UniDCF: A Foundation Model for Comprehensive Dentocraniofacial Hard Tissue Reconstruction

UniDCF: A Foundation Model for Comprehensive Dentocraniofacial Hard Tissue Reconstruction | 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 UniDCF: A Foundation Model for Comprehensive Dentocraniofacial Hard Tissue Reconstruction Li Xiao, Chunxia Ren, Ning Zhu, Yue Lai, Gui Chen, Ruijie Wang, and 5 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7163608/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted You are reading this latest preprint version Abstract Dentocraniofacial hard tissue defects profoundly affect patients’ physiological functions, facial aesthetics, and psychological well-being, posing significant challenges for precise reconstruction. Current deep learning models are limited to single-tissue scenarios and modality-specific imaging inputs, resulting in poor generalizability and trade-offs between anatomical fidelity, computational efficiency, and cross-tissue adaptability. Here we introduce UniDCF, a unified framework capable of reconstructing multiple dentocraniofacial hard tissues through multimodal fusion encoding of point clouds and multi-view images. By leveraging the complementary strengths of each modality and incorporating a score-based denoising module to refine surface smoothness, UniDCF overcomes the limitations of prior single-modality approaches. We curated the largest multimodal dataset, comprising intraoral scans, CBCT, and CT from 6,609 patients, resulting in 54,555 annotated instances. Evaluations demonstrate that UniDCF outperforms existing state-of-the-art methods in terms of geometric precision, structural completeness, and spatial accuracy. Clinical simulations indicate UniDCF reduces reconstruction design time by 99% and achieves clinician-rated acceptability exceeding 94%. Overall, UniDCF enables rapid, automated, and high-fidelity reconstruction, supporting personalized and precise restorative treatments, streamlining clinical workflows, and enhancing patient outcomes. Health sciences/Health occupations/Orthopaedics Health sciences/Health care/Medical imaging/Three-dimensional imaging Dentocraniofacial reconstruction Hard tissue defects Deep learning Foundation model Full Text Additional Declarations There is NO Competing Interest. Cite Share Download PDF Status: Under Review 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-7163608","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":489051177,"identity":"718fc34b-0e73-4f51-bf95-3f52aeb14f41","order_by":0,"name":"Li Xiao","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA7UlEQVRIiWNgGAWjYHACAxAhw8AMJD8AMRs7kVp4QFoYZ4C0MBOtBQiYISQB9fyzm7d9+NjGwGNwnPnhY5tf2+T5mBkYP3zMwa1F4s6x4pkzgVokm9mMjXP7bhu2MTMwS87chseaGznGzLzbGHj4mRnMpHN7bjMCtbCBRHACeZCWv0AtbMzs36Qte27bE9RiANLCCLaFx0ya4cftRIJaDG+kFTP2/pMA+oWn2LC34XZyGzNjM16/yN1I3szw44yNnMH54xsf/Phz23Z+e/PBDx/xeR8CJCAUYxuYbCCoHgn8IUXxKBgFo2AUjBQAAEssRh4O5gdnAAAAAElFTkSuQmCC","orcid":"","institution":"Beijing University of Posts and Telecommunications","correspondingAuthor":true,"prefix":"","firstName":"Li","middleName":"","lastName":"Xiao","suffix":""},{"id":489051178,"identity":"8f247b9a-bb04-4902-b931-5d216ac6f85a","order_by":1,"name":"Chunxia Ren","email":"","orcid":"","institution":"Beijing University of Posts and Telecommunications","correspondingAuthor":false,"prefix":"","firstName":"Chunxia","middleName":"","lastName":"Ren","suffix":""},{"id":489051179,"identity":"cc78dd17-41cc-4acd-849a-c0394378acd4","order_by":2,"name":"Ning Zhu","email":"","orcid":"","institution":"Peking University School and Hospital of Stomatology","correspondingAuthor":false,"prefix":"","firstName":"Ning","middleName":"","lastName":"Zhu","suffix":""},{"id":489051180,"identity":"4ae1e57a-ee5a-40be-9c3f-f4db576625a1","order_by":3,"name":"Yue Lai","email":"","orcid":"","institution":"Peking University School and Hospital of Stomatology","correspondingAuthor":false,"prefix":"","firstName":"Yue","middleName":"","lastName":"Lai","suffix":""},{"id":489051181,"identity":"0bc804c8-5c52-4cff-a1a4-2ed0b63166b0","order_by":4,"name":"Gui Chen","email":"","orcid":"","institution":"Peking University School and Hospital of Stomatology","correspondingAuthor":false,"prefix":"","firstName":"Gui","middleName":"","lastName":"Chen","suffix":""},{"id":489051182,"identity":"24be0a57-47b1-46ff-9b69-a3fd42d06954","order_by":5,"name":"Ruijie Wang","email":"","orcid":"","institution":"Peking University School and Hospital of Stomatology","correspondingAuthor":false,"prefix":"","firstName":"Ruijie","middleName":"","lastName":"Wang","suffix":""},{"id":489051183,"identity":"07fa5d1d-e8d0-41e1-8df9-65961e9036a1","order_by":6,"name":"Yangyi Hu","email":"","orcid":"","institution":"Peking University School and Hospital of Stomatology","correspondingAuthor":false,"prefix":"","firstName":"Yangyi","middleName":"","lastName":"Hu","suffix":""},{"id":489051184,"identity":"fc961807-13ce-4af7-b738-42fc37fbdf7b","order_by":7,"name":"Suyao Liu","email":"","orcid":"","institution":"Beijing University of Posts and