{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,15]],"date-time":"2026-05-15T00:12:35Z","timestamp":1778803955588,"version":"3.51.4"},"reference-count":51,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,3,16]],"date-time":"2026-03-16T00:00:00Z","timestamp":1773619200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100000038","name":"Natural Sciences and Engineering Research Council of Canada","doi-asserted-by":"publisher","award":["RGPIN-2022-05316"],"award-info":[{"award-number":["RGPIN-2022-05316"]}],"id":[{"id":"10.13039\/501100000038","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000038","name":"Natural Sciences and Engineering Research Council of Canada","doi-asserted-by":"publisher","award":["ALLRP 602633-24"],"award-info":[{"award-number":["ALLRP 602633-24"]}],"id":[{"id":"10.13039\/501100000038","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100014188","name":"Ministry of Science and ICT, South Korea","doi-asserted-by":"publisher","award":["RS-2024-00445087"],"award-info":[{"award-number":["RS-2024-00445087"]}],"id":[{"id":"10.13039\/501100014188","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100014188","name":"Ministry of Science and ICT, South Korea","doi-asserted-by":"publisher","award":["RS-2025-25464461"],"award-info":[{"award-number":["RS-2025-25464461"]}],"id":[{"id":"10.13039\/501100014188","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001712","name":"Stichting voor Fundamenteel Onderzoek der Materie","doi-asserted-by":"publisher","award":["PXJR\/GR027485"],"award-info":[{"award-number":["PXJR\/GR027485"]}],"id":[{"id":"10.13039\/501100001712","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000233","name":"Genome BC","doi-asserted-by":"publisher","award":["GEN037"],"award-info":[{"award-number":["GEN037"]}],"id":[{"id":"10.13039\/501100000233","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000196","name":"Canada Foundation for Innovation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000196","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001804","name":"Canada Research Chairs","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001804","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100012161","name":"Faculty of Medicine, University of British Columbia","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100012161","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004489","name":"Mitacs","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004489","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005247","name":"University of British Columbia","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100005247","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100006785","name":"Google Inc","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006785","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000024","name":"Canadian Institutes of Health Research","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000024","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100007631","name":"CIFAR","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100007631","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":[[2026,6]]},"DOI":"10.1016\/j.media.2026.104013","type":"journal-article","created":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T00:31:19Z","timestamp":1773189079000},"page":"104013","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["PTCMIL: multiple instance learning via prompt token clustering for whole slide image analysis"],"prefix":"10.1016","volume":"111","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2845-7550","authenticated-orcid":false,"given":"Beidi","family":"Zhao","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6918-677X","authenticated-orcid":false,"given":"Sangmook","family":"Kim","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8400-3780","authenticated-orcid":false,"given":"Hao","family":"Chen","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7898-4201","authenticated-orcid":false,"given":"Chen","family":"Zhou","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7232-0933","authenticated-orcid":false,"given":"Zu-hua","family":"Gao","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0225-4173","authenticated-orcid":false,"given":"Gang","family":"Wang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8833-0244","authenticated-orcid":false,"given":"Xiaoxiao","family":"Li","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"issue":"2","key":"10.1016\/j.media.2026.104013_bib0001","doi-asserted-by":"crossref","first-page":"93","DOI":"10.1038\/s44287-023-00012-7","article-title":"Artificial intelligence applications in histopathology","volume":"1","author":"Bahadir","year":"2024","journal-title":"Nat. Rev. Electri. Eng."