{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T20:01:15Z","timestamp":1792785675044,"version":"4.5.0"},"reference-count":48,"publisher":"IOP Publishing","issue":"15","license":[{"start":{"date-parts":[[2023,7,19]],"date-time":"2023-07-19T00:00:00Z","timestamp":1689724800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/publishingsupport.iopscience.iop.org\/iop-standard\/v1"},{"start":{"date-parts":[[2023,7,19]],"date-time":"2023-07-19T00:00:00Z","timestamp":1689724800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["12126610"],"award-info":[{"award-number":["12126610"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100019337","name":"Guangdong Province for Science and Technology Innovative Young Talents","doi-asserted-by":"crossref","award":["2018B030312002"],"award-info":[{"award-number":["2018B030312002"]}],"id":[{"id":"10.13039\/501100019337","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100011789","name":"Department of Science and Technology of Jilin Province","doi-asserted-by":"crossref","award":["20190302108GX"],"award-info":[{"award-number":["20190302108GX"]}],"id":[{"id":"10.13039\/501100011789","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Key-Area Research and Development Program of Guangdong Province","award":["2021B0101190003"],"award-info":[{"award-number":["2021B0101190003"]}]},{"DOI":"10.13039\/100017369","name":"Scientific and Technological Planning Project of Guangzhou City","doi-asserted-by":"crossref","award":["202011020002"],"award-info":[{"award-number":["202011020002"]}],"id":[{"id":"10.13039\/100017369","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100004000","name":"Guangzhou Science and Technology Program key projects","doi-asserted-by":"crossref","award":["201804020053"],"award-info":[{"award-number":["201804020053"]}],"id":[{"id":"10.13039\/501100004000","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100015377","name":"Shanghai Key Laboratory of Molecular Imaging","doi-asserted-by":"crossref","award":["18DZ2260400"],"award-info":[{"award-number":["18DZ2260400"]}],"id":[{"id":"10.13039\/501100015377","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100019318","name":"Guangdong Province Key Laboratory of Computational Science","doi-asserted-by":"crossref","award":["2020B1212060032"],"award-info":[{"award-number":["2020B1212060032"]}],"id":[{"id":"10.13039\/501100019318","id-type":"DOI","asserted-by":"crossref"}]},{"name":"the project of Guangzhou innovation leader team","award":["201809010012"],"award-info":[{"award-number":["201809010012"]}]}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Phys. Med. Biol."],"published-print":{"date-parts":[[2023,8,7]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    <jats:italic>Objective.<\/jats:italic>\n                    Whole slide images (WSIs) play a crucial role in histopathological analysis. The extremely high resolution of WSIs makes it laborious to obtain fine-grade annotations. Hence, classifying WSIs with only slide-level labels is often cast as a multiple instance learning (MIL) problem where a WSI is regarded as a bag and tiled into patches that are regarded as instances. The purpose of this study is to develop a novel MIL method for classifying WSIs with only slide-level labels in histopathology analysis.\n                    <jats:italic>Approach.<\/jats:italic>\n                    We propose a novel iterative MIL (IMIL) method for WSI classification where instance representations and bag representations are learned collaboratively. In particular, IMIL iteratively finetune the feature extractor with selected instances and corresponding pseudo labels generated by attention-based MIL pooling. Additionally, three procedures for robust training of IMIL are adopted: (1) the feature extractor is initialized by utilizing self-supervised learning methods on all instances, (2) samples for finetuning the feature extractor are selected according to the attention scores, and (3) a confidence-aware loss is applied for finetuning the feature extractor.\n                    <jats:italic>Main results.<\/jats:italic>\n                    Our proposed IMIL-SimCLR archives the optimal classification performance on Camelyon16 and KingMed-Lung. Compared with the baseline method CLAM, IMIL-SimCLR significantly outperforms it by 3.71% higher average area under curve (AUC) on Camelyon16 and 4.25% higher average AUC on KingMed-Lung. Additionally, our proposed IMIL-ImageNet achieve the optimal classification performance on TCGA-Lung with the average AUC of 96.55% and the accuracy of 96.76%, which significantly outperforms the baseline method CLAM by 1.65% higher average AUC and 2.09% higher average accuracy respectively.\n                    <jats:italic>Significance.