Telecommunications","correspondingAuthor":false,"prefix":"","firstName":"Suyao","middleName":"","lastName":"Liu","suffix":""},{"id":489051185,"identity":"81e7821d-d14f-44a8-893b-bf7b88820e41","order_by":8,"name":"Shuwen Mao","email":"","orcid":"","institution":"Beijing University of Posts and Telecommunications","correspondingAuthor":false,"prefix":"","firstName":"Shuwen","middleName":"","lastName":"Mao","suffix":""},{"id":489051186,"identity":"04e29803-1f24-44e6-8b0b-7e0cbc99de3a","order_by":9,"name":"Hong Su","email":"","orcid":"","institution":"Peking University School and Hospital of Stomatology","correspondingAuthor":false,"prefix":"","firstName":"Hong","middleName":"","lastName":"Su","suffix":""},{"id":489051187,"identity":"697acbd5-8262-44a6-8395-597b0d425f6c","order_by":10,"name":"Yu Zhang","email":"","orcid":"","institution":"Peking University School and Hospital of Stomatology","correspondingAuthor":false,"prefix":"","firstName":"Yu","middleName":"","lastName":"Zhang","suffix":""}],"badges":[],"createdAt":"2025-07-19 09:55:12","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7163608/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7163608/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":87996843,"identity":"26d9f685-e8e9-4515-924c-b12234e8b127","added_by":"auto","created_at":"2025-07-31 09:37:00","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":32049810,"visible":true,"origin":"","legend":"Article File","description":"","filename":"0715RCX.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7163608/v1_covered_9cbd4074-bc5c-4516-83f1-b98673ee487c.pdf"}],"financialInterests":"There is \u003cb\u003eNO\u003c/b\u003e Competing Interest.","formattedTitle":"UniDCF: A Foundation Model for Comprehensive Dentocraniofacial Hard Tissue Reconstruction","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"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":"nature-portfolio","isNatureJournal":true,"hasQc":false,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"","title":"Nature Portfolio","twitterHandle":"","acdcEnabled":false,"dfaEnabled":false,"editorialSystem":"ejp","reportingPortfolio":"","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Dentocraniofacial reconstruction, Hard tissue defects, Deep learning, Foundation model","lastPublishedDoi":"10.21203/rs.3.rs-7163608/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7163608/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Dentocraniofacial hard tissue defects profoundly affect patients’ physiological functions, facial aesthetics, and psychological well-being, posing significant challenges for precise reconstruction. Current deep learning models are limited to single-tissue scenarios and modality-specific imaging inputs, resulting in poor generalizability and trade-offs between anatomical fidelity, computational efficiency, and cross-tissue adaptability. Here we introduce UniDCF, a unified framework capable of reconstructing multiple dentocraniofacial hard tissues through multimodal fusion encoding of point clouds and multi-view images. By leveraging the complementary strengths of each modality and incorporating a score-based denoising module to refine surface smoothness, UniDCF overcomes the limitations of prior single-modality approaches. We curated the largest multimodal dataset, comprising intraoral scans, CBCT, and CT from 6,609 patients, resulting in 54,555 annotated instances. Evaluations demonstrate that UniDCF outperforms existing state-of-the-art methods in terms of geometric precision, structural completeness, and spatial accuracy. Clinical simulations indicate UniDCF reduces reconstruction design time by 99% and achieves clinician-rated acceptability exceeding 94%. Overall, UniDCF enables rapid, automated, and high-fidelity reconstruction, supporting personalized and precise restorative treatments, streamlining clinical workflows, and enhancing patient outcomes.","manuscriptTitle":"UniDCF: A Foundation Model for Comprehensive Dentocraniofacial Hard Tissue Reconstruction","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-07-31 09:28:06","doi":"10.21203/rs.3.rs-7163608/v1","editorialEvents":[],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"nature-communications","isNatureJournal":true,"hasQc":false,"allowDirectSubmit":false,"externalIdentity":"NCOMMS","sideBox":"Learn more about [Nature Communications](http://www.nature.com/ncomms/)","snPcode":"","submissionUrl":"https://mts-ncomms.nature.com/","title":"Nature Communications","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"ejp","reportingPortfolio":"Nature Communications","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"184710cb-f911-4d84-babe-f318e5bc24bc","owner":[],"postedDate":"July 31st, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[{"id":51917741,"name":"Health sciences/Health occupations/Orthopaedics"},{"id":51917742,"name":"Health sciences/Health care/Medical imaging/Three-dimensional imaging"}],"tags":[],"updatedAt":"2025-07-31T09:28:06+00:00","versionOfRecord":[],"versionCreatedAt":"2025-07-31 09:28:06","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7163608","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7163608","identity":"rs-7163608","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}