},{"key":"10.1016\/j.media.2026.104013_bib0002","doi-asserted-by":"crossref","first-page":"25005","DOI":"10.52202\/068431-1813","article-title":"Visual prompting via image inpainting","volume":"35","author":"Bar","year":"2022","journal-title":"Adv. Neural Inf. Process Syst."},{"issue":"22","key":"10.1016\/j.media.2026.104013_bib0003","doi-asserted-by":"crossref","first-page":"2199","DOI":"10.1001\/jama.2017.14585","article-title":"Diagnostic assessment of deep learning algorithms for detection of lymph node metastases in women with breast cancer","volume":"318","author":"Bejnordi","year":"2017","journal-title":"JAMA"},{"key":"10.1016\/j.media.2026.104013_bib0004","doi-asserted-by":"crossref","DOI":"10.1093\/database\/baac093","article-title":"Bracs: a dataset for breast carcinoma subtyping in h&e histology images","volume":"2022","author":"Brancati","year":"2022","journal-title":"Database"},{"issue":"1","key":"10.1016\/j.media.2026.104013_bib0005","doi-asserted-by":"crossref","first-page":"154","DOI":"10.1038\/s41591-021-01620-2","article-title":"Artificial intelligence for diagnosis and gleason grading of prostate cancer: the PANDA challenge","volume":"28","author":"Bulten","year":"2022","journal-title":"Nat. Med."},{"issue":"10","key":"10.1016\/j.media.2026.104013_bib0006","doi-asserted-by":"crossref","first-page":"1113","DOI":"10.1038\/ng.2764","article-title":"The cancer genome atlas pan-cancer analysis project","volume":"45","author":"Cancer Genome Atlas Research Network","year":"2013","journal-title":"Nat. Genet."},{"key":"10.1016\/j.media.2026.104013_bib0007","doi-asserted-by":"crossref","first-page":"329","DOI":"10.1016\/j.patcog.2017.10.009","article-title":"Multiple instance learning: a survey of problem characteristics and applications","volume":"77","author":"Carbonneau","year":"2018","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.media.2026.104013_bib0008","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"15661","article-title":"Histopathology whole slide image analysis with heterogeneous graph representation learning","author":"Chan","year":"2023"},{"key":"10.1016\/j.media.2026.104013_bib0009","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"19133","article-title":"Understanding and improving visual prompting: a label-mapping perspective","author":"Chen","year":"2023"},{"key":"10.1016\/j.media.2026.104013_bib0010","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"16144","article-title":"Scaling vision transformers to gigapixel images via hierarchical self-supervised learning","author":"Chen","year":"2022"},{"issue":"3","key":"10.1016\/j.media.2026.104013_bib0011","doi-asserted-by":"crossref","first-page":"850","DOI":"10.1038\/s41591-024-02857-3","article-title":"Towards a general-purpose foundation model for computational pathology","volume":"30","author":"Chen","year":"2024","journal-title":"Nat. Med."},{"key":"10.1016\/j.media.2026.104013_bib0012","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":"339","article-title":"Whole slide images are 2d point clouds: context-aware survival prediction using patch-based graph convolutional networks","author":"Chen","year":"2021"},{"key":"10.1016\/j.media.2026.104013_bib0013","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV)","first-page":"4015","article-title":"Multimodal co-attention transformer for survival prediction in gigapixel whole slide images","author":"Chen","year":"2021"},{"key":"10.1016\/j.media.2026.104013_bib0014","series-title":"European Conference on Computer Vision","first-page":"232","article-title":"cDP-MIL: robust multiple instance learning via cascaded dirichlet process","author":"Chen","year":"2025"},{"issue":"4","key":"10.1016\/j.media.2026.104013_bib0015","doi-asserted-by":"crossref","first-page":"412","DOI":"10.1038\/s41374-020-00514-0","article-title":"Artificial intelligence and computational pathology","volume":"101","author":"Cui","year":"2021","journal-title":"Lab. Invest."},{"key":"10.1016\/j.media.2026.104013_bib0016","doi-asserted-by":"crossref","DOI":"10.1016\/j.media.2024.103124","article-title":"Cross-scale multi-instance learning for pathological image diagnosis","volume":"94","author":"Deng","year":"2024","journal-title":"Med. Image Anal."