GoLoCo-Net: Global-Local guided Contextual Attention Network for Medical Images Segmentation

GoLoCo-Net: Global-Local guided Contextual Attention Network for Medical Images 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 Article GoLoCo-Net: Global-Local guided Contextual Attention Network for Medical Images Segmentation Ying He, Marc E. Miquel, Qianni Zhang This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8252130/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 05 Mar, 2026 Read the published version in Scientific Reports → Version 1 posted 15 You are reading this latest preprint version Abstract Accurate medical image segmentation plays a vital role in assisting diagnosis with quantifiable visual evidence. Due to the complex structure and diverse patterns in medical images, it is crucial to capture both short and long-range pixel relations. While transformers are adept at modeling long-range spatial dependencies in images, they struggle with learning local pixel relationships. To address this, we propose a deep learning network named GoLoCo-Net incorporating a dual decoder structure. More specifically, one decoder entails a Contextual Attention Feature Enhancement (CAFE) module to enhance the features for a broader capture of local and global contexts, whereas the other uses a Global-Guide-Local Feature (GGLF) module that leverages high-level features to enrich low-level features with a global context. The proposed method is evaluated on two dynamic MRI datasets and one multi-organ CT dataset. Experimental results show that the model achieves state-of-the-art performance across all three datasets. The code is available: https://github.com/Yhe9718/GoLoCoNet . Biological sciences/Computational biology and bioinformatics Physical sciences/Mathematics and computing Full Text Additional Declarations Competing interest reported. Ying He reports financial support was provided by Barts Charity. If there are other authors, they declare that they have no known competing financial interests or personal relationships that could have appeared to influence the work reported in this paper. Cite Share Download PDF Status: Published Journal Publication published 05 Mar, 2026 Read the published version in Scientific Reports → Version 1 posted Editorial decision: Revision requested 18 Dec, 2025 Reviewers agreed at journal 17 Dec, 2025 Reviewers agreed at journal 16 Dec, 2025 Reviews received at journal 16 Dec, 2025 Reviewers agreed at journal 15 Dec, 2025 Reviewers agreed at journal 14 Dec, 2025 Reviews received at journal 13 Dec, 2025 Reviewers agreed at journal 12 Dec, 2025 Reviewers agreed at journal 10 Dec, 2025 Reviewers agreed at journal 10 Dec, 2025 Reviewers invited by journal 10 Dec, 2025 Editor invited by journal 08 Dec, 2025 Editor assigned by journal 04 Dec, 2025 Submission checks completed at journal 04 Dec, 2025 First submitted to journal 01 Dec, 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-8252130","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":560037500,"identity":"845bf0e2-8d91-4dd6-848e-acfda03f2979","order_by":0,"name":"Ying He","email":"","orcid":"","institution":"Queen Mary University of London","correspondingAuthor":false,"prefix":"","firstName":"Ying","middleName":"","lastName":"He","suffix":""},{"id":560037501,"identity":"b02fe99b-dd06-46cd-9b5a-be64814c8369","order_by":1,"name":"Marc E. Miquel","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA10lEQVRIiWNgGAWjYPACCSBmbnzA2ECaFsZmA4gWZqK1MbZJEKVFt/3sww+MORayG443tlUX7qhjMGfvP4BXi9mZdGMJxm0SxhvOHGy7PfPMYQbLnsP4bTE7kMbGANSSuOFGYttt3rYDDAY3kgloOf8MquX+w7Zi3rY6BoP7jwlouQG3hbGNmbeNGWgLAe+b3XjGLJEI9MvMM4nN0rxth3kMziQbEHBYGuOHj9vqZPuOHz74GegwOYPjBx/gtwYEEoCR0gBl8xBWDgWkJJVRMApGwSgYaQAADTVHn3MlYkgAAAAASUVORK5CYII=","orcid":"","institution":"Guy's and St Thomas' NHS Foundation Trust","correspondingAuthor":true,"prefix":"","firstName":"Marc","middleName":"E.","lastName":"Miquel","suffix":""},{"id":560037502,"identity":"7493cacc-0a4d-4c8f-85de-f4d4484e3610","order_by":2,"name":"Qianni Zhang","email":"","orcid":"","institution":"Queen Mary University of London","correspondingAuthor":false,"prefix":"","firstName":"Qianni","middleName":"","lastName":"Zhang","suffix":""}],"badges":[],"createdAt":"2025-12-01 15:38:26","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8252130/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8252130/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1038/s41598-026-42415-0","type":"published","date":"2026-03-05T16:00:08+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":98274860,"identity":"1d86666c-dfbb-49c9-91f5-e78eb3858822","added_by":"auto","created_at":"2025-12-16 03:22:57","extension":"json","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":5314,"visible":true,"origin":"","legend":"","description":"","filename":"25840a69e5f44ca89db2f252544aefd5.json","url":"https://assets-eu.researchsquare.com/files/rs-8252130/v1/6ab226b2ca892802cfab1334.json"},{"id":104250787,"identity":"b0af4321-f2d5-44a8-9ae8-8c45faa74af0","added_by":"auto","created_at":"2026-03-09 16:08:30","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":581426,"visible":true,"origin":"","legend":"","description":"","filename":"submissionscientificreports.