GUDA-Net: An End-to-End Domain Adaptation Network for Multi-Modal MRI 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 Research Article GUDA-Net: An End-to-End Domain Adaptation Network for Multi-Modal MRI Segmentation First Guancheng Hui, Second Wenjie Sun, Third Lanlan Sun, Fourth Qi Yao, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7767527/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 Accurate segmentation of multimodal MRI is essential for brain tumor diagnosis, yet remains hindered by domain shifts across imaging modalities and the scarcity of labeled data. We introduce GUDA-Net, a novel end-to-end framework that performs task-driven unsupervised cross-modality adaptation via segmentation-guided generative learning. Unlike traditional CycleGAN-based pipelines that treat modality translation and segmentation independently, GUDA-Net establishes a bidirectional learning loop, where the segmentation network supervises the synthesis process, enforcing anatomical and semantic consistency in the generated modality. Central to our design is a modality-adaptive generator trained with dual consistency constraints—capturing both low-level visual fidelity and high-level semantic alignment. This strategy enables structure-preserving translation and enhances cross-domain generalization. Evaluated on the BraTS 2018 dataset, GUDA-Net achieves a Dice score of 89.90% in T2-to-T1 segmentation, surpassing existing state-of-the-art methods and underscoring its potential for clinically deployable multimodal MRI analysis under missing modality conditions. Generative Adversarial Network Magnetic Resonance Imaging Medical Image Segmentation Multimodal Image Processing Unsupervised Domain Adaptation. 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-7767527","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":566390835,"identity":"1cf1f887-701e-4548-a3e3-7a0af23d25ab","order_by":0,"name":"First Guancheng Hui","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAArklEQVRIiWNgGAWjYBACAwYGxscINpFamI1J1sImTZoWc/7Fz6oLKu4kNrA3b5NgqLlDWIvljGdmt2eceZbYwHOsTILh2DMiHHbjDNtt3rbDiQ0SOWYSjA2HidNSzPsPqEX+DbFazvewMfM2gGzhIdoWNmNpnmOHjdt40ootEo4RZcvhh595ag7L9rMf3njjQw0RWhgkEiA0G4hIIEIDAwP/AaKUjYJRMApGwUgGAK37OXxOpIIjAAAAAElFTkSuQmCC","orcid":"","institution":"Henan Kaifeng College of Science Technology and Communication","correspondingAuthor":true,"prefix":"","firstName":"First","middleName":"Guancheng","lastName":"Hui","suffix":""},{"id":566390837,"identity":"f8aee603-b6c1-4c6e-b17c-6495856f2b04","order_by":1,"name":"Second Wenjie Sun","email":"","orcid":"","institution":"Henan Kaifeng College of Science Technology and Communication","correspondingAuthor":false,"prefix":"","firstName":"Second","middleName":"Wenjie","lastName":"Sun","suffix":""},{"id":566390838,"identity":"951e518c-e550-4fd2-909b-dd012aefbc97","order_by":2,"name":"Third Lanlan Sun","email":"","orcid":"","institution":"Henan Kaifeng College of Science Technology and Communication","correspondingAuthor":false,"prefix":"","firstName":"Third","middleName":"Lanlan","lastName":"Sun","suffix":""},{"id":566390841,"identity":"8da277c3-82ea-4100-bcd8-c2f3732b4931","order_by":3,"name":"Fourth Qi Yao","email":"","orcid":"","institution":"The Third Affiliated Hospital of Zhengzhou University","correspondingAuthor":false,"prefix":"","firstName":"Fourth","middleName":"Qi","lastName":"Yao","suffix":""},{"id":566390842,"identity":"ea188e8e-a14b-424b-9f23-8d50ad12229e","order_by":4,"name":"Fifth Liangchen Zhao","email":"","orcid":"","institution":"The First Affiliated Hospital of Zhengzhou University","correspondingAuthor":false,"prefix":"","firstName":"Fifth","middleName":"Liangchen","lastName":"Zhao","suffix":""}],"badges":[],"createdAt":"2025-10-02 15:08:16","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7767527/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7767527/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":99316959,"identity":"6fdd582b-1bda-4c00-90a5-85518bc88e4b","added_by":"auto","created_at":"2025-12-31 