<\/jats:italic>\n                    Experimental results on a public lymph node metastasis dataset, a public lung cancer diagnosis dataset and an in-house lung cancer diagnosis datasets show the effectiveness of our proposed IMIL method across different WSI classification tasks compared with other state-of-the-art MIL methods.\n                  <\/jats:p>","DOI":"10.1088\/1361-6560\/acde3f","type":"journal-article","created":{"date-parts":[[2023,6,13]],"date-time":"2023-06-13T18:44:20Z","timestamp":1686681860000},"page":"155007","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":26,"title":["Iterative multiple instance learning for weakly annotated whole slide image classification"],"prefix":"10.1088","volume":"68","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6297-9600","authenticated-orcid":true,"given":"Yuanpin","family":"Zhou","sequence":"first","affiliation":[{"name":"Sun Yat-Sen University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuanlong","family":"Che","sequence":"additional","affiliation":[{"name":"Department of Pathology, KingMed Diagnostics, Guangzhou,"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fang","family":"Lu","sequence":"additional","affiliation":[{"name":"Department of Pathology, KingMed Diagnostics, Guangzhou,"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Si","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Pathology, KingMed Diagnostics, Guangzhou,"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ziye","family":"Yan","sequence":"additional","affiliation":[{"name":"Perception Vision Medical Technologies Co Ltd, Guangzhou,"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun","family":"Wei","sequence":"additional","affiliation":[{"name":"Perception Vision Medical Technologies Co Ltd, Guangzhou,"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yinghua","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Pathology, KingMed Diagnostics, Guangzhou,"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiangdong","family":"Ding","sequence":"additional","affiliation":[{"name":"Department of Pathology, KingMed Diagnostics, Guangzhou,"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yao","family":"Lu","sequence":"additional","affiliation":[{"name":"Sun Yat-Sen University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"266","published-online":{"date-parts":[[2023,7,19]]},"reference":[{"key":"pmbacde3fbib1","doi-asserted-by":"publisher","DOI":"10.7937\/K9\/TCIA.2016.JGNIHEP5","type":"journal-article","article-title":"The cancer genome atlas lung adenocarcinoma collection (TCGA-LUAD)","author":"Albertina","year":"2016","journal-title":"The Cancer Imaging Archive"},{"key":"pmbacde3fbib2","doi-asserted-by":"publisher","first-page":"2089","DOI":"10.1109\/TBME.2013.2245129","type":"journal-article","volume":"60","author":"Basavanhally","year":"2013","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"pmbacde3fbib3","doi-asserted-by":"publisher","first-page":"2199","DOI":"10.1001\/jama.2017.14585","type":"journal-article","volume":"318","author":"Bejnordi","year":"2017","journal-title":"Jama"},{"key":"pmbacde3fbib4","article-title":"Smooth loss functions for deep top-k classification","author":"Berrada","year":"2018","type":"preprint"},{"key":"pmbacde3fbib5","doi-asserted-by":"publisher","first-page":"1301","DOI":"10.1038\/s41591-019-0508-1","type":"journal-article","volume":"25","author":"Campanella","year":"2019","journal-title":"Nat. Med."},{"key":"pmbacde3fbib6","doi-asserted-by":"publisher","first-page":"329","DOI":"10.1016\/j.patcog.2017.10.009","type":"journal-article","volume":"77","author":"Carbonneau","year":"2018","journal-title":"Pattern Recognit."},{"key":"pmbacde3fbib7","first-page":"4308","type":"journal-article","volume":"33","author":"Castells","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"pmbacde3fbib8","first-page":"1597","type":"other","article-title":"A simple framework for contrastive learning of visual representations","author":"Chen","year":"2020"},{"key":"pmbacde3fbib9","doi-asserted-by":"publisher","DOI":"10.1117\/12.2043872","type":"journal-article","article-title":"Automatic detection of invasive ductal carcinoma in whole slide images with convolutional neural networks","volume":"9041","author":"Cruz-Roa","year":"2014","journal-title":"Proc SPIE"},{"key":"pmbacde3fbib10","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/srep46450","type":"journal-article","volume":"7","author":"Cruz-Roa","year":"2017","journal-title":"Sci. Rep."},{"key":"pmbacde3fbib11","doi-asserted-by":"publisher","first-page":"248","DOI":"10.1109\/CVPR.2009.5206848","type":"other","article-title":"Imagenet: a large-scale hierarchical image database","author":"Deng","year":"2009"},{"key":"pmbacde3fbib12","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1016\/S0004-3702(96)00034-3","type":"journal-article","volume":"89","author":"Dietterich","year":"1997","journal-title":"Artif. Intell."