{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T11:45:36Z","timestamp":1781264736999,"version":"3.54.1"},"reference-count":53,"publisher":"Springer Science and Business Media LLC","issue":"9","license":[{"start":{"date-parts":[[2025,3,15]],"date-time":"2025-03-15T00:00:00Z","timestamp":1741996800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,3,15]],"date-time":"2025-03-15T00:00:00Z","timestamp":1741996800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62276074"],"award-info":[{"award-number":["62276074"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Med Biol Eng Comput"],"published-print":{"date-parts":[[2025,9]]},"DOI":"10.1007\/s11517-025-03341-x","type":"journal-article","created":{"date-parts":[[2025,3,15]],"date-time":"2025-03-15T00:26:52Z","timestamp":1741998412000},"page":"2617-2635","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Reimagining cancer tissue classification: a multi-scale framework based on multi-instance learning for whole slide image classification"],"prefix":"10.1007","volume":"63","author":[{"given":"Zixuan","family":"Wu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haiyong","family":"He","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiushun","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhenghui","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanyan","family":"Ye","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jing","family":"Guo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wanming","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaobing","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,3,15]]},"reference":[{"key":"3341_CR1","doi-asserted-by":"crossref","unstructured":"Li H, Yang F, Zhao Y, Xing X, Zhang J, Gao M, Huang J, Wang L, Yao J (2021) DT-MIL: deformable transformer for multi-instance learning on histopathological image. In: Medical image computing and computer assisted intervention\u2013MICCAI 2021: 24th international conference, Strasbourg, France, September 27\u2013October 1, 2021, Proceedings, Part VIII 24, Springer, pp 206\u2013216","DOI":"10.1007\/978-3-030-87237-3_20"},{"key":"3341_CR2","doi-asserted-by":"publisher","first-page":"106","DOI":"10.1038\/s41586-021-03512-4","volume":"594","author":"MY Lu","year":"2021","unstructured":"Lu MY, Chen TY, Williamson DF, Zhao M, Shady M, Lipkova J, Mahmood F (2021) Ai-based pathology predicts origins for cancers of unknown primary. Nature 594:106\u2013110","journal-title":"Nature"},{"key":"3341_CR3","doi-asserted-by":"publisher","first-page":"1581","DOI":"10.1109\/TPAMI.2020.3019563","volume":"44","author":"H Pinckaers","year":"2020","unstructured":"Pinckaers H, Van Ginneken B, Litjens G (2020) Streaming convolutional neural networks for end-to-end learning with multi-megapixel images. IEEE Trans Pattern Anal Mach Intell 44:1581\u20131590","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"3341_CR4","doi-asserted-by":"crossref","unstructured":"Zhao Y, Lin Z, Sun K, Zhang Y, Huang J, Wang L, Yao J (2022) Setmil: spatial encoding transformer-based multiple instance learning for pathological image analysis. In: International conference on medical image computing and computer-assisted intervention, Springer, pp 66\u201376","DOI":"10.1007\/978-3-031-16434-7_7"},{"key":"3341_CR5","doi-asserted-by":"publisher","first-page":"930","DOI":"10.1038\/s44222-023-00096-8","volume":"1","author":"AH Song","year":"2023","unstructured":"Song AH, Jaume G, Williamson DF, Lu MY, Vaidya A, Miller TR, Mahmood F (2023) Artificial intelligence for digital and computational pathology. Nat Rev Bioeng 1:930\u2013949","journal-title":"Nat Rev Bioeng"},{"key":"3341_CR6","doi-asserted-by":"publisher","first-page":"100316","DOI":"10.1016\/j.modpat.2023.100316","volume":"36","author":"Q