The Enhancement of Unsupervised Cross-Modality Domain Adaptive Cardiac Segmentation: Self-Training++ and FC-CRF Optimization

The Enhancement of Unsupervised Cross-Modality Domain Adaptive Cardiac Segmentation: Self-Training++ and FC-CRF Optimization | 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 The Enhancement of Unsupervised Cross-Modality Domain Adaptive Cardiac Segmentation: Self-Training++ and FC-CRF Optimization Yongbo Li, Xiaoyi Qi, Jinjin Wang, Fei Yang This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4212413/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract The training of deep convolutional neural networks requires a substantial amount of labeled data. Nevertheless, the available kinds of labels that are implemented currently to segment medical images cause high-quality image annotations that bring costly and time-consuming procedures. Moreover, distinct modalities such as CT and MRI-based cardiac images make it difficult to train a model. So, one set of image data in one modality cannot be segmented into image data in another modality efficiently. Thus, an unsupervised domain-adaptive cardiac segmentation algorithm implementing a Self-training + + algorithm is suggested to conduct a process called the cross-modality medical-image segmentation known as modality data. The algorithm produces pseudo-labels for images utilized in the target domain and introduces rare class sampling (RCS) by implementing the Self-training + + approach. Additionally, the network called the Mix Transformer semantic segmentation is enhanced by incorporating the module called the atrous spatial pyramid pooling to acquire multiscale semantic information as if it were a teacher and student network to advance the robustness of the segmentation network. Then, fully connected conditional random fields (FC-CRF) are implemented to raise the confidence level of pseudo-labeling. The proposed algorithm substantially decreases the domain bias impact on the outcomes of cardiac image segmentation when distinct modalities exist and alleviates the dependence on expert-labeled data. Then, domain-adaptive training for full cardiac medical-image segmentation is performed in two directions, namely, CT to MRI and MRI to CT cardiac images, and promising experimental outcomes are achieved even though a limited number of data is employed. domain adaptive Self-training++ Transformer fully connected conditional random field tans modal Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Posted Version 1 posted 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-4212413","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":287114912,"identity":"3bd22ebb-a2b3-4abf-a7c0-b9de71bd902b","order_by":0,"name":"Yongbo Li","email":"","orcid":"","institution":"Shandong University","correspondingAuthor":false,"prefix":"","firstName":"Yongbo","middleName":"","lastName":"Li","suffix":""},{"id":287114916,"identity":"a9337c3e-d1fb-44d3-8d64-78a80345e07c","order_by":1,"name":"Xiaoyi Qi","email":"","orcid":"","institution":"Shandong University","correspondingAuthor":false,"prefix":"","firstName":"Xiaoyi","middleName":"","lastName":"Qi","suffix":""},{"id":287114918,"identity":"4fc82187-bf1c-44cf-aee9-b2b632808698","order_by":2,"name":"Jinjin Wang","email":"","orcid":"","institution":"Shandong University","correspondingAuthor":false,"prefix":"","firstName":"Jinjin","middleName":"","lastName":"Wang","suffix":""},{"id":287114919,"identity":"0e9c1732-e01d-4de9-8632-1fda6198b440","order_by":3,"name":"Fei Yang","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA3UlEQVRIiWNgGAWjYBAC9gbGBhAtx8CQAKTYiNDCcwCixZgULRA6sYF4LezNbRI/d9Smz2/PMWD4UHaYgX92AwEtPAfbJHvPHM/dcOaNAeOMc4cZJO4cwK/FXiKxTYK37VjuBokcA2betsMMBhIJBGyRf9gm+bftWLr8DKCWv0RpkWBsk+Ztq0lguAHUwkiUFp7EZmvZtgOGG848KzjYcy6dR+IGIS3sxx/efNtWJy/fnrzxwY8yazn+GQS0AAGLBAPDYTDrAMgMguqBgPkDA0MdMQpHwSgYBaNgpAIA/jtEQKrs7rMAAAAASUVORK5CYII=","orcid":"","institution":"Shandong University","correspondingAuthor":true,"prefix":"","firstName":"Fei","middleName":"","lastName":"Yang","suffix":""}],"badges":[],"createdAt":"2024-04-03 11:35:15","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4212413/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4212413/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":54522482,"identity":"3cb58455-27b3-46ce-95c2-5372c61c44c1","added_by":"auto","created_at":"2024-04-11 18:30:04","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":698380,"visible":true,"origin":"","legend":"","description":"","filename":"KL123560031801DG0401.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4212413/v1_covered_80f22980-8640-4b9e-b853-a59ee2312d64.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"The Enhancement of Unsupervised Cross-Modality Domain Adaptive Cardiac Segmentation: Self-Training++ and FC-CRF Optimization","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":true,"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":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"domain adaptive, Self-training++, Transformer, fully connected conditional random field, tans modal","lastPublishedDoi":"10.21203/rs.3.rs-4212413/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4212413/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eThe training of deep convolutional neural networks requires a substantial amount of labeled data. Nevertheless, the available kinds of labels that are implemented currently to segment medical images cause high-quality image annotations that bring costly and time-consuming procedures. Moreover, distinct modalities such as CT and MRI-based cardiac images make it difficult to train a model. So, one set of image data in one modality cannot be segmented into image data in another modality efficiently. Thus, an unsupervised domain-adaptive cardiac segmentation algorithm implementing a Self-training\u0026thinsp;+\u0026thinsp;+\u0026thinsp;algorithm is suggested to conduct a process called the cross-modality medical-image segmentation known as modality data. The algorithm produces pseudo-labels for images utilized in the target domain and introduces rare class sampling (RCS) by implementing the Self-training\u0026thinsp;+\u0026thinsp;+\u0026thinsp;approach. Additionally, the network called the Mix Transformer semantic segmentation is enhanced by incorporating the module called the atrous spatial pyramid pooling to acquire multiscale semantic information as if it were a teacher and student network to advance the robustness of the segmentation network. Then, fully connected conditional random fields (FC-CRF) are implemented to raise the confidence level of pseudo-labeling. The proposed algorithm substantially decreases the domain bias impact on the outcomes of cardiac image segmentation when distinct modalities exist and alleviates the dependence on expert-labeled data. Then, domain-adaptive training for full cardiac medical-image segmentation is performed in two directions, namely, CT to MRI and MRI to CT cardiac images, and promising experimental outcomes are achieved even though a limited number of data is employed.\u003c/p\u003e","manuscriptTitle":"The Enhancement of Unsupervised Cross-Modality Domain Adaptive Cardiac Segmentation: Self-Training++ and FC-CRF Optimization","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-04-08 17:26:57","doi":"10.21203/rs.3.rs-4212413/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"e1ed4799-6598-4f7f-a52f-16828133df2a","owner":[],"postedDate":"April 8th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2024-04-11T18:29:30+00:00","versionOfRecord":[],"versionCreatedAt":"2024-04-08 17:26:57","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-4212413","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4212413","identity":"rs-4212413","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}