16:29:29","extension":"json","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":6534,"visible":true,"origin":"","legend":"","description":"","filename":"436a139d5a2241fb8557de1afd6e28e7.json","url":"https://assets-eu.researchsquare.com/files/rs-7767527/v1/bba5b41ca1ead96789a4cd3d.json"},{"id":99135361,"identity":"6bb821dc-6f72-4b52-b20c-2d122a0cce28","added_by":"auto","created_at":"2025-12-29 06:27:05","extension":"xml","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":96684,"visible":true,"origin":"","legend":"","description":"","filename":"436a139d5a2241fb8557de1afd6e28e71enriched.xml","url":"https://assets-eu.researchsquare.com/files/rs-7767527/v1/398c6c615dac2b83cee538c6.xml"},{"id":99315592,"identity":"b3b8f141-c298-4b15-a10a-a22b524b7da6","added_by":"auto","created_at":"2025-12-31 16:27:06","extension":"pdf","order_by":2,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":5208323,"visible":true,"origin":"","legend":"","description":"","filename":"LaTeX.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7767527/v1/dac19946e4a9ef38eba581d4.pdf"},{"id":99135359,"identity":"87340324-736e-4e59-bfd3-5a813cd16d87","added_by":"auto","created_at":"2025-12-29 06:27:05","extension":"pdf","order_by":3,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":84419,"visible":true,"origin":"","legend":"","description":"","filename":"Pointbypointreponse.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7767527/v1/866aa8456e7d6d709dea530c.pdf"},{"id":99315202,"identity":"bdfcac28-fdba-49cc-b577-a90477089a10","added_by":"auto","created_at":"2025-12-31 16:26:36","extension":"png","order_by":4,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":463291,"visible":true,"origin":"","legend":"","description":"","filename":"fig1.png","url":"https://assets-eu.researchsquare.com/files/rs-7767527/v1/f7e7c549eee418a1053fff2a.png"},{"id":99135367,"identity":"7497faca-e48a-44f5-99d6-dd0d189519ec","added_by":"auto","created_at":"2025-12-29 06:27:05","extension":"png","order_by":5,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":507451,"visible":true,"origin":"","legend":"","description":"","filename":"fig2.png","url":"https://assets-eu.researchsquare.com/files/rs-7767527/v1/79777ab003c537ef665b1732.png"},{"id":99315058,"identity":"8b3907eb-9f9c-470b-9227-51523f625d2d","added_by":"auto","created_at":"2025-12-31 16:26:15","extension":"png","order_by":6,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":407388,"visible":true,"origin":"","legend":"","description":"","filename":"fig3.png","url":"https://assets-eu.researchsquare.com/files/rs-7767527/v1/e3e7c66a482846f06126656b.png"},{"id":99315170,"identity":"489ff96a-fe6b-4d26-a89e-89df29c5791d","added_by":"auto","created_at":"2025-12-31 16:26:32","extension":"png","order_by":7,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1681821,"visible":true,"origin":"","legend":"","description":"","filename":"fig4.png","url":"https://assets-eu.researchsquare.com/files/rs-7767527/v1/5a52c4ae6d5905fad5a50daa.png"},{"id":99315525,"identity":"21030cd3-3185-4ff5-b670-cbe06a363d5a","added_by":"auto","created_at":"2025-12-31 16:27:02","extension":"png","order_by":8,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":63236,"visible":true,"origin":"","legend":"","description":"","filename":"fig5.png","url":"https://assets-eu.researchsquare.com/files/rs-7767527/v1/4706d831780639bbb3a66121.png"},{"id":99314691,"identity":"bed84e35-6d86-4cb5-9d41-6ae01d6c9574","added_by":"auto","created_at":"2025-12-31 16:22:22","extension":"png","order_by":9,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1576731,"visible":true,"origin":"","legend":"","description":"","filename":"fig6.png","url":"https://assets-eu.researchsquare.com/files/rs-7767527/v1/6ea6209e09f6a11825369e62.png"},{"id":99135362,"identity":"43c49af0-4d6d-45e2-bd89-efc06eb05458","added_by":"auto","created_at":"2025-12-29 06:27:05","extension":"png","order_by":10,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":136287,"visible":true,"origin":"","legend":"","description":"","filename":"fig7.png","url":"https://assets-eu.researchsquare.com/files/rs-7767527/v1/d5d1eabc08fc710195f075ef.png"},{"id":99315340,"identity":"74754a68-67f4-4eba-be8b-5c921636065e","added_by":"auto","created_at":"2025-12-31 