A Multi-Scale Channel Attention Network with Federated Learning for Magnetic Resonance Image Super-Resolution

A Multi-Scale Channel Attention Network with Federated Learning for Magnetic Resonance Image Super-Resolution | 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 A Multi-Scale Channel Attention Network with Federated Learning for Magnetic Resonance Image Super-Resolution Feiqiang Liu, Aiwen Jiang, Lihui Chen This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4146876/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 23 Jul, 2024 Read the published version in Multimedia Systems → Version 1 posted 14 You are reading this latest preprint version Abstract Magnetic resonance (MR) images are widely used for clinical diagnosis, whereas its resolution is always limited by some surrounding factors, and under-sampled data is usually generated during imaging. Since high-resolution (HR) MR images contribute to the clinic diagnosis, reconstructing HR MR images from these under-sampled data is pretty important. Recently, deep learning (DL) methods for HR reconstruction of MR images have achieved impressive performance. However, it is difficult to collect enough data for training DL models in practice due to medical data privacy regulations. Fortunately, federated learning (FL) is proposed to eliminate this issue by local/distributed training and encryption. In this paper, we propose a multi-scale channel attention network (MSCAN) for MR image super-resolution (SR) and integrate it into an FL framework named FedAve to make use of data from multiple institutions and avoid privacy risk. Specifically, to utilize multi-scale information in MR images, we introduce a multi-scale feature block (MSFB), in which multi-scale features are extracted and attention among features at different scales is captured to re-weight these multi-scale features. Then, a spatial gradient profile loss is integrated into MSCAN to facilitate the recovery of textures in MR images. Last, we incorporate MSCAN into FedAve to simulate the scenery of collaborated training among multiple institutions. Ablation studies show the effectiveness of the multi-scale features, the multi-scale channel attention, and the texture loss. Comparative experiments with some state-of-the-art (SOTA) methods indicate that the proposed MSCAN is superior to the compared methods and the model with FL has close results to the one trained by centralized data. Magnetic resonance imaging image super-resolution deep learning multi-resolution networks channel attention Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 23 Jul, 2024 Read the published version in Multimedia Systems → Version 1 posted Editorial decision: Revision requested 20 Jun, 2024 Reviewers agreed at journal 19 Jun, 2024 Reviews received at journal 18 Jun, 2024 Reviewers agreed at journal 18 Jun, 2024 Reviewers agreed at journal 16 Jun, 2024 Reviewers agreed at journal 16 Jun, 2024 Reviewers agreed at journal 16 Jun, 2024 Reviews received at journal 07 May, 2024 Reviewers agreed at journal 09 Apr, 2024 Reviewers agreed at journal 09 Apr, 2024 Reviewers invited by journal 09 Apr, 2024 Editor assigned by journal 06 Apr, 2024 Submission checks completed at journal 26 Mar, 2024 First submitted to journal 21 Mar, 2024 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-4146876","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":289328619,"identity":"07e23e3e-b02c-4b6e-8f6c-e73ce7f826fd","order_by":0,"name":"Feiqiang Liu","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAyElEQVRIie3QsQrCMBCA4StCuxzimCJWfAAhEHCx1MEXMRTataNjipC+hPgYzi0ZfA2zO+QBHIy4CAqJm0P+7eC+4Q4gFPrDEjESPdA8i5O21caHYB9Z0lRsjOrAiC8BMIqfSC0n6EUS3iqkistUSyBQZEvhIqiFJTWTUy6vDZRs1TvIhvAnWc8s6SiBnp9dBF9kFMl0kAR/INuFJJEvsbcMR1qxGLl9MvW4BZNSmds9z+bdRWuzLzInAdi9D9S5/kFCoVAo9KUHjD9CkzxWcsYAAAAASUVORK5CYII=","orcid":"","institution":"Jiangxi Normal University","correspondingAuthor":true,"prefix":"","firstName":"Feiqiang","middleName":"","lastName":"Liu","suffix":""},{"id":289328620,"identity":"51c56771-5336-485e-b7a4-f9ad9475a03e","order_by":1,"name":"Aiwen Jiang","email":"","orcid":"","institution":"Jiangxi Normal University","correspondingAuthor":false,"prefix":"","firstName":"Aiwen","middleName":"","lastName":"Jiang","suffix":""},{"id":289328621,"identity":"3bf5d728-a0a4-428c-b740-91d7b3b74b3c","order_by":2,"name":"Lihui Chen","email":"","orcid":"","institution":"Chongqing University","correspondingAuthor":false,"prefix":"","firstName":"Lihui","middleName":"","lastName":"Chen","suffix":""}],"badges":[],"createdAt":"2024-03-22 03:59:27","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4146876/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4146876/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1007/s00530-024-01415-8","type":"published","date":"2024-07-23T16:15:03+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":61596842,"identity":"d069ad76-776a-44d2-9b61-eb9cf78e7fb1","added_by":"auto","created_at":"2024-08-01 17:30:13","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1080518,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4146876/v1_covered_498e1838-8035-48ee-9123-835827772bc8.