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8252130/v1_covered_bd974064-c08c-49f6-bcbc-6e0ac3571aaa.pdf"}],"financialInterests":"Competing interest reported. Ying He reports financial support was provided by Barts Charity. If there are other authors, they declare that they have no known competing financial interests or personal relationships that could have appeared to influence the work reported in this paper.","formattedTitle":"GoLoCo-Net: Global-Local guided Contextual Attention Network for Medical Images Segmentation","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":"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":"","lastPublishedDoi":"10.21203/rs.3.rs-8252130/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8252130/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Accurate medical image segmentation plays a vital role in assisting diagnosis with quantifiable visual evidence. Due to the complex structure and diverse patterns in medical images, it is crucial to capture both short and long-range pixel relations. While transformers are adept at modeling long-range spatial dependencies in images, they struggle with learning local pixel relationships. To address this, we propose a deep learning network named GoLoCo-Net incorporating a dual decoder structure. More specifically, one decoder entails a Contextual Attention Feature Enhancement (CAFE) module to enhance the features for a broader capture of local and global contexts, whereas the other uses a Global-Guide-Local Feature (GGLF) module that leverages high-level features to enrich low-level features with a global context. The proposed method is evaluated on two dynamic MRI datasets and one multi-organ CT dataset. Experimental results show that the model achieves state-of-the-art performance across all three datasets. The code is available:https://github.com/Yhe9718/GoLoCoNet.","manuscriptTitle":"GoLoCo-Net: Global-Local guided Contextual Attention Network for Medical Images Segmentation","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-12-16 03:22:53","doi":"10.21203/rs.3.rs-8252130/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-12-18T08:43:26+00:00","index":"","fulltext":""},{"type":"reviewerAgreed","content":"154531265853707505588765214094923369802","date":"2025-12-17T07:04:47+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"180702641310739918726197661541511069295","date":"2025-12-16T11:39:19+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-12-16T05:29:06+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"102344888960852709377176899685536360388","date":"2025-12-16T01:03:36+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"59556436594138175692209729173153386822","date":"2025-12-14T12:06:27+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-12-13T08:54:27+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"182176974706193538470612939125549470345","date":"2025-12-13T00:49:33+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"141418257755069704964996152658922126745","date":"2025-12-11T00:30:14+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"191926499704445449310333589451820846062","date":"2025-12-11T00:29:48+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-12-11T00:28:46+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2025-12-08T16:39:56+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-12-04T13:55:44+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-12-04T13:55:32+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2025-12-01T15:33:51+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":"e0f9b205-7d37-4baf-adfd-9693c03f838b","owner":[],"postedDate":"December 16th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[{"id":59619943,"name":"Biological sciences/Computational biology and bioinformatics"},{"id":59619944,"name":"Physical sciences/Mathematics and computing"}],"tags":[],"updatedAt":"2026-03-09T16:04:27+00:00","versionOfRecord":{"articleIdentity":"rs-8252130","link":"https://doi.org/10.1038/s41598-026-42415-0","journal":{"identity":"scientific-reports","isVorOnly":false,"title":"Scientific Reports"},"publishedOn":"2026-03-05 16:00:08","publishedOnDateReadable":"March 5th, 2026"},"versionCreatedAt":"2025-12-16 03:22:53","video":"","vorDoi":"10.1038/s41598-026-42415-0","vorDoiUrl":"https://doi.org/10.1038/s41598-026-42415-0","workflowStages":[]},"version":"v1","identity":"rs-8252130","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8252130","identity":"rs-8252130","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}