conference on Computer Vision. pp. 2980\u20132988.","DOI":"10.1109\/ICCV.2017.324"},{"issue":"4","key":"10.1016\/j.media.2025.103511_b25","first-page":"327","article-title":"The role of inflammatory cytokines in the pathogenesis of diabetic retinopathy","volume":"46","author":"Liu","year":"2022","journal-title":"Int. J. Ophthalmol. Rev. (Guoji Yanke Zonglan)"},{"key":"10.1016\/j.media.2025.103511_b26","series-title":"Medical Image Computing and Computer Assisted Intervention\u2013MICCAI 2020: 23rd International Conference, Lima, Peru, October 4\u20138, 2020, Proceedings, Part V 23","first-page":"585","article-title":"Green: a graph residual re-ranking network for grading diabetic retinopathy","author":"Liu","year":"2020"},{"key":"10.1016\/j.media.2025.103511_b27","doi-asserted-by":"crossref","DOI":"10.1016\/j.artmed.2019.07.002","article-title":"Referable diabetic retinopathy identification from eye fundus images with weighted path for convolutional neural network","volume":"99","author":"Liu","year":"2019","journal-title":"Artif. Intell. Med."},{"key":"10.1016\/j.media.2025.103511_b28","doi-asserted-by":"crossref","unstructured":"Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., Guo, B., 2021. Swin transformer: Hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 10012\u201310022.","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"10.1016\/j.media.2025.103511_b29","doi-asserted-by":"crossref","first-page":"157","DOI":"10.1016\/j.media.2017.10.005","article-title":"Landmark-based deep multi-instance learning for brain disease diagnosis","volume":"43","author":"Liu","year":"2018","journal-title":"Med. Image Anal."},{"key":"10.1016\/j.media.2025.103511_b30","doi-asserted-by":"crossref","DOI":"10.1016\/j.compbiomed.2023.106791","article-title":"MedViT: a robust vision transformer for generalized medical image classification","volume":"157","author":"Manzari","year":"2023","journal-title":"Comput. Biol. Med."},{"key":"10.1016\/j.media.2025.103511_b31","unstructured":"Messidor Dataset, ., Messidor Dataset. Available: http:\/\/www.messidor.crihan.fr\/. Analysis of retinal images."},{"key":"10.1016\/j.media.2025.103511_b32","article-title":"Diabetic retinopathy detection through integration of deep learning classification framework","author":"Rakhlin","year":"2017","journal-title":"BioRxiv"},{"key":"10.1016\/j.media.2025.103511_b33","series-title":"Retinal image analysis for multi-disease detection challenge","author":"Retinal Image Analysis for Multi-Disease Detection Challenge","year":"2020"},{"key":"10.1016\/j.media.2025.103511_b34","first-page":"2136","article-title":"Transmil: Transformer based correlated multiple instance learning for whole slide image classification","volume":"34","author":"Shao","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.media.2025.103511_b35","doi-asserted-by":"crossref","DOI":"10.1016\/j.compbiomed.2022.106444","article-title":"Classification for thyroid nodule using ViT with contrastive learning in ultrasound images","volume":"152","author":"Sun","year":"2023","journal-title":"Comput. Biol. Med."},{"issue":"11","key":"10.1016\/j.media.2025.103511_b36","doi-asserted-by":"crossref","first-page":"1580","DOI":"10.1016\/j.ophtha.2021.04.027","article-title":"Global prevalence of diabetic retinopathy and projection of burden through 2045: systematic review and meta-analysis","volume":"128","author":"Teo","year":"2021","journal-title":"Ophthalmology"},{"key":"10.1016\/j.media.2025.103511_b37","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"4","key":"10.1016\/j.media.2025.103511_b38","first-page":"275","article-title":"Observation on the efficacy of laser photocoagulation in different stages of diabetic retinopathy","author":"Wang","year":"2009","journal-title":"Chin. J. Ocul. Fundus Dis. (Zhonghua Yandi Bing Zazhi)"},{"key":"10.1016\/j.media.2025.103511_b39","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TIM.2021.3123218","article-title":"ViT-P: Classification of genitourinary syndrome of menopause from OCT images based on vision transformer models","volume":"70","author":"Wang","year":"2021","journal-title":"IEEE Trans. Instrum. Meas."