},{"key":"pmbacde3fbib13","first-page":"1284","type":"other","article-title":"Automated grading of prostate cancer using architectural and textural image features","author":"Doyle","year":"2007"},{"key":"pmbacde3fbib14","first-page":"4759","type":"other","article-title":"Detecting prostatic adenocarcinoma from digitized histology using a multi-scale hierarchical classification approach","author":"Doyle","year":"2006"},{"key":"pmbacde3fbib15","doi-asserted-by":"publisher","first-page":"1502","DOI":"10.1038\/s41379-018-0073-z","type":"journal-article","volume":"31","author":"Ehteshami Bejnordi","year":"2018","journal-title":"Mod. Pathology"},{"key":"pmbacde3fbib16","first-page":"592","type":"conference-proceedings","article-title":"Learning visual features by colorization for slide-consistent survival prediction from whole slide images","author":"Fan","year":"2021"},{"key":"pmbacde3fbib17","doi-asserted-by":"publisher","first-page":"14009","DOI":"10.1109\/CVPR46437.2021.01379","type":"other","article-title":"Mist: Multiple instance self-training framework for video anomaly detection","author":"Feng","year":"2021"},{"key":"pmbacde3fbib18","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41598-019-50313-x","type":"journal-article","volume":"9","author":"Halicek","year":"2019","journal-title":"Sci. Rep."},{"key":"pmbacde3fbib19","doi-asserted-by":"publisher","first-page":"770","DOI":"10.1109\/CVPR.2016.90","type":"other","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"key":"pmbacde3fbib20","first-page":"2127","type":"other","article-title":"Attention-based deep multiple instance learning","author":"Ilse","year":"2018"},{"key":"pmbacde3fbib21","doi-asserted-by":"publisher","first-page":"697","DOI":"10.1109\/TBME.2003.812194","type":"journal-article","volume":"50","author":"Jafari-Khouzani","year":"2003","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"pmbacde3fbib22","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","type":"conference-proceedings"},{"key":"pmbacde3fbib23","doi-asserted-by":"publisher","DOI":"10.7937\/K9\/TCIA.2016.TYGKKFMQ)","type":"other","article-title":"The cancer genome atlas lung squamous cell carcinoma collection (TCGA-LUSC)","author":"Kirk","year":"2016"},{"key":"pmbacde3fbib24","first-page":"14318","type":"other","article-title":"Dual-stream multiple instance learning network for whole slide image classification with self-supervised contrastive learning","author":"Li","year":"2021"},{"key":"pmbacde3fbib25","doi-asserted-by":"publisher","first-page":"2190","DOI":"10.1109\/ICASSP43922.2022.9746822","type":"other","article-title":"Learning task-specific representation for video anomaly detection with spatial-temporal attention","author":"Liu","year":"2022"},{"key":"pmbacde3fbib26","doi-asserted-by":"publisher","first-page":"555","DOI":"10.1038\/s41551-020-00682-w","type":"journal-article","volume":"5","author":"Lu","year":"2021","journal-title":"Nat. Biomed. Eng."},{"key":"pmbacde3fbib27","doi-asserted-by":"publisher","first-page":"501","DOI":"10.1016\/j.jtho.2016.10.017","type":"journal-article","volume":"12","author":"Luo","year":"2017","journal-title":"J. Thoracic Oncol."},{"key":"pmbacde3fbib28","type":"book","article-title":"A framework for multiple-instance learning","volume":"vol 10","author":"Maron","year":"1997"},{"key":"pmbacde3fbib29","doi-asserted-by":"publisher","first-page":"316","DOI":"10.1109\/TMI.2017.2758580","type":"journal-article","volume":"37","author":"Mercan","year":"2017","journal-title":"IEEE Trans. Med. Imaging"},{"key":"pmbacde3fbib30","doi-asserted-by":"publisher","first-page":"329","DOI":"10.1007\/978-3-030-87237-3_32","type":"conference-proceedings","article-title":"Accounting for dependencies in deep learning based multiple instance learning for whole slide imaging","author":"Myronenko","year":"2021"},{"key":"pmbacde3fbib31","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41746-018-0076-7","type":"journal-article","volume":"2","author":"Nagpal","year":"2019","journal-title":"NPJ Digit. Med."},{"key":"pmbacde3fbib32","article-title":"An introduction to convolutional neural networks","author":"O\u2019Shea","year":"2015","type":"preprint"},{"key":"pmbacde3fbib33","doi-asserted-by":"publisher","first-page":"62","DOI":"10.1109\/TSMC.1979.4310076","type":"journal-article","volume":"9","author":"Otsu","year":"1979","journal-title":"IEEE Trans. Syst., Man, Cybern."},{"key":"pmbacde3fbib34","type":"dataset","article-title":"Automatic Differentiation in PyTorch","author":"Paszke","year":"2017","unstructured":"Paszke A Gross S Chintala S Chanan G Yang E DeVito Z Lin Z Desmaison A Antiga L Lerer A 2017 Automatic Differentiation in PyTorch 2017 Workshop on Autodiff ( https:\/\/openreview.net\/forum?id=BJJsrmfCZ )"},{"key":"pmbacde3fbib35","first-page":"2825","type":"journal-article","volume":"12","author":"Pedregosa","year":"2011","journal-title":"J. Mach. Learn. Res."