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"A Multi-Scale Channel Attention Network with Federated Learning for Magnetic Resonance Image Super-Resolution","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":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"multimedia-systems","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"mmsj","sideBox":"Learn more about [Multimedia Systems](http://link.springer.com/journal/530)","snPcode":"530","submissionUrl":"https://submission.nature.com/new-submission/530/3","title":"Multimedia Systems","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Magnetic resonance imaging, image super-resolution, deep learning, multi-resolution networks, channel attention","lastPublishedDoi":"10.21203/rs.3.rs-4146876/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4146876/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eMagnetic resonance (MR) images are widely used for clinical diagnosis, whereas its resolution is always limited by some surrounding factors, and under-sampled data is usually generated during imaging. Since high-resolution (HR) MR images contribute to the clinic diagnosis, reconstructing HR MR images from these under-sampled data is pretty important. Recently, deep learning (DL) methods for HR reconstruction of MR images have achieved impressive performance. However, it is difficult to collect enough data for training DL models in practice due to medical data privacy regulations. Fortunately, federated learning (FL) is proposed to eliminate this issue by local/distributed training and encryption. In this paper, we propose a multi-scale channel attention network (MSCAN) for MR image super-resolution (SR) and integrate it into an FL framework named FedAve to make use of data from multiple institutions and avoid privacy risk. Specifically, to utilize multi-scale information in MR images, we introduce a multi-scale feature block (MSFB), in which multi-scale features are extracted and attention among features at different scales is captured to re-weight these multi-scale features. Then, a spatial gradient profile loss is integrated into MSCAN to facilitate the recovery of textures in MR images. Last, we incorporate MSCAN into FedAve to simulate the scenery of collaborated training among multiple institutions. Ablation studies show the effectiveness of the multi-scale features, the multi-scale channel attention, and the texture loss. Comparative experiments with some state-of-the-art (SOTA) methods indicate that the proposed MSCAN is superior to the compared methods and the model with FL has close results to the one trained by centralized data.\u003c/p\u003e","manuscriptTitle":"A Multi-Scale Channel Attention Network with Federated Learning for Magnetic Resonance Image Super-Resolution","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-04-10 12:21:52","doi":"10.21203/rs.3.rs-4146876/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2024-06-20T10:32:31+00:00","index":"","fulltext":""},{"type":"reviewerAgreed","content":"265686191131898805394323795103084101518","date":"2024-06-19T16:37:16+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-06-19T02:17:10+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"101584169366429855827634847278560216423","date":"2024-06-18T11:31:40+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"237690115802547862119941368950948313477","date":"2024-06-16T16:36:35+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"190360609160686233447873923003718737903","date":"2024-06-16T12:19:03+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"331434297233732772593165334282436761433","date":"2024-06-16T12:11:06+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-05-07T15:31:25+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"ad09554d-5bd7-4fbb-9375-841b89263b48","date":"2024-04-09T14:37:39+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"f4f6f553-0826-41c0-a1c5-d8daf5445801","date":"2024-04-09T14:32:24+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2024-04-09T14:23:27+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2024-04-07T02:11:38+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2024-03-26T10:31:01+00:00","index":"","fulltext":""},{"type":"submitted","content":"Multimedia Systems","date":"2024-03-22T03:54:23+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"multimedia-systems","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"mmsj","sideBox":"Learn more about [Multimedia Systems](http://link.springer.com/journal/530)","snPcode":"530","submissionUrl":"https://submission.nature.com/new-submission/530/3","title":"Multimedia Systems","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"5c11e637-a074-43a1-8734-ba65989b499c","owner":[],"postedDate":"April 10th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2024-08-01T17:16:42+00:00","versionOfRecord":{"articleIdentity":"rs-4146876","link":"https://doi.org/10.1007/s00530-024-01415-8","journal":{"identity":"multimedia-systems","isVorOnly":false,"title":"Multimedia Systems"},"publishedOn":"2024-07-23 16:15:03","publishedOnDateReadable":"July 23rd, 2024"},"versionCreatedAt":"2024-04-10 12:21:52","video":"","vorDoi":"10.1007/s00530-024-01415-8","vorDoiUrl":"https://doi.org/10.1007/s00530-024-01415-8","workflowStages":[]},"version":"v1","identity":"rs-4146876","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4146876","identity":"rs-4146876","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}