A Multiple Instance Learning framework with Instance Identification and Supervised Contrastive Learning for WSI Classification

A Multiple Instance Learning framework with Instance Identification and Supervised Contrastive Learning for WSI Classification | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Research Article A Multiple Instance Learning framework with Instance Identification and Supervised Contrastive Learning for WSI Classification Liming Yuan, Guangcan Hu, Na Qin, Lu Zhao This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8808357/v1 This work is licensed under a CC BY 4.0 License Status: Under Revision Version 1 posted 10 You are reading this latest preprint version Abstract Multiple Instance Learning (MIL) has been widely used for Whole Slide Image (WSI) classification by dividing a gigapixel WSI into lots of patches, termed bag-of-instances. In order to derive more discriminative instance features, some MIL methods introduce a pseudo-label generation tactic to attach pseudo labels to instances based on attention scores and train an instance-level classifier. However, depending on the attention mechanism completely is not very robust in the correctness of pseudo labels of instances. In addition, the imbalance problem of positive versus negative examples in WSI classification is often neglected but has some influence on the performance. To address the two issues, this paper presents a novel MIL framework with instance identification and supervised contrastive learning for WSI classification. Specifically, we adopt a two-step instance identification strategy, where top-k instances are chosen first according to attention scores and then filtered using the estimated negative-instance distribution, effectively reducing the noise on pseudo labels of instances. Secondly, we introduce supervised contrastive learning at the bag level, which enhances intra-class compactness and inter-class separability to alleviate the bag class imbalance problem. To this end, we use a very efficient random instance masking strategy to generate the augmented view for a bag and maintain two dynamic queues to construct sufficient and diversified bag pairs. Experimental results on three publicly available WSI data sets show that the proposed framework is superior to or highly comparable to state-of-the-art methods. Meanwhile, qualitative visualizations highlight the effectiveness and superiority of our framework in identifying tumor regions. whole slide image classification multiple instance learning instance identification supervised contrastive learning random instance masking Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Revision Version 1 posted Editorial decision: Revision requested 11 May, 2026 Reviews received at journal 10 May, 2026 Reviews received at journal 05 May, 2026 Reviewers agreed at journal 15 Apr, 2026 Reviewers agreed at journal 07 Apr, 2026 Reviewers agreed at journal 30 Mar, 2026 Reviewers invited by journal 30 Mar, 2026 Editor assigned by journal 02 Mar, 2026 Submission checks completed at journal 18 Feb, 2026 First submitted to journal 06 Feb, 2026 You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-8808357","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":614945182,"identity":"a9cc8050-e968-49be-9be5-7604fdbb6e45","order_by":0,"name":"Liming Yuan","email":"","orcid":"","institution":"Tianjin University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Liming","middleName":"","lastName":"Yuan","suffix":""},{"id":614945183,"identity":"75b429c2-2c46-4584-89b9-5cf0263f0f0d","order_by":1,"name":"Guangcan Hu","email":"","orcid":"","institution":"Tianjin University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Guangcan","middleName":"","lastName":"Hu","suffix":""},{"id":614945184,"identity":"eb4edd74-e1c2-444f-9744-417bcfb0ad27","order_by":2,"name":"Na Qin","email":"","orcid":"","institution":"Tianjin University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Na","middleName":"","lastName":"Qin","suffix":""},{"id":614945185,"identity":"27766fdc-8861-436e-b6e2-3f3243856abf","order_by":3,"name":"Lu Zhao","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAu0lEQVRIiWNgGAWjYDACCSB+wGAD4fAQrSWBIU2CZC2HSdAiP7v54YPEtvN1/DMSGB+8bWOQNyekhXHOMWODxLbbEhI3EpgN57YxGO5sIKCFWSLBTAKkxUAigU2at40hweAAAS1sEunfgFrOgbSw/yZKC49EDsiWA2BbmInSIiGRU2yQcC5ZcsaZh82Sc85JGG4gpEV+RvrGBx/K7Pj525MPfnhTZiNP0BYkwNjAAImmUTAKRsEoGAUUAwD/3DjioRt/0gAAAABJRU5ErkJggg==","orcid":"","institution":"Tianjin Chengjian University","correspondingAuthor":true,"prefix":"","firstName":"Lu","middleName":"","lastName":"Zhao","suffix":""}],"badges":[],"createdAt":"2026-02-06 14:47:23","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8808357/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8808357/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":106093628,"identity":"158b8cba-90d2-4612-9a2b-21b1e1363a4c","added_by":"auto","created_at":"2026-04-03 11:38:21","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1438917,"visible":true,"origin":"","legend":"","description":"","filename":"ArticleTitle8.