},{"key":"10.1016\/j.media.2026.104013_bib0017","series-title":"Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","author":"Glorot","year":"2010"},{"key":"10.1016\/j.media.2026.104013_bib0018","series-title":"European Conference on Computer Vision","first-page":"200","article-title":"Agglomerative token clustering","author":"Haurum","year":"2025"},{"key":"10.1016\/j.media.2026.104013_bib0019","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"933","article-title":"H\u2227 2-MIL: exploring hierarchical representation with heterogeneous multiple instance learning for whole slide image analysis","volume":"Vol. 36","author":"Hou","year":"2022"},{"key":"10.1016\/j.media.2026.104013_bib0020","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.2026.104013_bib0021","series-title":"Algorithms for Clustering Data","author":"Jain","year":"1988"},{"key":"10.1016\/j.media.2026.104013_bib0022","series-title":"European Conference on Computer Vision","first-page":"709","article-title":"Visual prompt tuning","author":"Jia","year":"2022"},{"key":"10.1016\/j.media.2026.104013_bib0023","first-page":"25586","article-title":"Brain network transformer","volume":"35","author":"Kan","year":"2022","journal-title":"Adv. Neural Inf. Process Syst."},{"key":"10.1016\/j.media.2026.104013_bib0024","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"14318","article-title":"Dual-stream multiple instance learning network for whole slide image classification with self-supervised contrastive learning","author":"Li","year":"2021"},{"issue":"6","key":"10.1016\/j.media.2026.104013_bib0025","doi-asserted-by":"crossref","first-page":"555","DOI":"10.1038\/s41551-020-00682-w","article-title":"Data-efficient and weakly supervised computational pathology on whole-slide images","volume":"5","author":"Lu","year":"2021","journal-title":"Nat. Biomed. Eng."},{"key":"10.1016\/j.media.2026.104013_bib0026","series-title":"Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision","first-page":"12","article-title":"Token pooling in vision transformers for image classification","author":"Marin","year":"2023"},{"key":"10.1016\/j.media.2026.104013_bib0027","first-page":"13937","article-title":"Dynamicvit: efficient vision transformers with dynamic token sparsification","volume":"34","author":"Rao","year":"2021","journal-title":"Adv. Neural Inf. Process Syst."},{"key":"10.1016\/j.media.2026.104013_bib0028","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.2026.104013_bib0029","series-title":"Medical Imaging with Deep Learning","first-page":"682","article-title":"Cluster-to-conquer: a framework for end-to-end multi-instance learning for whole slide image classification","author":"Sharma","year":"2021"},{"key":"10.1016\/j.media.2026.104013_bib0030","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"11248","article-title":"Vila-MIL: dual-scale vision-language multiple instance learning for whole slide image classification","author":"Shi","year":"2024"},{"key":"10.1016\/j.media.2026.104013_bib0031","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"11566","article-title":"Morphological prototyping for unsupervised slide representation learning in computational pathology","author":"Song","year":"2024"},{"key":"10.1016\/j.media.2026.104013_bib0032","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"11566","article-title":"Morphological prototyping for unsupervised slide representation learning in computational pathology","author":"Song","year":"2024"},{"key":"10.1016\/j.media.2026.104013_bib0033","doi-asserted-by":"crossref","DOI":"10.1016\/j.media.2023.102743","article-title":"Handcrafted histological transformer (h2t): unsupervised representation of whole slide images","volume":"85","author":"Vu","year":"2023","journal-title":"Med. Image Anal."},{"key":"10.1016\/j.media.2026.104013_bib0034","doi-asserted-by":"crossref","unstructured":"Wang, H., Luo, L., Wang, F., Tong, R., Chen, Y.-W., Hu, H., Lin, L., Chen, H., 2023a. Iteratively coupled multiple instance learning from instance to bag classifier for whole slide image classification. arXiv: 2303.15749.","DOI":"10.1007\/978-3-031-43987-2_45"},{"key":"10.1016\/j.media.2026.104013_bib0035","doi-asserted-by":"crossref","DOI":"10.1016\/j.metrad.2023.100047","article-title":"Review of large vision models and visual prompt engineering","author":"Wang","year":"2023","journal-title":"Meta-Radiol."},{"key":"10.1016\/j.media.2026.104013_bib0036","doi-asserted-by":"crossref","DOI":"10.1016\/j.media.2022.102559","article-title":"Transformer-based unsupervised contrastive learning for histopathological image classification","volume":"81","author":"Wang","year":"2022","journal-title":"Med. Image Anal."},{"key":"10.1016\/j.media.2026.104013_bib0037","series-title":"The Eleventh International Conference on Learning Representations","article-title":"Exploring low-rank property in multiple instance learning for whole slide image classification","author":"Xiang","year":"2023"},{"key":"10.1016\/j.media.2026.104013_bib0038","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"21241","article-title":"Multimodal optimal transport-based co-attention transformer with global structure consistency for survival prediction","author":"Xu","year":"2023"},{"key":"10.1016\/j.media.2026.104013_bib0039","doi-asserted-by":"crossref","DOI":"10.1016\/j.compmedimag.2022.102053","article-title":"Deep contrastive learning based tissue clustering for annotation-free histopathology image analysis","volume":"97","author":"Yan","year":"2022","journal-title":"Computer. Med. Imaging Graph."