SAFNet: A Spatially Adaptive Fusion Network for Dual-Domain Undersampled MRI Reconstruction

SAFNet: A Spatially Adaptive Fusion Network for Dual-Domain Undersampled MRI 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 Research Article SAFNet: A Spatially Adaptive Fusion Network for Dual-Domain Undersampled MRI Reconstruction Yingjie Huo, HongYuan Zhang, Dan Ge, Ziliang Ren This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6103845/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 25 Sep, 2025 Read the published version in Physical and Engineering Sciences in Medicine → Version 1 posted 6 You are reading this latest preprint version Abstract Undersampled magnetic resonance imaging (MRI) reconstruction aims to minimize scanning time while maintaining optimal image quality, enhancing patient comfort and clinical efficiency. Currently, parallel reconstruction strategies in both k-space and image domains effectively utilize dual-domain information to enhance image feature capture and reconstruction accuracy. However, most existing dual-domain information fusion methods primarily utilize straightforward fusion techniques, such as weighted fusion and cascade processing, neglecting differences in image spatial features and limiting the full exploitation of dual-domain information. Moreover, these methods are plagued by limited receptive field scales, which curtails the network's ability to comprehend and depict complex image structures. In this paper, we introduce a spatially adaptive fusion network (SAFNet) for dual-domain undersampled MRI reconstruction. SAFNet comprises two parallel reconstruction branches. The employment of weighted shortcut module empowers the network to effectuate a dynamic adjustment of the reconstruction strategy, enhancing its flexibility and responsiveness in handling diverse reconstruction scenarios. Spatial adaptive fusion modules are integrated within the decoder components of each branch. By spatially adaptively fusing the dual-domain features, it facilitates the enhanced extraction and utilization of intrinsic correlated features across dual domains. Furthermore, we incorporate a dynamic perception initialization module in the encoder of each branch to enrich the network's receptive fields, enhancing its ability to capture useful information across different scales. Experimental results indicate that SAFNet achieves more accurate reconstruction and demonstrates superior adaptability compared to several state-of-the-art methods. The framework presented in this paper offers valuable insights for image reconstruction and multimodal information fusion. magnetic resonance imaging (MRI) convolutional neural network undersampled MRI reconstruction information fusion spatially adaptive fusion Full Text Cite Share Download PDF Status: Published Journal Publication published 25 Sep, 2025 Read the published version in Physical and Engineering Sciences in Medicine → Version 1 posted Reviewers agreed at journal 30 Apr, 2025 Reviewers invited by journal 26 Mar, 2025 Editor invited by journal 12 Mar, 2025 Editor assigned by journal 10 Mar, 2025 First submitted to journal 09 Mar, 2025 Editorial decision: Major revisions 03 Mar, 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-6103845","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":434584654,"identity":"ef93f60b-5d4b-40b4-adef-36ffb701e8cc","order_by":0,"name":"Yingjie Huo","email":"","orcid":"","institution":"zhangzhou institute of science \u0026 technology and j.balasagyn kyrgyz national university","correspondingAuthor":false,"prefix":"","firstName":"Yingjie","middleName":"","lastName":"Huo","suffix":""},{"id":434584655,"identity":"4014dd59-e96f-44b6-93c2-d42c101bdf13","order_by":1,"name":"HongYuan Zhang","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA40lEQVRIiWNgGAWjYBAC/hkQWs6AGUwzE9YicQNCGxOvxSACQiduYCBai3TzsYdffh1O387OfvEDQ4V1YgP72QP4tcgcSzeW7Tucu7OZp1iC4Ux6YgNPXgJ+LRI5ZtKSPYdzNxzmSWNgbDuc2CDBY0BAS/43kJZ0A7CWf8Roichhk/zw43CCwWH2YwyMDURokbiRZibN2JBuCPQLs0QC0GNtPDn4tfDPSH4m+eOPtbw5//GHHz7UWMv2s5/BrwUEmHnbmoEU0D0JQIqNoHogYPzxpw5IsT8gRvEoGAWjYBSMQAAA++ZFrS29lO8AAAAASUVORK5CYII=","orcid":"https://orcid.org/0009-0003-3555-0635","institution":"zhangzhou institute of science \u0026 technology","correspondingAuthor":true,"prefix":"","firstName":"HongYuan","middleName":"","lastName":"Zhang","suffix":""},{"id":434584656,"identity":"a283d345-9d81-4b0e-92ec-7ea1fbc7a3ef","order_by":2,"name":"Dan Ge","email":"","orcid":"","institution":"j.balasagyn kyrgyz national university","correspondingAuthor":false,"prefix":"","firstName":"Dan","middleName":"","lastName":"Ge","suffix":""},{"id":434584657,"identity":"396ac8dd-1a9e-462d-92dd-0b3042099ce7","order_by":3,"name":"Ziliang Ren","email":"","orcid":"","institution":"Dongguan University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Ziliang","middleName":"","lastName":"Ren","suffix":""}],"badges":[],"createdAt":"2025-02-25 09:48:15","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6103845/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6103845/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1007/s13246-025-01628-9","type":"published","date":"2025-09-25T15:57:24+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":92430663,"identity":"f17417ff-8d0d-4862-9414-0aaf8d35bf40","added_by":"auto","created_at":"2025-09-29 16:07:26","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1098785,"visible":true,"origin":"","legend":"","description":"","filename":"SAFNetv3.