{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,9]],"date-time":"2026-05-09T01:43:15Z","timestamp":1778290995824,"version":"3.51.4"},"reference-count":32,"publisher":"Oxford University Press (OUP)","issue":"3","license":[{"start":{"date-parts":[[2023,3,2]],"date-time":"2023-03-02T00:00:00Z","timestamp":1677715200000},"content-version":"vor","delay-in-days":1,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Major and Seed Inter-Disciplinary Research"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,3,1]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:sec><jats:title>Motivation<\/jats:title><jats:p>Multiple instance learning (MIL) is a powerful technique to classify whole slide images (WSIs) for diagnostic pathology. The key challenge of MIL on WSI classification is to discover the critical instances that trigger the bag label. However, tumor heterogeneity significantly hinders the algorithm\u2019s performance.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>Here, we propose a novel multiplex-detection-based multiple instance learning (MDMIL) which targets tumor heterogeneity by multiplex detection strategy and feature constraints among samples. Specifically, the internal query generated after the probability distribution analysis and the variational query optimized throughout the training process are utilized to detect potential instances in the form of internal and external assistance, respectively. The multiplex detection strategy significantly improves the instance-mining capacity of the deep neural network. Meanwhile, a memory-based contrastive loss is proposed to reach consistency on various phenotypes in the feature space. The novel network and loss function jointly achieve high robustness towards tumor heterogeneity. We conduct experiments on three computational pathology datasets, e.g. CAMELYON16, TCGA-NSCLC, and TCGA-RCC. Benchmarking experiments on the three datasets illustrate that our proposed MDMIL approach achieves superior performance over several existing state-of-the-art methods.<\/jats:p><\/jats:sec><jats:sec><jats:title>Availability and implementation<\/jats:title><jats:p>MDMIL is available for academic purposes at https:\/\/github.com\/ZacharyWang-007\/MDMIL.<\/jats:p><\/jats:sec>","DOI":"10.1093\/bioinformatics\/btad114","type":"journal-article","created":{"date-parts":[[2023,3,1]],"date-time":"2023-03-01T15:15:03Z","timestamp":1677683703000},"source":"Crossref","is-referenced-by-count":20,"title":["Targeting tumor heterogeneity: multiplex-detection-based multiple instance learning for whole slide image classification"],"prefix":"10.1093","volume":"39","author":[{"given":"Zhikang","family":"Wang","sequence":"first","affiliation":[{"name":"Monash Biomedicine Discovery Institute, Department of Biochemistry and Molecular Biology, Monash University , Melbourne, VIC 3800, Australia"}]},{"given":"Yue","family":"Bi","sequence":"additional","affiliation":[{"name":"Monash Biomedicine Discovery Institute, Department of Biochemistry and Molecular Biology, Monash University , Melbourne, VIC 3800, Australia"}]},{"given":"Tong","family":"Pan","sequence":"additional","affiliation":[{"name":"Monash Biomedicine Discovery Institute, Department of Biochemistry and Molecular Biology, Monash University , Melbourne, VIC 3800, Australia"}]},{"given":"Xiaoyu","family":"Wang","sequence":"additional","affiliation":[{"name":"Monash Biomedicine Discovery Institute, Department of Biochemistry and Molecular Biology, Monash University , Melbourne, VIC 3800, Australia"}]},{"given":"Chris","family":"Bain","sequence":"additional","affiliation":[{"name":"Department of Human Centred Computing, Faculty of Information Technology, Monash University , Melbourne, VIC 3800, Australia"}]},{"given":"Richard","family":"Bassed","sequence":"additional","affiliation":[{"name":"Victorian Institute of Forensic Medicine , Melbourne, VIC 3006, Australia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2989-308X","authenticated-orcid":false,"given":"Seiya","family":"Imoto","sequence":"additional","affiliation":[{"name":"Division of Health Medical Intelligence, Human Genome Center, The Institute of Medical Science, The University of Tokyo , Tokyo 108-8639, Japan"}]},{"given":"Jianhua","family":"Yao","sequence":"additional","affiliation":[{"name":"Tencent AI Lab, Tencent , Shenzhen, Guangdong 518000, China"}]},{"given":"Roger J","family":"Daly","sequence":"additional","affiliation":[{"name":"Monash Biomedicine Discovery Institute, Department of Biochemistry and Molecular Biology, Monash University , Melbourne, VIC 3800, Australia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8031-9086","authenticated-orcid":false,"given":"Jiangning","family":"Song","sequence":"additional","affiliation":[{"name":"Monash Biomedicine Discovery Institute, Department of Biochemistry and Molecular Biology, Monash University , Melbourne, VIC 3800, Australia"}]}],"member":"286","published-online":{"date-parts":[[2023,3,2]]},"reference":[{"key":"2023031723181069000_","year":"2016"},{"key":"2023031723181069000_","year":"2014"},{"key":"2023031723181069000_","doi-asserted-by":"crossref","first-page":"233","DOI":"10.1016\/S1470-2045(19)30739-9","article-title":"Automated deep-learning