Guo","year":"2023","unstructured":"Guo Q, Qu L, Zhu J, Li H, Wu Y, Wang S, Yu M, Wu J, Wen H, Ju X et al (2023) Predicting lymph node metastasis from primary cervical squamous cell carcinoma based on deep learning in histopathologic images. Modern Pathol 36:100316","journal-title":"Modern Pathol"},{"key":"3341_CR7","doi-asserted-by":"crossref","unstructured":"Berb\u00eds MA, McClintock DS, Bychkov A, Van\u00a0der Laak J, Pantanowitz L, Lennerz JK, Cheng JY, Delahunt B, Egevad L, Eloy C, et\u00a0al (2023) Computational pathology in 2030: a delphi study forecasting the role of ai in pathology within the next decade, EBioMedicine 88","DOI":"10.1016\/j.ebiom.2022.104427"},{"key":"3341_CR8","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1016\/S0004-3702(96)00034-3","volume":"89","author":"TG Dietterich","year":"1997","unstructured":"Dietterich TG, Lathrop RH, Lozano-P\u00e9rez T (1997) Solving the multiple instance problem with axis-parallel rectangles. Artif Intell 89:31\u201371","journal-title":"Artif Intell"},{"key":"3341_CR9","unstructured":"Maron O, Lozano-P\u00e9rez T (1997) A framework for multiple-instance learning. Adv Neural Inf Process Syst 10"},{"key":"3341_CR10","doi-asserted-by":"publisher","first-page":"101813","DOI":"10.1016\/j.media.2020.101813","volume":"67","author":"CL Srinidhi","year":"2021","unstructured":"Srinidhi CL, Ciga O, Martel AL (2021) Deep neural network models for computational histopathology: a survey. Med Image Anal 67:101813","journal-title":"Med Image Anal"},{"key":"3341_CR11","doi-asserted-by":"publisher","first-page":"107034","DOI":"10.1016\/j.compbiomed.2023.107034","volume":"161","author":"W Hu","year":"2023","unstructured":"Hu W, Li X, Li C, Li R, Jiang T, Sun H, Huang X, Grzegorzek M, Li X (2023) A state-of-the-art survey of artificial neural networks for whole-slide image analysis: from popular convolutional neural networks to potential visual transformers. Comput Biol Med 161:107034","journal-title":"Comput Biol Med"},{"key":"3341_CR12","doi-asserted-by":"crossref","unstructured":"Qu L, Liu S, Liu X, Wang M, Song Z (2022) Towards label-efficient automatic diagnosis and analysis: a comprehensive survey of advanced deep learning-based weakly-supervised, semi-supervised and self-supervised techniques in histopathological image analysis. Phys Med Biol 67. 20TR01","DOI":"10.1088\/1361-6560\/ac910a"},{"key":"3341_CR13","doi-asserted-by":"publisher","first-page":"101813","DOI":"10.1016\/j.media.2020.101813","volume":"67","author":"CL Srinidhi","year":"2021","unstructured":"Srinidhi CL, Ciga O, Martel AL (2021) Deep neural network models for computational histopathology: a survey. Med Image Anal 67:101813","journal-title":"Med Image Anal"},{"key":"3341_CR14","doi-asserted-by":"crossref","unstructured":"Li X, Yang B, Chen T, Gao Z, Li H (2023) Multiple instance learning-based two-stage metric learning network for whole slide image classification. Vis Comput 1\u201316","DOI":"10.1007\/s00371-023-03131-2"},{"key":"3341_CR15","doi-asserted-by":"crossref","unstructured":"Chen RJ, Chen C, Li Y, Chen TY, Trister AD, Krishnan RG, Mahmood F (2022) Scaling vision transformers to gigapixel images via hierarchical self-supervised learning. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 16144\u201316155","DOI":"10.1109\/CVPR52688.2022.01567"},{"key":"3341_CR16","unstructured":"Ilse M, Tomczak J, Welling M (2018) Attention-based deep multiple instance learning. In: International conference on machine learning, PMLR, pp 2127\u20132136"},{"key":"3341_CR17","doi-asserted-by":"crossref","unstructured":"Li B, Li Y, Eliceiri KW (2021) Dual-stream multiple instance learning network for whole slide image classification with self-supervised contrastive learning. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 14318\u201314328","DOI":"10.1109\/CVPR46437.2021.01409"},{"key":"3341_CR18","first-page":"2136","volume":"34","author":"Z Shao","year":"2021","unstructured":"Shao Z, Bian H, Chen Y, Wang Y, Zhang J, Ji X et al (2021) Transmil: transformer based correlated multiple instance learning for whole slide image classification. Adv Neural Inf Process Syst 34:2136\u20132147","journal-title":"Adv Neural Inf Process Syst"},{"key":"3341_CR19","unstructured":"Zhang R, Zhang Q, Liu Y, Xin H, Liu Y, Wang X (2023) Multi-level multiple instance learning with transformer for whole slide image classification. arXiv:2306.05029"},{"key":"3341_CR20","doi-asserted-by":"crossref","unstructured":"Xiong C, Chen H, Sung JJ, King I (2023) Diagnose like a pathologist: transformer-enabled hierarchical attention-guided multiple instance learning for whole slide image classification. arXiv:2301.08125","DOI":"10.24963\/ijcai.2023\/176"},{"key":"3341_CR21","doi-asserted-by":"crossref","unstructured":"Bontempo G, Porrello A, Bolelli F, Calderara S, Ficarra E (2023) Das-mil: distilling across scales for mil classification of histological wsis, in: International conference on medical image computing and computer-assisted intervention, Springer, pp 248\u2013258","DOI":"10.1007\/978-3-031-43907-0_24"},{"key":"3341_CR22","doi-asserted-by":"crossref","unstructured":"Stegm\u00fcller T, Bozorgtabar B, Spahr A, Thiran J-P (2023) Scorenet: learning non-uniform attention and augmentation for transformer-based histopathological image classification. In: Proceedings of the IEEE\/CVF winter Conference on applications of computer vision, pp 6170\u20136179","DOI":"10.1109\/WACV56688.2023.00611"},{"key":"3341_CR23","doi-asserted-by":"publisher","first-page":"555","DOI":"10.1038\/s41551-020-00682-w","volume":"5","author":"MY Lu","year":"2021","unstructured":"Lu MY, Williamson DF, Chen TY, Chen RJ, Barbieri M, Mahmood F (2021) Data-efficient and weakly supervised computational pathology on whole-slide images. Nat Biomed Eng 5:555\u2013570","journal-title":"Nat Biomed Eng"},{"key":"3341_CR24","doi-asserted-by":"crossref","unstructured":"Xu G, Song Z, Sun Z, Ku C, Yang Z, Liu C, Wang S, Ma J, Xu W (2019) Camel: a weakly supervised learning framework for histopathology image segmentation. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 10682\u201310691","DOI":"10.1109\/ICCV.2019.01078"},{"key":"3341_CR25","doi-asserted-by":"crossref","unstructured":"Zhang H, Meng Y, Zhao Y, Qiao Y, Yang X, Coupland SE, 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"},{"key":"3341_CR26","doi-asserted-by":"crossref","unstructured":"Tang W, Huang S, Zhang X, Zhou F, Zhang Y, Liu B (2023) Multiple instance learning framework with masked hard instance mining for whole slide image classification. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 4078\u20134087","DOI":"10.1109\/ICCV51070.2023.00377"},{"key":"3341_CR27","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1109\/5254.708428","volume":"13","author":"MA Hearst","year":"1998","unstructured":"Hearst MA, Dumais ST, Osuna E, Platt J, Scholkopf B (1998) Support vector machines. IEEE Intell Syst Their Appl 13:18\u201328","journal-title":"IEEE Intell Syst Their Appl"},{"key":"3341_CR28","doi-asserted-by":"publisher","first-page":"102105","DOI":"10.1016\/j.media.2021.102105","volume":"72","author":"P Chikontwe","year":"2021","unstructured":"Chikontwe P, Luna M, Kang M, Hong KS, Ahn JH, Park SH (2021) Dual attention multiple instance learning with unsupervised complementary loss for covid-19 screening. Med Image Anal 72:102105","journal-title":"Med Image Anal"},{"key":"3341_CR29","unstructured":"Sharma Y, Shrivastava A, Ehsan L, Moskaluk CA, Syed S, Brown D (2021) Cluster-to-conquer: A framework for end-to-end multi-instance learning for whole slide image classification. In: Medical imaging with deep learning, PMLR, pp 682\u2013698"},{"key":"3341_CR30","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1016\/j.patcog.2017.08.026","volume":"74","author":"X Wang","year":"2018","unstructured":"Wang X, Yan Y, Tang P, Bai X, Liu W (2018) Revisiting multiple instance neural networks. Pattern Recognit 74:15\u201324","journal-title":"Pattern Recognit"},{"key":"3341_CR31","doi-asserted-by":"crossref","unstructured":"Wu Y, Schmidt A, Hern\u00e1ndez-S\u00e1nchez E, Molina R, Katsaggelos AK (2021) Combining attention-based multiple instance learning and gaussian processes for ct hemorrhage detection. In: International conference on medical image computing and computer-assisted intervention, Springer, pp 582\u2013591","DOI":"10.1007\/978-3-030-87196-3_54"},{"key":"3341_CR32","doi-asserted-by":"crossref","unstructured":"Liu W, Anguelov D, Erhan D, Szegedy, Reed S, Fu C-Y, Berg AC (2016) Ssd: single shot multibox detector, in: Computer Vision\u2013ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11\u201314, 2016, Proceedings, Part I 14, Springer, pp 21\u201337","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"3341_CR33","doi-asserted-by":"crossref","unstructured":"Zhang D, Tang J, Cheng K-T (2022) Graph reasoning transformer for image parsing. In: Proceedings of the 30th ACM international conference on multimedia, pp 2380\u20132389","DOI":"10.1145\/3503161.3547858"},{"key":"3341_CR34","doi-asserted-by":"crossref","unstructured":"Lin T-Y, Doll\u00e1r P, Girshick R, He K, Hariharan B, Belongie S (2017) Feature pyramid networks for object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2117\u20132125","DOI":"10.1109\/CVPR.2017.106"},{"key":"3341_CR35","doi-asserted-by":"crossref","unstructured":"Liu S, Qi L, Qin H, Shi J, Jia J (2018) Path aggregation network for instance segmentation, in: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 8759\u20138768","DOI":"10.1109\/CVPR.2018.00913"},{"key":"3341_CR36","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"},{"key":"3341_CR37","unstructured":"Li X, Wang W, Wu L, Chen S, Hu X, Li J, Tang J, Yang J (2020) Generalized focal loss: learning qualified and distributed\u00a0bounding boxes for dense object detection. Adv Neural Inf Process Syst 33:21002\u201321012"},{"key":"3341_CR38","unstructured":"Hermans A, Beyer L, Leibe B (2017) In defense of the triplet loss for person re-identification. arXiv:1703.07737"},{"key":"3341_CR39","doi-asserted-by":"crossref","unstructured":"Schroff F, Kalenichenko D, Philbin J (2015) Facenet: a unified embedding for face recognition and clustering. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 815\u2013823","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"3341_CR40","doi-asserted-by":"publisher","first-page":"1301","DOI":"10.1038\/s41591-019-0508-1","volume":"25","author":"G Campanella","year":"2019","unstructured":"Campanella G, Hanna MG, Geneslaw L, Miraflor A, Werneck Krauss Silva V, Busam KJ, Brogi E, Reuter VE, Klimstra DS, Fuchs TJ (2019) Clinical-grade computational pathology using weakly supervised deep learning on whole slide images. Nat Med 25:1301\u20131309","journal-title":"Nat Med"},{"key":"3341_CR41","doi-asserted-by":"crossref","unstructured":"Feng J, Zhou Z-H (2017) Deep miml network. In: Proceedings of the AAAI conference on artificial intelligence, vol 31","DOI":"10.1609\/aaai.v31i1.10890"},{"key":"3341_CR42","doi-asserted-by":"crossref","unstructured":"Hou L, Samaras D, Kurc TM, Gao Y, Davis JE, Saltz JH (2016) Patch-based convolutional neural network for whole slide tissue image classification. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2424\u20132433","DOI":"10.1109\/CVPR.2016.266"},{"key":"3341_CR43","doi-asserted-by":"crossref","unstructured":"Liu Z, Mao H, Wu C-Y, Feichtenhofer C, Darrell T, Xie S (2022) A convnet for the 2020s. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 11976\u201311986","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"3341_CR44","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser \u0141, Polosukhin I (2017) Attention is all you need. Adv Neural Inf Process Syst 30"},{"key":"3341_CR45","unstructured":"Zhu X, Su W, Lu L, Li B, Wang X, Dai J (2020) Deformable detr: Deformable transformers for end-to-end object detection. arXiv:2010.04159"},{"key":"3341_CR46","unstructured":"Chen J, Lu Y, Yu Q, Luo X, Adeli E, Wang Y, Lu L, Yuille AL, Zhou Y (2021) Transunet: transformers make strong encoders for medical image segmentation. arXiv:2102.04306"},{"key":"3341_CR47","unstructured":"Dosovitskiy A, Beyer L, Kolesnikov A, Weissenborn D, Zhai X, Unterthiner T, Dehghani M, Minderer M, Heigold G, Gelly S, et\u00a0al (2020) An image is worth 16x16 words: transformers for image recognition at scale. arXiv:2010.11929"},{"key":"3341_CR48","doi-asserted-by":"crossref","unstructured":"Xiong Y, Zeng Z, Chakraborty R, Tan M, Fung G, Li Y, Singh V (2021) Nystr\u00f6mformer: a nystr\u00f6m-based algorithm for approximating self-attention. In: Proceedings of the AAAI conference on artificial intelligence, vol 35, pp 14138\u201314148","DOI":"10.1609\/aaai.v35i16.17664"},{"key":"3341_CR49","doi-asserted-by":"crossref","unstructured":"Sandler M, Howard A, Zhu M, Zhmoginov A, Chen L-C (2018) Mobilenetv2: inverted residuals and linear bottlenecks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4510\u20134520","DOI":"10.1109\/CVPR.2018.00474"},{"key":"3341_CR50","unstructured":"Loshchilov I, Hutter F (2017) Decoupled weight decay regularization. arXiv:1711.05101"},{"key":"3341_CR51","unstructured":"Keshvarikhojasteh H (2024) Quantitative evaluation of mils\u2019 reliability for wsis classification. arXiv:2409.11110"},{"key":"3341_CR52","doi-asserted-by":"crossref","unstructured":"Zhang Y, Li H, Sun Y, Zheng S, Zhu C, Yang L (2025) Attention-challenging multiple instance learning for whole slide image classification. In: European conference on computer vision, Springer, pp 125\u2013143","DOI":"10.1007\/978-3-031-73668-1_8"},{"key":"3341_CR53","doi-asserted-by":"crossref","unstructured":"Rymarczyk D, Borowa A, Tabor J, Zielinski B (2021) Kernel self-attention for weakly-supervised image classification using deep multiple instance learning. In: Proceedings of the IEEE\/CVF winter conference on applications of computer vision, pp 1721\u20131730","DOI":"10.1109\/WACV48630.2021.00176"}],"container-title":["Medical & Biological Engineering & Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11517-025-03341-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11517-025-03341-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11517-025-03341-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,6]],"date-time":"2025-09-06T07:46:33Z","timestamp":1757144793000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11517-025-03341-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,15]]},"references-count":53,"journal-issue":{"issue":"9","published-print":{"date-parts":[[2025,9]]}},"alternative-id":["3341"],"URL":"https:\/\/doi.org\/10.1007\/s11517-025-03341-x","relation":{},"ISSN":["0140-0118","1741-0444"],"issn-type":[{"value":"0140-0118","type":"print"},{"value":"1741-0444","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,3,15]]},"assertion":[{"value":"10 May 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 February 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 March 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}