{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T01:40:25Z","timestamp":1783042825681,"version":"3.54.6"},"reference-count":40,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"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":["62276052"],"award-info":[{"award-number":["62276052"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005408","name":"University of Electronic Science and Technology of China","doi-asserted-by":"publisher","award":["ZYGX2022YGRH014"],"award-info":[{"award-number":["ZYGX2022YGRH014"]}],"id":[{"id":"10.13039\/501100005408","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Pattern Recognition"],"published-print":{"date-parts":[[2026,11]]},"DOI":"10.1016\/j.patcog.2026.113642","type":"journal-article","created":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T03:43:39Z","timestamp":1774928619000},"page":"113642","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":1,"special_numbering":"PB","title":["Attention-guided knowledge distillation based deep multiple instance learning for gigapixel whole slide image analysis"],"prefix":"10.1016","volume":"179","author":[{"given":"Weiheng","family":"Fu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-5362-6835","authenticated-orcid":false,"given":"Yike","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Meilian","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianfu","family":"Wen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4934-0850","authenticated-orcid":false,"given":"Xiaoshuang","family":"Shi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaofeng","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.patcog.2026.113642_bib0001","doi-asserted-by":"crossref","DOI":"10.1016\/j.compmedimag.2024.102337","article-title":"Multiple instance learning for digital pathology: a review of the state-of-the-art, limitations & future potential","volume":"112","author":"Gadermayr","year":"2024","journal-title":"Comput. Med. Imaging Graph."},{"key":"10.1016\/j.patcog.2026.113642_bib0002","series-title":"IEEE 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.patcog.2026.113642_bib0003","doi-asserted-by":"crossref","DOI":"10.1016\/j.media.2025.103468","article-title":"Dynamic graph based weakly supervised deep hashing for whole slide image classification and retrieval","volume":"101","author":"Jin","year":"2025","journal-title":"Med. Image Anal."},{"key":"10.1016\/j.patcog.2026.113642_bib0004","doi-asserted-by":"crossref","first-page":"1662","DOI":"10.1109\/TIP.2020.3046875","article-title":"Loss-based attention for interpreting image-level prediction of convolutional neural networks","volume":"30","author":"Shi","year":"2020","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.patcog.2026.113642_bib0005","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2024.110341","article-title":"A patch distribution-based active learning method for multiple instance Alzheimer\u2019s disease diagnosis","volume":"150","author":"Wang","year":"2024","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113642_bib0006","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.patcog.2026.113642_bib0007","series-title":"Proceedings of the International Joint Conference on Artificial Intelligence","first-page":"9","article-title":"Diagnose like a pathologist: transformer-enabled hierarchical attention-guided multiple instance learning for whole slide image classification","author":"Xiong","year":"2023"},{"key":"10.1016\/j.patcog.2026.113642_bib0008","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","article-title":"ImageNet large scale visual recognition challenge","volume":"115","author":"Russakovsky","year":"2015","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.patcog.2026.113642_bib0009","series-title":"IEEE 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":"5","key":"10.1016\/j.patcog.2026.113642_bib0010","doi-asserted-by":"crossref","first-page":"1337","DOI":"10.1109\/TMI.2022.3227066","article-title":"MuRCL: multi-instance reinforcement contrastive learning for whole slide image classification","volume":"42","author":"Zhu","year":"2022","journal-title":"IEEE Trans. Med. Imaging"},{"key":"10.1016\/j.patcog.2026.113642_bib0011","series-title":"Machine Learning and Knowledge Discovery in Databases","first-page":"421","article-title":"ProtoMIL: multiple instance learning with prototypical parts for whole-slide image classification","author":"Rymarczyk","year":"2023"},{"key":"10.1016\/j.patcog.2026.113642_bib0012","doi-asserted-by":"crossref","DOI":"10.1016\/j.cmpb.2024.108161","article-title":"ProDiv: prototype-driven consistent pseudo-bag division for whole-slide image classification","volume":"249","author":"Yang","year":"2024","journal-title":"Comput. Methods Programs Biomed."},{"key":"10.1016\/j.patcog.2026.113642_bib0013","series-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention","first-page":"24","article-title":"DGMIL: distribution guided multiple instance learning for whole slide image classification","author":"Qu","year":"2022"},{"key":"10.1016\/j.patcog.2026.113642_bib0014","doi-asserted-by":"crossref","DOI":"10.1016\/j.media.2023.102890","article-title":"Multi-scale representation attention based deep multiple instance learning for gigapixel whole slide image analysis","volume":"89","author":"Xiang","year":"2023","journal-title":"Med. Image Anal."},{"key":"10.1016\/j.patcog.2026.113642_bib0015","series-title":"International Workshop on Computational Mathematics Modeling in Cancer Analysis","first-page":"35","article-title":"MLCN: metric learning constrained network for whole slide image classification with bilinear gated attention mechanism","author":"Shi","year":"2022"},{"key":"10.1016\/j.patcog.2026.113642_bib0016","series-title":"IEEE Conference on Computer Vision and Pattern Recognition","first-page":"19830","article-title":"Interventional bag multi-instance learning on whole-slide pathological images","author":"Lin","year":"2023"},{"key":"10.1016\/j.patcog.2026.113642_bib0017","series-title":"International Workshop on Machine Learning in Medical Imaging","first-page":"392","article-title":"Knowledge distillation based dual-branch network for whole slide image analysis","author":"Fu","year":"2024"},{"key":"10.1016\/j.patcog.2026.113642_bib0018","series-title":"International Conference on Learning Representations","article-title":"An image is worth 16x16 words: transformers for