GeoShoot-GAN: Unsupervised Diffeomorphic Image Registration Using Geodesic Shooting and Generative Adversarial Networks

GeoShoot-GAN: Unsupervised Diffeomorphic Image Registration Using Geodesic Shooting and Generative Adversarial Networks | 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 GeoShoot-GAN: Unsupervised Diffeomorphic Image Registration Using Geodesic Shooting and Generative Adversarial Networks Ubaldo Ramon-Julvez, Monica Hernandez, Elvira Mayordomo This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7758784/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 5 You are reading this latest preprint version Abstract Deformable image registration is a fundamental step in medical image analysis. Diffeomorphic registration provides topology-preserving transformations which is an essential property for many clinical studies. Despite the theoretical strengths of geodesic shooting models, their high computational complexity and the absence of fully unsupervisedmethods have limited their widespread adoption. We propose GeoShoot-GAN, the first fully unsupervised, end-to-end framework for diffeomorphic registration via geodesic shooting. Our approach is based on adversarial learning, that allows the inference of complex deformable models without requiring the guidance ofground-truth deformations. We further extend the method to the stationary velocity field parameterization, providing a flexible framework that unifies geodesic andstationary variants. To stabilize adversarial training, we introduce tailored loss designs and careful optimization strategies that balance the relativedifficulty between generator and discriminator tasks. This design ensures that the generator produces smooth velocity fields while the discriminatorenforces plausibility on the image disimilarity after registration, driving the system toward realistic topology-preserving deformations. Experiments on two independent brain MRI datasets (NIREP and OASIS) demonstrate that GeoShoot-GAN achieves accurate diffeomorphic transformationsthrough efficient inference.The method performs competitively with state-of-the-art optimization- and learning- based methods, while preserving geodesic guarantees.Moreover, GeoShoot-GAN exhibits strong generalization across datasets, underscoring both its robustness and practical applicability. These results demonstrate the potential of adversarial learning as a powerful driver for unsupervised diffeomorphic registration, opening newopportunities for large-scale studies in Computational Anatomy and time-sensitive clinical applications, in contrast with diffusion modelsthat, while promissing, are still far from being computationally viable for this kind of studies. Biological sciences/Computational biology and bioinformatics Physical sciences/Engineering Physical sciences/Mathematics and computing diffeomorphic registration geodesic shooting unsupervised end-to-end generative adversarial networks computational anatomy Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Reviewers invited by journal 04 Feb, 2026 Editor invited by journal 07 Oct, 2025 Editor assigned by journal 06 Oct, 2025 Submission checks completed at journal 03 Oct, 2025 First submitted to journal 01 Oct, 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-7758784","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":586520381,"identity":"32c9671d-648d-458d-b170-6cf564e9e893","order_by":0,"name":"Ubaldo Ramon-Julvez","email":"","orcid":"","institution":"University of Zaragoza","correspondingAuthor":false,"prefix":"","firstName":"Ubaldo","middleName":"","lastName":"Ramon-Julvez","suffix":""},{"id":586520382,"identity":"fb2b6b84-93a8-4338-863b-31cc1fc3a9bd","order_by":1,"name":"Monica Hernandez","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAqElEQVRIiWNgGAWjYDACCQbGByCSJC3MBiRrYSNJPQOD7uz2a9W8Oyzs+WcfYHz4gxgtZnfOlN3mPSPBLHEugdmYhygtN3LSbvO2SbAxnGFgkybKYSAtxUAtPPJnGNh/EuewG+nHmIFaJAyAtjAQ6zBmybltEgaGZxibpYnUkv7ww9u2Onu5M8wHPxLlMAYGHgMog7GBOA0MDOwPiFU5CkbBKBgFIxUAAOztLCW165d9AAAAAElFTkSuQmCC","orcid":"","institution":"University of Zaragoza","correspondingAuthor":true,"prefix":"","firstName":"Monica","middleName":"","lastName":"Hernandez","suffix":""},{"id":586520385,"identity":"8594237d-4813-4039-a12c-38df025e598d","order_by":2,"name":"Elvira Mayordomo","email":"","orcid":"","institution":"University of Zaragoza","correspondingAuthor":false,"prefix":"","firstName":"Elvira","middleName":"","lastName":"Mayordomo","suffix":""}],"badges":[],"createdAt":"2025-10-01 10:53:29","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7758784/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7758784/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":102296042,"identity":"1df2dc89-4073-4c51-97a5-a653d00acdc9","added_by":"auto","created_at":"2026-02-10 10:16:51","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":7106277,"visible":true,"origin":"","legend":"","description":"","filename":"ganmain.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7758784/v1_covered_d0e86b32-417b-459b-8a04-9c4a74d9701a.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"GeoShoot-GAN: Unsupervised Diffeomorphic Image Registration Using Geodesic Shooting and Generative Adversarial Networks","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":"diffeomorphic registration, geodesic shooting, unsupervised end-to-end, generative adversarial networks, computational anatomy","lastPublishedDoi":"10.21203/rs.3.rs-7758784/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7758784/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Deformable image registration is a fundamental step in medical image analysis. Diffeomorphic registration provides topology-preserving transformations which is an essential property for many clinical studies. Despite the theoretical strengths of geodesic shooting models, their high computational complexity and the absence of fully unsupervisedmethods have limited their widespread adoption. We propose GeoShoot-GAN, the first fully unsupervised, end-to-end framework for diffeomorphic registration via geodesic shooting. Our approach is based on adversarial learning, that allows the inference of complex deformable models without requiring the guidance ofground-truth deformations. We further extend the method to the stationary velocity field parameterization, providing a flexible framework that unifies geodesic andstationary variants. To stabilize adversarial training, we introduce tailored loss designs and careful optimization strategies that balance the relativedifficulty between generator and discriminator tasks. This design ensures that the generator produces smooth velocity fields while the discriminatorenforces plausibility on the image disimilarity after registration, driving the system toward realistic topology-preserving deformations. Experiments on two independent brain MRI datasets (NIREP and OASIS) demonstrate that GeoShoot-GAN achieves accurate diffeomorphic transformationsthrough efficient inference.The method performs competitively with state-of-the-art optimization- and learning- based methods, while preserving geodesic guarantees.Moreover, GeoShoot-GAN exhibits strong generalization across datasets, underscoring both its robustness and practical applicability. These results demonstrate the potential of adversarial learning as a powerful driver for unsupervised diffeomorphic registration, opening newopportunities for large-scale studies in Computational Anatomy and time-sensitive clinical applications, in contrast with diffusion modelsthat, while promissing, are still far from being computationally viable for this kind of studies.","manuscriptTitle":"GeoShoot-GAN: Unsupervised Diffeomorphic Image Registration Using Geodesic Shooting and Generative Adversarial Networks","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-02-07 03:31:33","doi":"10.21203/rs.3.rs-7758784/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"reviewersInvited","content":"","date":"2026-02-04T09:07:11+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2025-10-07T12:27:58+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-10-06T09:34:30+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-10-04T01:12:58+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2025-10-01T10:51:33+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":"d211566a-bd58-4fc2-92ae-48e8922fdbf2","owner":[],"postedDate":"February 7th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[{"id":62404554,"name":"Biological sciences/Computational biology and bioinformatics"},{"id":62404555,"name":"Physical sciences/Engineering"},{"id":62404556,"name":"Physical sciences/Mathematics and computing"}],"tags":[],"updatedAt":"2026-02-07T03:31:33+00:00","versionOfRecord":[],"versionCreatedAt":"2026-02-07 03:31:33","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7758784","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7758784","identity":"rs-7758784","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}