AFCNet:An adaptive fusion of composite attention convolutional neuralnetwork for polyp image segmentation

AFCNet:An adaptive fusion of composite attention convolutional neuralnetwork for polyp image 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 AFCNet:An adaptive fusion of composite attention convolutional neuralnetwork for polyp image segmentation Bo jiao Jin, Yi Zhang, Lin Qi, Wei Qian This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4483283/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 Accurately locating and segmenting polyps from colon images is crucial for the treatment of rectal cancer. However, the environment of rectal polyps is characterized by high noise, diverse sizes, complex boundaries, and a high demand for detailed information, making the task challenging. The acquisition and processing of polyp features are central to the research on polyp segmentation methods. This paper introduces an Adaptive Fusion Of Composite Attention Convolutional Neural Network (AFCNet) for polyp image segmentation. First, this work combine depth-wise separable convolutions and convolutional attention mechanisms with a multi-branch structure to better supplement missing details and unearth potential critical features. Secondly, we employ a multi-scale cross structure and an adaptive multi-scale feature harmonization module to balance the contribution of features at different levels, thus fully integrating information across scales to maximize the utilization of previously acquired features. Lastly, we propose an upsampling feature retrospective module to filter detailed information and use the concept of gating units to filter out interfering information. Extensive experiments on five publicly available polyp segmentation datasets demonstrate the effectiveness of our AFCNet in enhancing the accuracy of polyp segmentation.The experimental results indicate that AFCNet significantly outperforms state-of-the-art models. AFCNet is an effective polyp segmentation network, and due to its excellent generalization ability, it can also be applied to other medical image segmentation tasks. Physical sciences/Engineering/Biomedical engineering Physical sciences/Mathematics and computing/Computational science Physical sciences/Mathematics and computing/Software Polyp segmentation Convolutional attention Adaptive feature fusion Gating units 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-4483283","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":311694402,"identity":"1746a5a6-f34c-4a17-bd6e-966c2a380862","order_by":0,"name":"Bo jiao Jin","email":"","orcid":"","institution":"Northeastern University","correspondingAuthor":false,"prefix":"","firstName":"Bo","middleName":"jiao","lastName":"Jin","suffix":""},{"id":311694404,"identity":"12d0a06c-64da-4f9f-b678-9641d9b02e88","order_by":1,"name":"Yi Zhang","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA9UlEQVRIiWNgGAWjYDACCQgpx8DA2HgAKmZAlBZjoJYGkrQwJDYACeK0yM9ufvbwa5tF+tr2ww0HGHfYJDawN2+TYKi5g1ML45xj5saybRK5284kArWcSUts4DlWJsFw7BlOLcwSCWbSkiAtB0Ba2g4nNkjkmEkwNhzGqYVNIv0bSEu62fmHIC3/Exvk3+DXwgM0U/JjG9CuG2BbgHZJ8ODXIiGRUybNcE7CcNsNoC2JbcnGbTxpxRYJx3BrkZ+Rvk3yR1mdvNn59IcPPrbZyfazH95440MNbi3gIOBlg7ISQL6DMfABxh9/CKgYBaNgFIyCkQ0A9IRW56UywMMAAAAASUVORK5CYII=","orcid":"","institution":"Northeastern University","correspondingAuthor":true,"prefix":"","firstName":"Yi","middleName":"","lastName":"Zhang","suffix":""},{"id":311694409,"identity":"f3fc377b-4149-4215-95ac-b036d6a8c2ae","order_by":2,"name":"Lin Qi","email":"","orcid":"","institution":"Northeastern University","correspondingAuthor":false,"prefix":"","firstName":"Lin","middleName":"","lastName":"Qi","suffix":""},{"id":311694412,"identity":"c69c479d-9763-4a0e-ae5e-daa27ddf1781","order_by":3,"name":"Wei Qian","email":"","orcid":"","institution":"Northeastern University","correspondingAuthor":false,"prefix":"","firstName":"Wei","middleName":"","lastName":"Qian","suffix":""}],"badges":[],"createdAt":"2024-05-27 08:03:54","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4483283/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4483283/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":86129749,"identity":"62bfd000-6873-4fcc-936a-cb3d767cfc11","added_by":"auto","created_at":"2025-07-07 06:32:04","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1067887,"visible":true,"origin":"","legend":"","description":"","filename":"AFCNet.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4483283/v1_covered_718b06f0-aee7-4643-892b-00bd8b6b8991.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"AFCNet:An adaptive fusion of composite attention convolutional neuralnetwork for polyp image 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":"Polyp segmentation, Convolutional attention, Adaptive feature fusion, Gating units","lastPublishedDoi":"10.21203/rs.3.rs-4483283/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4483283/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Accurately locating and segmenting polyps from colon images is crucial for the treatment of rectal cancer. However, the environment of rectal polyps is characterized by high noise, diverse sizes, complex boundaries, and a high demand for detailed information, making the task challenging. The acquisition and processing of polyp features are central to the research on polyp segmentation methods. This paper introduces an Adaptive Fusion Of Composite Attention Convolutional Neural Network (AFCNet) for polyp image segmentation. First, this work combine depth-wise separable convolutions and convolutional attention mechanisms with a multi-branch structure to better supplement missing details and unearth potential critical features. Secondly, we employ a multi-scale cross structure and an adaptive multi-scale feature harmonization module to balance the contribution of features at different levels, thus fully integrating information across scales to maximize the utilization of previously acquired features. Lastly, we propose an upsampling feature retrospective module to filter detailed information and use the concept of gating units to filter out interfering information. Extensive experiments on five publicly available polyp segmentation datasets demonstrate the effectiveness of our AFCNet in enhancing the accuracy of polyp segmentation.The experimental results indicate that AFCNet significantly outperforms state-of-the-art models. AFCNet is an effective polyp segmentation network, and due to its excellent generalization ability, it can also be applied to other medical image segmentation tasks.","manuscriptTitle":"AFCNet:An adaptive fusion of composite attention convolutional neuralnetwork for polyp image segmentation","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-06-10 07:18:30","doi":"10.21203/rs.3.rs-4483283/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":"2a0666ff-f1c6-40dc-a4b1-b61bddbc517b","owner":[],"postedDate":"June 10th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":32943620,"name":"Physical sciences/Engineering/Biomedical engineering"},{"id":32943621,"name":"Physical sciences/Mathematics and computing/Computational science"},{"id":32943622,"name":"Physical sciences/Mathematics and computing/Software"}],"tags":[],"updatedAt":"2025-07-07T06:23:52+00:00","versionOfRecord":[],"versionCreatedAt":"2024-06-10 07:18:30","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-4483283","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4483283","identity":"rs-4483283","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}