image recognition at scale","author":"Dosovitskiy","year":"2021"},{"key":"10.1016\/j.patcog.2026.113642_bib0019","series-title":"International Conference on Medical Image Computing and Computer Assisted Intervention","first-page":"467","article-title":"Iteratively coupled multiple instance learning from instance to bag classifier for whole slide image classification","author":"Wang","year":"2023"},{"key":"10.1016\/j.patcog.2026.113642_bib0020","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2023.109984","article-title":"Multiple instance learning from similarity-confidence bags","volume":"146","author":"Zhang","year":"2024","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113642_bib0021","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2024.110621","article-title":"A multi-resolution self-supervised learning framework for semantic segmentation in histopathology","volume":"155","author":"Wang","year":"2024","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113642_bib0022","series-title":"International Conference on Learning Representations","first-page":"1","article-title":"CAMIL: context-aware multiple instance learning for cancer detection and subtyping in whole slide images","author":"Fourkioti","year":"2024"},{"key":"10.1016\/j.patcog.2026.113642_bib0023","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.111539","article-title":"Interpretable 2.5 D network by hierarchical attention and consistency learning for 3D MRI classification","volume":"164","author":"Pang","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113642_bib0024","series-title":"Advances in Neural Information Processing Systems","first-page":"2136","article-title":"TransMIL: transformer based correlated multiple instance learning for whole slide image classification","volume":"34","author":"Shao","year":"2021"},{"key":"10.1016\/j.patcog.2026.113642_bib0025","series-title":"European Conference on Artificial Intelligence","first-page":"953","article-title":"Ensemble knowledge distillation for learning improved and efficient networks","author":"Asif","year":"2020"},{"key":"10.1016\/j.patcog.2026.113642_bib0026","series-title":"Proceedings of the European Conference on Computer Vision","first-page":"268","article-title":"Learning deep representations with probabilistic knowledge transfer","author":"Passalis","year":"2018"},{"key":"10.1016\/j.patcog.2026.113642_bib0027","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"4320","article-title":"Deep mutual learning","author":"Zhang","year":"2018"},{"key":"10.1016\/j.patcog.2026.113642_bib0028","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"3430","article-title":"Online knowledge distillation with diverse peers","volume":"34","author":"Chen","year":"2020"},{"key":"10.1016\/j.patcog.2026.113642_bib0029","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"1013","article-title":"Learning lightweight lane detection CNNs by self attention distillation","author":"Hou","year":"2019"},{"key":"10.1016\/j.patcog.2026.113642_bib0030","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"1355","article-title":"Distillation-based training for multi-exit architectures","author":"Phuong","year":"2019"},{"key":"10.1016\/j.patcog.2026.113642_bib0031","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"2859","article-title":"Snapshot distillation: teacher-student optimization in one generation","author":"Yang","year":"2019"},{"issue":"37","key":"10.1016\/j.patcog.2026.113642_bib0032","doi-asserted-by":"crossref","DOI":"10.17485\/ijst\/2016\/v9i37\/102081","article-title":"A new approach for recognition of implant in knee by template matching","volume":"9","author":"Malathy","year":"2016","journal-title":"Indian J. Sci. Technol."},{"key":"10.1016\/j.patcog.2026.113642_bib0033","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"770","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"key":"10.1016\/j.patcog.2026.113642_bib0034","series-title":"NIPS Deep Learning and Representation Learning Workshop","first-page":"1","article-title":"Distilling the knowledge in a neural network","author":"Hinton","year":"2015"},{"issue":"1","key":"10.1016\/j.patcog.2026.113642_bib0035","doi-asserted-by":"crossref","first-page":"68","DOI":"10.5114\/wo.2014.47136","article-title":"Review the cancer genome atlas (TCGA): an immeasurable source of knowledge","volume":"2015","author":"Tomczak","year":"2015","journal-title":"Contemporary Oncology\/Wsp\u00f3\u0142czesna Onkologia"},{"issue":"22","key":"10.1016\/j.patcog.2026.113642_bib0036","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"},{"issue":"6","key":"10.1016\/j.patcog.2026.113642_bib0037","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.patcog.2026.113642_bib0038","unstructured":"D.P. Kingma, Adam: a method for stochastic optimization, arxiv preprint arXiv: 1412.6980 (2014)."},{"key":"10.1016\/j.patcog.2026.113642_bib0039","series-title":"Artificial Intelligence and Machine Learning for Multi-domain Operations Applications","first-page":"369","article-title":"Super-convergence: very fast training of neural networks using large learning rates","volume":"Vol. 11006","author":"Smith","year":"2019"},{"issue":"7","key":"10.1016\/j.patcog.2026.113642_bib0040","doi-asserted-by":"crossref","first-page":"3952","DOI":"10.1109\/TII.2018.2884211","article-title":"Multimodal face-pose estimation with multitask manifold deep learning","volume":"15","author":"Hong","year":"2019","journal-title":"IEEE Trans. Ind. Inf."}],"container-title":["Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326006072?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326006072?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T21:07:59Z","timestamp":1781298479000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0031320326006072"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,11]]},"references-count":40,"alternative-id":["S0031320326006072"],"URL":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113642","relation":{},"ISSN":["0031-3203"],"issn-type":[{"value":"0031-3203","type":"print"}],"subject":[],"published":{"date-parts":[[2026,11]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Attention-guided knowledge distillation based deep multiple instance learning for gigapixel whole slide image analysis","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113642","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":"113642"}}