system for Gleason grading of prostate cancer using biopsies: a diagnostic study","volume":"21","author":"Bulten","year":"2020","journal-title":"Lancet Oncol"},{"key":"2023031723181069000_","doi-asserted-by":"crossref","first-page":"1301","DOI":"10.1038\/s41591-019-0508-1","article-title":"Clinical-grade computational pathology using weakly supervised deep learning on whole slide images","volume":"25","author":"Campanella","year":"2019","journal-title":"Nat Med"},{"key":"2023031723181069000_","doi-asserted-by":"crossref","first-page":"152","DOI":"10.1097\/PAP.0b013e318253459e","article-title":"Whole-slide imaging: routine pathologic diagnosis","volume":"19","author":"Cornish","year":"2012","journal-title":"Adv Anat Pathol"},{"key":"2023031723181069000_","first-page":"904103","year":"2014"},{"key":"2023031723181069000_","first-page":"770","year":"2016"},{"key":"2023031723181069000_","first-page":"9729","year":"2020"},{"key":"2023031723181069000_","first-page":"2424","year":"2016"},{"key":"2023031723181069000_","first-page":"7132","year":"2018"},{"key":"2023031723181069000_","first-page":"2127","year":"2018"},{"key":"2023031723181069000_","first-page":"14318","year":"2021"},{"key":"2023031723181069000_","first-page":"532","year":"2019"},{"key":"2023031723181069000_","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":"2023031723181069000_","first-page":"3862","year":"2020"},{"key":"2023031723181069000_","doi-asserted-by":"crossref","first-page":"15","DOI":"10.4103\/2153-3539.153914","article-title":"Automated discrimination of lower and higher grade gliomas based on histopathological image analysis","volume":"6","author":"Mousavi","year":"2015","journal-title":"J Pathol Inform"},{"key":"2023031723181069000_","doi-asserted-by":"crossref","first-page":"36","DOI":"10.4103\/2153-3539.83746","article-title":"Review of the current state of whole slide imaging in pathology","volume":"2","author":"Pantanowitz","year":"2011","journal-title":"J Pathol Inform"},{"key":"2023031723181069000_","doi-asserted-by":"crossref","first-page":"1817","DOI":"10.1109\/TMI.2021.3066295","article-title":"Detection of prostate cancer in whole-slide images through end-to-end training with image-level labels","volume":"40","author":"Pinckaers","year":"2021","journal-title":"IEEE Trans Med Imaging"},{"key":"2023031723181069000_","first-page":"2136","year":"2021"},{"key":"2023031723181069000_","first-page":"682","year":"2021"},{"key":"2023031723181069000_","year":"2017"},{"key":"2023031723181069000_","doi-asserted-by":"crossref","first-page":"4291","DOI":"10.1093\/bioinformatics\/btab380","article-title":"Heal: an automated deep learning framework for cancer histopathology image analysis","volume":"37","author":"Wang","year":"2021","journal-title":"Bioinformatics"},{"key":"2023031723181069000_","first-page":"1","article-title":"Cell graph neural networks enable the precise prediction of patient survival in gastric cancer","volume":"6","author":"Wang","year":"2022","journal-title":"NPJ Precis Oncol"},{"key":"2023031723181069000_","doi-asserted-by":"crossref","first-page":"8179","DOI":"10.1109\/TCSVT.2021.3076097","article-title":"Robust video-based person re-identification by hierarchical mining","volume":"32","author":"Wang","year":"2021","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"2023031723181069000_","first-page":"4754","year":"2022"},{"key":"2023031723181069000_","first-page":"843","year":"2020"},{"key":"2023031723181069000_","first-page":"10524","year":"2020"},{"key":"2023031723181069000_","first-page":"10682","year":"2019"},{"key":"2023031723181069000_","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/ncomms12474","article-title":"Predicting non-small cell lung cancer prognosis by fully automated microscopic pathology image features","volume":"7","author":"Yu","year":"2016","journal-title":"Nature Communication"},{"key":"2023031723181069000_","first-page":"558","year":"2021"},{"key":"2023031723181069000_","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s12859-021-04400-4","article-title":"Deep learning for cancer type classification and driver gene identification","volume":"22","author":"Zeng","year":"2021","journal-title":"BMC Bioinformatics"},{"key":"2023031723181069000_","first-page":"18802","year":"2022"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btad114\/49403983\/btad114.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/39\/3\/btad114\/49555806\/btad114.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/39\/3\/btad114\/49555806\/btad114.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,3,27]],"date-time":"2023-03-27T00:52:21Z","timestamp":1679878341000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/doi\/10.1093\/bioinformatics\/btad114\/7067746"}},"subtitle":[],"editor":[{"given":"Hanchuan","family":"Peng","sequence":"additional","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2023,3,1]]},"references-count":32,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2023,3,1]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btad114","relation":{},"ISSN":["1367-4811"],"issn-type":[{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2023,3,1]]},"published":{"date-parts":[[2023,3,1]]},"article-number":"btad114"}}