},{"issue":"12","key":"10.1016\/j.media.2025.103511_b40","doi-asserted-by":"crossref","first-page":"3431","DOI":"10.1109\/JBHI.2020.2983730","article-title":"UD-MIL: uncertainty-driven deep multiple instance learning for OCT image classification","volume":"24","author":"Wang","year":"2020","journal-title":"IEEE J. Biomed. Heal. Inform."},{"issue":"3","key":"10.1016\/j.media.2025.103511_b41","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"},{"issue":"5","key":"10.1016\/j.media.2025.103511_b42","doi-asserted-by":"crossref","first-page":"2216","DOI":"10.1109\/JBHI.2021.3119519","article-title":"Joint learning of multi-level tasks for diabetic retinopathy grading on low-resolution fundus images","volume":"26","author":"Wang","year":"2021","journal-title":"IEEE J. Biomed. Heal. Inform."},{"issue":"12","key":"10.1016\/j.media.2025.103511_b43","doi-asserted-by":"crossref","first-page":"7850","DOI":"10.1002\/mp.15312","article-title":"Vision transformer-based recognition of diabetic retinopathy grade","volume":"48","author":"Wu","year":"2021","journal-title":"Med. Phys."},{"key":"10.1016\/j.media.2025.103511_b44","doi-asserted-by":"crossref","unstructured":"Wu, H., Xiao, B., Codella, N., Liu, M., Dai, X., Yuan, L., Zhang, L., 2021b. Cvt: Introducing convolutions to vision transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 22\u201331.","DOI":"10.1109\/ICCV48922.2021.00009"},{"issue":"3","key":"10.1016\/j.media.2025.103511_b45","first-page":"249","article-title":"Multicolor laser treatment for retinal macroaneurysm","volume":"19","author":"Yan","year":"2011","journal-title":"J. Clin. Ophthalmol. (Linchuang Yanke Zazhi)"},{"key":"10.1016\/j.media.2025.103511_b46","article-title":"A novel transformer model with multiple instance learning for diabetic retinopathy classification","author":"Yang","year":"2024","journal-title":"IEEE Access"},{"key":"10.1016\/j.media.2025.103511_b47","doi-asserted-by":"crossref","DOI":"10.1016\/j.media.2020.101789","article-title":"Whole slide images based cancer survival prediction using attention guided deep multiple instance learning networks","volume":"65","author":"Yao","year":"2020","journal-title":"Med. Image Anal."},{"key":"10.1016\/j.media.2025.103511_b48","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.media.2025.103511_b49","doi-asserted-by":"crossref","unstructured":"Yuan, L., Chen, Y., Wang, T., Yu, W., Shi, Y., Jiang, Z.-H., Tay, F.E., Feng, J., Yan, S., 2021. Tokens-to-token vit: Training vision transformers from scratch on imagenet. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 558\u2013567.","DOI":"10.1109\/ICCV48922.2021.00060"},{"key":"10.1016\/j.media.2025.103511_b50","doi-asserted-by":"crossref","unstructured":"Zhang, H., Meng, Y., Zhao, Y., Qiao, Y., Yang, X., Coupland, S.E., Zheng, Y., 2022. Dtfd-mil: Double-tier feature distillation multiple instance learning for histopathology whole slide image classification. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 18802\u201318812.","DOI":"10.1109\/CVPR52688.2022.01824"},{"issue":"2","key":"10.1016\/j.media.2025.103511_b51","first-page":"94","article-title":"A case of retinal macroaneurysm with retinal branch artery occlusion","volume":"26","author":"Zhao","year":"2017","journal-title":"Ophthalmol. (Yan Ke)"}],"container-title":["Medical Image Analysis"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1361841525000593?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1361841525000593?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T20:02:15Z","timestamp":1762372935000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1361841525000593"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5]]},"references-count":51,"alternative-id":["S1361841525000593"],"URL":"https:\/\/doi.org\/10.1016\/j.media.2025.103511","relation":{},"ISSN":["1361-8415"],"issn-type":[{"value":"1361-8415","type":"print"}],"subject":[],"published":{"date-parts":[[2025,5]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"MSTNet: Multi-scale spatial-aware transformer with multi-instance learning for diabetic retinopathy classification","name":"articletitle","label":"Article Title"},{"value":"Medical Image Analysis","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.media.2025.103511","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2025 Published by Elsevier B.V.","name":"copyright","label":"Copyright"}],"article-number":"103511"}}