Cross Modal Reliable Pixel Contrastive Learning for Incomplete Modal Brain Tumor Segmentation

Cross Modal Reliable Pixel Contrastive Learning for Incomplete Modal Brain Tumor Segmentation | 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 Article Cross Modal Reliable Pixel Contrastive Learning for Incomplete Modal Brain Tumor Segmentation JingJing Xu, ZhiWei Yang, Xin Wu, Jian Xiong This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7099555/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 10 You are reading this latest preprint version Abstract In clinical practice, Magnetic Resonance Imaging (MRI) often lacks specific modalities, inevitably leading to a degradation in predictive performance. Different modes are currently treated as independent and non-interfering during training for modal feature extraction, yet there are rich semantic relations between pixels across different modalities. This paper proposes the Cross Modal Reliable Pixel Contrastive Learning (CMR-PCL) algorithm for incomplete modal brain tumor segmentation to compensate for the information deficit among the modalities. Specifically, we propose a label inaccuracies-guided sampling strategy for each modality and then preserve the reliable region to reduce the likelihood of noise sampling. Next, we enforce reliable pixel embeddings belonging to the same semantic class to be more similar than those from different classes. CMR-PCL uses a standard training strategy and requires no specific architectural choices so that it can be easily incorporated into existing incomplete modal brain tumor segmentation. Remarkably, extensive experiments on the BraTS2020, BraTS2018, and BraTS2015 datasets show that CMR-PCL can improve the performance of state-of-the-art algorithms. Biological sciences/Cancer Biological sciences/Computational biology and bioinformatics Physical sciences/Mathematics and computing Health sciences/Medical research Health sciences/Oncology Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Editorial decision: Revision requested 12 May, 2026 Reviews received at journal 08 May, 2026 Reviewers agreed at journal 05 May, 2026 Reviews received at journal 05 Jan, 2026 Reviewers agreed at journal 02 Jan, 2026 Reviewers invited by journal 24 Nov, 2025 Editor assigned by journal 18 Nov, 2025 Editor invited by journal 29 Jul, 2025 Submission checks completed at journal 22 Jul, 2025 First submitted to journal 22 Jul, 2025 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-7099555","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":550685868,"identity":"1336ad8a-254c-4f96-8d9b-1a320d9b31b8","order_by":0,"name":"JingJing Xu","email":"","orcid":"","institution":"Guangzhou Xinhua University","correspondingAuthor":false,"prefix":"","firstName":"JingJing","middleName":"","lastName":"Xu","suffix":""},{"id":550685869,"identity":"2d88831d-3aff-43d3-882f-09cfc35b4961","order_by":1,"name":"ZhiWei Yang","email":"","orcid":"","institution":"Guangdong Science \u0026 Technology Infrastructure Center","correspondingAuthor":false,"prefix":"","firstName":"ZhiWei","middleName":"","lastName":"Yang","suffix":""},{"id":550685872,"identity":"e1ae48ef-3bff-427d-892d-08832ab55a7e","order_by":2,"name":"Xin Wu","email":"","orcid":"","institution":"Guangzhou Xinhua University","correspondingAuthor":false,"prefix":"","firstName":"Xin","middleName":"","lastName":"Wu","suffix":""},{"id":550685873,"identity":"e2b5c06c-efb0-4b5f-b3a1-c28c8a91732a","order_by":3,"name":"Jian Xiong","email":"data:image/png;base64,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","orcid":"","institution":"Guangzhou Xinhua University","correspondingAuthor":true,"prefix":"","firstName":"Jian","middleName":"","lastName":"Xiong","suffix":""}],"badges":[],"createdAt":"2025-07-11 08:38:25","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7099555/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7099555/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":97006052,"identity":"10b6b479-1d8d-4c48-a488-6d930c8d6493","added_by":"auto","created_at":"2025-11-28 14:41:25","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":938911,"visible":true,"origin":"","legend":"","description":"","filename":"v2.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7099555/v1/402e97545c7e9a82896f96d8.pdf"},{"id":97006051,"identity":"6b69c797-8444-4645-b8f9-593a15b9972a","added_by":"auto","created_at":"2025-11-28 14:41:25","extension":"json","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":5735,"visible":true,"origin":"","legend":"","description":"","filename":"ca8c0e2eec504f278dbef4e8e1eef71a.json","url":"https://assets-eu.researchsquare.com/files/rs-7099555/v1/2c31700f5b7de8dff92c2201.json"},{"id":97139717,"identity":"845ea2bb-bc6c-4297-9732-d439fd7094b0","added_by":"auto","created_at":"2025-12-01 10:02:01","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":813470,"visible":true,"origin":"","legend":"","description":"","filename":"v2.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7099555/v1_covered_725e37d6-4b63-487d-8e59-3a4523d9e667.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Cross Modal Reliable Pixel Contrastive Learning for Incomplete Modal Brain Tumor Segmentation","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":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"","lastPublishedDoi":"10.21203/rs.3.rs-7099555/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7099555/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"In clinical practice, Magnetic Resonance Imaging (MRI) often lacks specific modalities, inevitably leading to a degradation in predictive performance. Different modes are currently treated as independent and non-interfering during training for modal feature extraction, yet there are rich semantic relations between pixels across different modalities. This paper proposes the Cross Modal Reliable Pixel Contrastive Learning (CMR-PCL) algorithm for incomplete modal brain tumor segmentation to compensate for the information deficit among the modalities. Specifically, we propose a label inaccuracies-guided sampling strategy for each modality and then preserve the reliable region to reduce the likelihood of noise sampling. Next, we enforce reliable pixel embeddings belonging to the same semantic class to be more similar than those from different classes. CMR-PCL uses a standard training strategy and requires no specific architectural choices so that it can be easily incorporated into existing incomplete modal brain tumor segmentation. Remarkably, extensive experiments on the BraTS2020, BraTS2018, and BraTS2015 datasets show that CMR-PCL can improve the performance of state-of-the-art algorithms.","manuscriptTitle":"Cross Modal Reliable Pixel Contrastive Learning for Incomplete Modal Brain Tumor Segmentation","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-11-28 14:41:21","doi":"10.21203/rs.3.rs-7099555/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2026-05-12T09:39:09+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-05-08T22:05:03+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"15414391876282630508113236425721386209","date":"2026-05-05T15:54:25+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-01-05T17:59:05+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"180188721030753703106382073107089124165","date":"2026-01-02T10:11:26+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-11-24T05:36:38+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-11-18T07:56:57+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2025-07-29T09:32:48+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-07-23T03:44:40+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2025-07-23T03:43:20+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"045aa3cb-6b90-4519-ae03-75974fdad6fb","owner":[],"postedDate":"November 28th, 2025","published":true,"recentEditorialEvents":[{"type":"decision","content":"Revision requested","date":"2026-05-12T09:39:09+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-05-08T22:05:03+00:00","index":136,"fulltext":""},{"type":"reviewerAgreed","content":"15414391876282630508113236425721386209","date":"2026-05-05T15:54:25+00:00","index":135,"fulltext":""}],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[{"id":58594916,"name":"Biological sciences/Cancer"},{"id":58594917,"name":"Biological sciences/Computational biology and bioinformatics"},{"id":58594918,"name":"Physical sciences/Mathematics and computing"},{"id":58594919,"name":"Health sciences/Medical research"},{"id":58594920,"name":"Health sciences/Oncology"}],"tags":[],"updatedAt":"2026-05-22T10:08:34+00:00","versionOfRecord":[],"versionCreatedAt":"2025-11-28 14:41:21","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7099555","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7099555","identity":"rs-7099555","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}