16:26:49","extension":"png","order_by":11,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":377546,"visible":true,"origin":"","legend":"","description":"","filename":"fig8.png","url":"https://assets-eu.researchsquare.com/files/rs-7767527/v1/93f43b2568f7f533a5d9b502.png"},{"id":99135377,"identity":"200ad1e2-0c11-4ca3-8073-ec2b4ab9065a","added_by":"auto","created_at":"2025-12-29 06:27:05","extension":"bst","order_by":12,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":151345,"visible":true,"origin":"","legend":"","description":"","filename":"snapacite.bst","url":"https://assets-eu.researchsquare.com/files/rs-7767527/v1/0c699e7cc358846fb1f95afd.bst"},{"id":99135365,"identity":"6ce848ca-d123-40af-9b54-d07804044d15","added_by":"auto","created_at":"2025-12-29 06:27:05","extension":"bst","order_by":13,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":29828,"visible":true,"origin":"","legend":"","description":"","filename":"snaps.bst","url":"https://assets-eu.researchsquare.com/files/rs-7767527/v1/c6eb77b133d389128fe28c6b.bst"},{"id":99135375,"identity":"bdffdb71-3f7f-4b3e-ac00-12f36a45a84d","added_by":"auto","created_at":"2025-12-29 06:27:05","extension":"pdf","order_by":14,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":5088040,"visible":true,"origin":"","legend":"","description":"","filename":"snarticle.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7767527/v1/95b54dfabf8689ac5406f128.pdf"},{"id":99135370,"identity":"42668980-8b9e-43f3-aaf2-45c590443540","added_by":"auto","created_at":"2025-12-29 06:27:05","extension":"bst","order_by":15,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":35515,"visible":true,"origin":"","legend":"","description":"","filename":"snbasic.bst","url":"https://assets-eu.researchsquare.com/files/rs-7767527/v1/9eca26917ff1c11af90ce218.bst"},{"id":99315672,"identity":"55524ce2-b11a-4c7d-a8e4-c4144325d3c3","added_by":"auto","created_at":"2025-12-31 16:27:14","extension":"bst","order_by":16,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":33968,"visible":true,"origin":"","legend":"","description":"","filename":"snchicago.bst","url":"https://assets-eu.researchsquare.com/files/rs-7767527/v1/bc0494dddd06800512ab6058.bst"},{"id":99314907,"identity":"3ef3d636-fa6c-4a8e-83c7-62046f5adb61","added_by":"auto","created_at":"2025-12-31 16:24:28","extension":"cls","order_by":17,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":55857,"visible":true,"origin":"","legend":"","description":"","filename":"snjnl.cls","url":"https://assets-eu.researchsquare.com/files/rs-7767527/v1/234d79622b8e2738d6083e92.cls"},{"id":99316245,"identity":"d6397f10-2d09-42a5-b804-130d4e49e453","added_by":"auto","created_at":"2025-12-31 16:27:58","extension":"bst","order_by":18,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":64023,"visible":true,"origin":"","legend":"","description":"","filename":"snmathphysay.bst","url":"https://assets-eu.researchsquare.com/files/rs-7767527/v1/0492f1de644133488a0a7ae1.bst"},{"id":99135379,"identity":"70e0f593-fe98-49f3-ac69-9d7a996b62d5","added_by":"auto","created_at":"2025-12-29 06:27:05","extension":"bst","order_by":19,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":64164,"visible":true,"origin":"","legend":"","description":"","filename":"snmathphysnum.bst","url":"https://assets-eu.researchsquare.com/files/rs-7767527/v1/8bb8ec07ee4baa7d44faee9f.bst"},{"id":99314971,"identity":"3d3260b8-934b-446e-9a3b-36f8a0e11f54","added_by":"auto","created_at":"2025-12-31 16:25:16","extension":"bst","order_by":20,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":39056,"visible":true,"origin":"","legend":"","description":"","filename":"snnature.bst","url":"https://assets-eu.researchsquare.com/files/rs-7767527/v1/35619ff2808d39576d827e52.bst"},{"id":99135381,"identity":"ac3c36bf-e0a6-4954-ab82-82ebc965925f","added_by":"auto","created_at":"2025-12-29 06:27:05","extension":"bst","order_by":21,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":39951,"visible":true,"origin":"","legend":"","description":"","filename":"snvancouveray.bst","url":"https://assets-eu.researchsquare.com/files/rs-7767527/v1/ea0ceb6c7fb7cd88c4ea67f5.bst"},{"id":99135383,"identity":"ad759072-415d-4850-9a83-c93712bba617","added_by":"auto","created_at":"2025-12-29 