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6103845/v1_covered_73cd320c-2596-4196-bfcb-f2e8cc5ccf93.pdf"}],"financialInterests":"","formattedTitle":"SAFNet: A Spatially Adaptive Fusion Network for Dual-Domain Undersampled MRI Reconstruction","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":true,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":true,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"physical-and-engineering-sciences-in-medicine","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"apes","sideBox":"Learn more about [Physical and Engineering Sciences in Medicine](http://link.springer.com/journal/13246)","snPcode":"","submissionUrl":"https://www.editorialmanager.com/apes/default.aspx","title":"Physical and Engineering Sciences in Medicine","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"magnetic resonance imaging (MRI), convolutional neural network, undersampled MRI reconstruction, information fusion, spatially adaptive fusion","lastPublishedDoi":"10.21203/rs.3.rs-6103845/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6103845/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eUndersampled magnetic resonance imaging (MRI) reconstruction aims to minimize scanning time while maintaining optimal image quality, enhancing patient comfort and clinical efficiency. Currently, parallel reconstruction strategies in both k-space and image domains effectively utilize dual-domain information to enhance image feature capture and reconstruction accuracy. However, most existing dual-domain information fusion methods primarily utilize straightforward fusion techniques, such as weighted fusion and cascade processing, neglecting differences in image spatial features and limiting the full exploitation of dual-domain information. Moreover, these methods are plagued by limited receptive field scales, which curtails the network's ability to comprehend and depict complex image structures. In this paper, we introduce a spatially adaptive fusion network (SAFNet) for dual-domain undersampled MRI reconstruction. SAFNet comprises two parallel reconstruction branches. The employment of weighted shortcut module empowers the network to effectuate a dynamic adjustment of the reconstruction strategy, enhancing its flexibility and responsiveness in handling diverse reconstruction scenarios. Spatial adaptive fusion modules are integrated within the decoder components of each branch. By spatially adaptively fusing the dual-domain features, it facilitates the enhanced extraction and utilization of intrinsic correlated features across dual domains. Furthermore, we incorporate a dynamic perception initialization module in the encoder of each branch to enrich the network's receptive fields, enhancing its ability to capture useful information across different scales. Experimental results indicate that SAFNet achieves more accurate reconstruction and demonstrates superior adaptability compared to several state-of-the-art methods. The framework presented in this paper offers valuable insights for image reconstruction and multimodal information fusion.\u003c/p\u003e","manuscriptTitle":"SAFNet: A Spatially Adaptive Fusion Network for Dual-Domain Undersampled MRI Reconstruction","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-04-14 11:36:53","doi":"10.21203/rs.3.rs-6103845/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"reviewerAgreed","content":"","date":"2025-05-01T03:55:36+00:00","index":0,"fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-03-27T03:59:26+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"Physical and Engineering Sciences in Medicine","date":"2025-03-12T08:54:10+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-03-10T15:59:06+00:00","index":"","fulltext":""},{"type":"submitted","content":"Physical and Engineering Sciences in Medicine","date":"2025-03-09T21:28:23+00:00","index":"","fulltext":""},{"type":"decision","content":"Major revisions","date":"2025-03-03T22:47:54+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"physical-and-engineering-sciences-in-medicine","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"apes","sideBox":"Learn more about [Physical and Engineering Sciences in Medicine](http://link.springer.com/journal/13246)","snPcode":"","submissionUrl":"https://www.editorialmanager.com/apes/default.aspx","title":"Physical and Engineering Sciences in Medicine","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"e6010b97-b0e0-46da-a56a-3a1fd0c914d9","owner":[],"postedDate":"April 14th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2025-09-29T16:04:44+00:00","versionOfRecord":{"articleIdentity":"rs-6103845","link":"https://doi.org/10.1007/s13246-025-01628-9","journal":{"identity":"physical-and-engineering-sciences-in-medicine","isVorOnly":false,"title":"Physical and Engineering Sciences in Medicine"},"publishedOn":"2025-09-25 15:57:24","publishedOnDateReadable":"September 25th, 2025"},"versionCreatedAt":"2025-04-14 11:36:53","video":"","vorDoi":"10.1007/s13246-025-01628-9","vorDoiUrl":"https://doi.org/10.1007/s13246-025-01628-9","workflowStages":[]},"version":"v1","identity":"rs-6103845","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6103845","identity":"rs-6103845","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}