Lightweight U-Net for Breast Ultrasound Image Segmentation

Lightweight U-Net for Breast Ultrasound 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 Lightweight U-Net for Breast Ultrasound Image Segmentation Wenyang Qiu, Ethan Hamburg, Yinkun Zhou, Yaser Esmaeili Salehani This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6768159/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 Purpose: Accurate segmentation of breast lesions in ultrasound images is essential for early breast cancer diagnosis and treatment planning. This work introduces a lightweight U-Net architecture optimized for clinical deployment. Methods: We replace standard U-Net encoder blocks with a MobileNetV2 backbone trained from scratch, yielding 3.10 M parameters and 0.72 GFLOPs. Evaluations use the BUS-BRA dataset. Results: On the BUS-BRA dataset, the proposed model achieves a Dice coefficient of 88.88% and a mean IoU of 81.26%, surpassing the standard U-Net, Attention U-Net, and self-supervised baselines, while maintaining an efficient inference time of 1.53 ± 0.33 s per image. Conclusion: Combining a lightweight encoder with attention mechanisms delivers high segmentation accuracy and computational efficiency, making it well-suited for breast ultrasound applications on resource-limited hardware. Health sciences/Diseases/Cancer Health sciences/Diseases/Cancer/Cancer imaging breast cancer segmentation U-Net lightweight networks ultrasound imaging medical image analysis 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-6768159","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":492340723,"identity":"16744f73-eaa3-4a1a-8904-2ab02ee32d82","order_by":0,"name":"Wenyang Qiu","email":"","orcid":"","institution":"Concordia University","correspondingAuthor":false,"prefix":"","firstName":"Wenyang","middleName":"","lastName":"Qiu","suffix":""},{"id":492340724,"identity":"901e4c5a-b11c-462e-a7af-1c74bfb60ecd","order_by":1,"name":"Ethan Hamburg","email":"","orcid":"","institution":"Concordia University","correspondingAuthor":false,"prefix":"","firstName":"Ethan","middleName":"","lastName":"Hamburg","suffix":""},{"id":492340725,"identity":"d2872160-6f0c-4f0b-83fd-e4c383ee35ac","order_by":2,"name":"Yinkun Zhou","email":"","orcid":"","institution":"Concordia University","correspondingAuthor":false,"prefix":"","firstName":"Yinkun","middleName":"","lastName":"Zhou","suffix":""},{"id":492340726,"identity":"93408d00-ab36-4524-9933-ee3ea1195f68","order_by":3,"name":"Yaser Esmaeili Salehani","email":"data:image/png;base64,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","orcid":"","institution":"Concordia University","correspondingAuthor":true,"prefix":"","firstName":"Yaser","middleName":"Esmaeili","lastName":"Salehani","suffix":""}],"badges":[],"createdAt":"2025-05-28 12:38:30","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6768159/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6768159/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":105576048,"identity":"a1d894f2-72ac-4010-a3c4-20e6f667e9fd","added_by":"auto","created_at":"2026-03-27 13:42:40","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":317534,"visible":true,"origin":"","legend":"","description":"","filename":"LightweightUNetforBreastUltrasoundImageSegmentation.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6768159/v1_covered_55834db9-6f11-4512-9419-4a0ff7228082.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Lightweight U-Net for Breast Ultrasound 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":"breast cancer segmentation, U-Net, lightweight networks, ultrasound imaging, medical image analysis","lastPublishedDoi":"10.21203/rs.3.rs-6768159/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6768159/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003e\u003cstrong\u003ePurpose: \u003c/strong\u003eAccurate segmentation of breast lesions in ultrasound images is essential for early breast cancer diagnosis and treatment planning. This work introduces a lightweight U-Net architecture optimized for clinical deployment.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eMethods: \u003c/strong\u003eWe replace standard U-Net encoder blocks with a MobileNetV2 backbone trained from scratch, yielding 3.10 M parameters and 0.72 GFLOPs. Evaluations use the BUS-BRA dataset.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eResults:\u003c/strong\u003e On the BUS-BRA dataset, the proposed model achieves a Dice coefficient of 88.88% and a mean IoU of 81.26%, surpassing the standard U-Net, Attention U-Net, and self-supervised baselines, while maintaining an efficient inference time of 1.53 ± 0.33 s per image.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eConclusion:\u003c/strong\u003e Combining a lightweight encoder with attention mechanisms delivers high segmentation accuracy and computational efficiency, making it well-suited for breast ultrasound applications on resource-limited hardware.\u003c/p\u003e","manuscriptTitle":"Lightweight U-Net for Breast Ultrasound Image Segmentation","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-07-30 16:35:09","doi":"10.21203/rs.3.rs-6768159/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":"a5e4a0bd-a439-45a0-a886-3e39411a8c2f","owner":[],"postedDate":"July 30th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":52273524,"name":"Health sciences/Diseases/Cancer"},{"id":52273525,"name":"Health sciences/Diseases/Cancer/Cancer imaging"}],"tags":[],"updatedAt":"2026-03-27T13:36:55+00:00","versionOfRecord":[],"versionCreatedAt":"2025-07-30 16:35:09","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-6768159","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6768159","identity":"rs-6768159","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}