06:27:05","extension":"bst","order_by":22,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":40758,"visible":true,"origin":"","legend":"","description":"","filename":"snvancouvernum.bst","url":"https://assets-eu.researchsquare.com/files/rs-7767527/v1/969048ae3d335433b8ef91d6.bst"},{"id":99135382,"identity":"51bb5146-c4b3-42d5-accb-ad6a520b6d53","added_by":"auto","created_at":"2025-12-29 06:27:05","extension":"xml","order_by":31,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":101885,"visible":true,"origin":"","legend":"","description":"","filename":"436a139d5a2241fb8557de1afd6e28e71structuring.xml","url":"https://assets-eu.researchsquare.com/files/rs-7767527/v1/c5bc6b1321bd801d77494edd.xml"},{"id":99314982,"identity":"fdb1ef92-dc0d-4603-a7a5-b365ea9b93c9","added_by":"auto","created_at":"2025-12-31 16:25:19","extension":"html","order_by":32,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":112702,"visible":true,"origin":"","legend":"","description":"","filename":"earlyproof.html","url":"https://assets-eu.researchsquare.com/files/rs-7767527/v1/d0f5c2e8571e5b63025abde9.html"},{"id":100250396,"identity":"6d18c491-13bb-4967-8f65-f7bc6359c62f","added_by":"auto","created_at":"2026-01-14 14:55:31","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1681053,"visible":true,"origin":"","legend":"","description":"","filename":"LaTeX.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7767527/v1_covered_29bef335-cd91-4e83-a4e4-d3c734186edb.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"GUDA-Net: An End-to-End Domain Adaptation Network for Multi-Modal MRI Segmentation","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":"Generative Adversarial Network, Magnetic Resonance Imaging, Medical Image Segmentation, Multimodal Image Processing, Unsupervised Domain Adaptation.","lastPublishedDoi":"10.21203/rs.3.rs-7767527/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7767527/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eAccurate segmentation of multimodal MRI is essential for brain tumor diagnosis, yet remains hindered by domain shifts across imaging modalities and the scarcity of labeled data. We introduce GUDA-Net, a novel end-to-end framework that performs task-driven unsupervised cross-modality adaptation via segmentation-guided generative learning. Unlike traditional CycleGAN-based pipelines that treat modality translation and segmentation independently, GUDA-Net establishes a bidirectional learning loop, where the segmentation network supervises the synthesis process, enforcing anatomical and semantic consistency in the generated modality. Central to our design is a modality-adaptive generator trained with dual consistency constraints\u0026mdash;capturing both low-level visual fidelity and high-level semantic alignment. This strategy enables structure-preserving translation and enhances cross-domain generalization. Evaluated on the BraTS 2018 dataset, GUDA-Net achieves a Dice score of 89.90% in T2-to-T1 segmentation, surpassing existing state-of-the-art methods and underscoring its potential for clinically deployable multimodal MRI analysis under missing modality conditions.\u003c/p\u003e","manuscriptTitle":"GUDA-Net: An End-to-End Domain Adaptation Network for Multi-Modal MRI Segmentation","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-12-29 06:27:00","doi":"10.21203/rs.3.rs-7767527/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":"44492544-a27c-4465-921e-53c11e6c680a","owner":[],"postedDate":"December 29th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2026-01-14T14:54:59+00:00","versionOfRecord":[],"versionCreatedAt":"2025-12-29 06:27:00","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7767527","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7767527","identity":"rs-7767527","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}
Text is read by the "Ask this paper" AI Q&A widget below.
Extraction quality varies by source — PMC NXML preserves structure
cleanly, OA-HTML may include some navigation residue, and OA-PDF can
have broken hyphenation. The publisher copy
(via DOI)
is the canonical version.