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8808357/v1_covered_f7d3e278-9f5c-46fc-ac13-21cf3ce7739d.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"A Multiple Instance Learning framework with Instance Identification and Supervised Contrastive Learning for WSI Classification","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"multimedia-systems","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"mmsj","sideBox":"Learn more about [Multimedia Systems](http://link.springer.com/journal/530)","snPcode":"530","submissionUrl":"https://submission.nature.com/new-submission/530/3","title":"Multimedia Systems","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"whole slide image classification, multiple instance learning, instance identification, supervised contrastive learning, random instance masking","lastPublishedDoi":"10.21203/rs.3.rs-8808357/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8808357/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Multiple Instance Learning (MIL) has been widely used for Whole Slide Image (WSI) classification by dividing a gigapixel WSI into lots of patches, termed bag-of-instances. In order to derive more discriminative instance features, some MIL methods introduce a pseudo-label generation tactic to attach pseudo labels to instances based on attention scores and train an instance-level classifier. However, depending on the attention mechanism completely is not very robust in the correctness of pseudo labels of instances. In addition, the imbalance problem of positive versus negative examples in WSI classification is often neglected but has some influence on the performance. To address the two issues, this paper presents a novel MIL framework with instance identification and supervised contrastive learning for WSI classification. Specifically, we adopt a two-step instance identification strategy, where top-k instances are chosen first according to attention scores and then filtered using the estimated negative-instance distribution, effectively reducing the noise on pseudo labels of instances. Secondly, we introduce supervised contrastive learning at the bag level, which enhances intra-class compactness and inter-class separability to alleviate the bag class imbalance problem. To this end, we use a very efficient random instance masking strategy to generate the augmented view for a bag and maintain two dynamic queues to construct sufficient and diversified bag pairs. Experimental results on three publicly available WSI data sets show that the proposed framework is superior to or highly comparable to state-of-the-art methods. Meanwhile, qualitative visualizations highlight the effectiveness and superiority of our framework in identifying tumor regions.","manuscriptTitle":"A Multiple Instance Learning framework with Instance Identification and Supervised Contrastive Learning for WSI Classification","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-04-01 12:52:19","doi":"10.21203/rs.3.rs-8808357/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2026-05-11T09:03:23+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-05-10T16:41:26+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-05-06T00:49:19+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"235657807085216930343894496579142094584","date":"2026-04-15T09:37:47+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"334518774246462420560685024805760950270","date":"2026-04-08T03:36:21+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"257350116191696429910652561480890869309","date":"2026-03-31T03:12:23+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-03-30T13:11:28+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-03-03T04:40:00+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-02-18T05:07:51+00:00","index":"","fulltext":""},{"type":"submitted","content":"Multimedia Systems","date":"2026-02-06T14:26:18+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"multimedia-systems","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"mmsj","sideBox":"Learn more about [Multimedia Systems](http://link.springer.com/journal/530)","snPcode":"530","submissionUrl":"https://submission.nature.com/new-submission/530/3","title":"Multimedia Systems","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"b4bec024-fc7b-4529-95fb-c5bf201e30c4","owner":[],"postedDate":"April 1st, 2026","published":true,"recentEditorialEvents":[{"type":"decision","content":"Revision requested","date":"2026-05-11T09:03:23+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-05-10T16:41:26+00:00","index":34,"fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-05-06T00:49:19+00:00","index":33,"fulltext":""}],"rejectedJournal":[],"revision":"","amendment":"","status":"in-revision","subjectAreas":[],"tags":[],"updatedAt":"2026-05-11T09:15:50+00:00","versionOfRecord":[],"versionCreatedAt":"2026-04-01 12:52:19","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8808357","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8808357","identity":"rs-8808357","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}