},{"key":"pmbacde3fbib36","doi-asserted-by":"publisher","first-page":"119","DOI":"10.1016\/j.procs.2016.07.033","type":"journal-article","volume":"90","author":"Qaiser","year":"2016","journal-title":"Proc. Comput. Sci."},{"key":"pmbacde3fbib37","first-page":"196","type":"conference-proceedings","article-title":"Adaptive discriminant wavelet packet transform and local binary patterns for meningioma subtype classification","author":"Qureshi","year":"2008"},{"key":"pmbacde3fbib38","doi-asserted-by":"publisher","first-page":"829","DOI":"10.1007\/978-3-540-30136-3_101","type":"conference-proceedings","article-title":"Svm optimization for hyperspectral colon tissue cell classification","author":"Rajpoot","year":"2004"},{"key":"pmbacde3fbib39","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41598-019-49710-z","type":"journal-article","volume":"9","author":"Shaban","year":"2019","journal-title":"Sci. Rep."},{"key":"pmbacde3fbib40","doi-asserted-by":"publisher","DOI":"10.1016\/j.physd.2019.132306","type":"journal-article","volume":"404","author":"Sherstinsky","year":"2020","journal-title":"Physica D"},{"key":"pmbacde3fbib41","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2020.101813","type":"journal-article","volume":"67","author":"Srinidhi","year":"2021","journal-title":"Med. Image Anal."},{"key":"pmbacde3fbib42","doi-asserted-by":"publisher","first-page":"3950","DOI":"10.1109\/TCYB.2019.2935141","type":"journal-article","volume":"50","author":"Wang","year":"2019","journal-title":"IEEE Trans. Cybern."},{"key":"pmbacde3fbib43","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1016\/j.patcog.2017.08.026","type":"journal-article","volume":"74","author":"Wang","year":"2018","journal-title":"Pattern Recognit."},{"key":"pmbacde3fbib44","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41598-018-37186-2","type":"journal-article","volume":"9","author":"Wei","year":"2019","journal-title":"Sci. Rep."},{"key":"pmbacde3fbib45","doi-asserted-by":"publisher","first-page":"3460","DOI":"10.1109\/CVPR.2015.7298968","type":"other","article-title":"Deep multiple instance learning for image classification and auto-annotation","author":"Wu","year":"2015"},{"key":"pmbacde3fbib46","doi-asserted-by":"publisher","first-page":"47","DOI":"10.1007\/978-3-030-87196-3_5","type":"conference-proceedings","article-title":"Self-supervised visual representation learning for histopathological images","author":"Yang","year":"2021"},{"key":"pmbacde3fbib47","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/ncomms12474","type":"journal-article","volume":"7","author":"Yu","year":"2016","journal-title":"Nat. Commun."},{"key":"pmbacde3fbib48","doi-asserted-by":"publisher","first-page":"1366","DOI":"10.1109\/ICASSP43922.2022.9747121","type":"other","article-title":"Multiple instance learning with task-specific multi-level features for weakly annotated histopathological image classification","author":"Zhou","year":"2022"}],"container-title":["Physics in Medicine &amp; Biology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/acde3f","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/acde3f\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/acde3f","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/acde3f\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/acde3f\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/acde3f\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/acde3f\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/acde3f\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T17:06:46Z","timestamp":1778778406000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/acde3f"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,19]]},"references-count":48,"journal-issue":{"issue":"15","published-online":{"date-parts":[[2023,7,19]]},"published-print":{"date-parts":[[2023,8,7]]}},"URL":"https:\/\/doi.org\/10.1088\/1361-6560\/acde3f","relation":{},"ISSN":["0031-9155","1361-6560"],"issn-type":[{"value":"0031-9155","type":"print"},{"value":"1361-6560","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,7,19]]},"assertion":[{"value":"Iterative multiple instance learning for weakly annotated whole slide image classification","name":"article_title","label":"Article Title"},{"value":"Physics in Medicine & Biology","name":"journal_title","label":"Journal Title"},{"value":"paper","name":"article_type","label":"Article Type"},{"value":"\u00a9 2023 Institute of Physics and Engineering in Medicine. All rights, including for text and data mining, AI training, and similar technologies, are reserved.","name":"copyright_information","label":"Copyright Information"},{"value":"2022-12-26","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2023-06-13","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2023-07-19","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}