},{"key":"10.1016\/j.media.2026.104013_bib0040","series-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention","first-page":"296","article-title":"Mambamil: enhancing long sequence modeling with sequence reordering in computational pathology","author":"Yang","year":"2024"},{"key":"10.1016\/j.media.2026.104013_bib0041","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.2026.104013_bib0042","doi-asserted-by":"crossref","DOI":"10.1016\/j.media.2023.102748","article-title":"Prototypical multiple instance learning for predicting lymph node metastasis of breast cancer from whole-slide pathological images","volume":"85","author":"Yu","year":"2023","journal-title":"Med. Image Anal."},{"key":"10.1016\/j.media.2026.104013_bib0043","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"11101","article-title":"Not all tokens are equal: human-centric visual analysis via token clustering transformer","author":"Zeng","year":"2022"},{"key":"10.1016\/j.media.2026.104013_bib0044","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"18802","article-title":"Dtfd-mil: double-tier feature distillation multiple instance learning for histopathology whole slide image classification","author":"Zhang","year":"2022"},{"key":"10.1016\/j.media.2026.104013_bib0045","doi-asserted-by":"crossref","DOI":"10.1016\/j.asoc.2024.111653","article-title":"Prognosis prediction based on liver histopathological image via graph deep learning and transformer","volume":"161","author":"Zhang","year":"2024","journal-title":"Appl. Soft Comput."},{"key":"10.1016\/j.media.2026.104013_bib0046","series-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention","first-page":"502","article-title":"Ptcmil: multiple instance learning via prompt token clustering for whole slide image analysis","author":"Zhao","year":"2025"},{"key":"10.1016\/j.media.2026.104013_bib0047","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"3606","article-title":"MulGT: multi-task graph-transformer with task-aware knowledge injection and domain knowledge-driven pooling for whole slide image analysis","volume":"Vol. 37","author":"Zhao","year":"2023"},{"key":"10.1016\/j.media.2026.104013_bib0048","series-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention","first-page":"66","article-title":"Setmil: spatial encoding transformer-based multiple instance learning for pathological image analysis","author":"Zhao","year":"2022"},{"issue":"11","key":"10.1016\/j.media.2026.104013_bib0049","doi-asserted-by":"crossref","first-page":"3003","DOI":"10.1109\/TMI.2022.3176598","article-title":"A graph-transformer for whole slide image classification","volume":"41","author":"Zheng","year":"2022","journal-title":"IEEE Trans. Med Imaging"},{"issue":"9","key":"10.1016\/j.media.2026.104013_bib0050","doi-asserted-by":"crossref","first-page":"2337","DOI":"10.1007\/s11263-022-01653-1","article-title":"Learning to prompt for vision-language models","volume":"130","author":"Zhou","year":"2022","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.media.2026.104013_bib0051","series-title":"European Conference on Computer Vision","first-page":"333","article-title":"Dgr-mil: exploring diverse global representation in multiple instance learning for whole slide image classification","author":"Zhu","year":"2024"}],"container-title":["Medical Image Analysis"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1361841526000824?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1361841526000824?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,15]],"date-time":"2026-05-15T00:03:58Z","timestamp":1778803438000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1361841526000824"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":51,"alternative-id":["S1361841526000824"],"URL":"https:\/\/doi.org\/10.1016\/j.media.2026.104013","relation":{},"ISSN":["1361-8415"],"issn-type":[{"value":"1361-8415","type":"print"}],"subject":[],"published":{"date-parts":[[2026,6]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"PTCMIL: multiple instance learning via prompt token clustering for whole slide image analysis","name":"articletitle","label":"Article Title"},{"value":"Medical Image Analysis","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.media.2026.104013","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Authors. Published by Elsevier B.V.","name":"copyright","label":"Copyright"}],"article-number":"104013"}}