Robust and generalized deep learning-based approach for mouse bone segmentation from 3D high-resolution μCT imaging data

Robust and generalized deep learning-based approach for mouse bone segmentation from 3D high-resolution μCT imaging data | 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 Robust and generalized deep learning-based approach for mouse bone segmentation from 3D high-resolution μCT imaging data Amine Lagzouli, Peter Pivonka, David Cooper, Vittorio Sansalone, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4864927/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 13 Mar, 2025 Read the published version in Scientific Reports → Version 1 posted 10 You are reading this latest preprint version Abstract Recent advancements in deep learning have significantly enhanced the segmentation of high-resolution microcomputed tomography (µCT) bone scans. In this paper, we present the Dual-Branch Attention-based Hybrid Network (DBAHNet), a deep learning architecture designed for automatically segmenting the cortical and trabecular compartments in 3D µCT scans of mouse tibiae. DBAHNet’s hierarchical structure combines transformers and convolutional neural networks to capture long-range dependencies and local features for improved contextual representation. We trained DBAHNet on a limited dataset of 3D µCT scans of mouse tibiae and evaluated its performance on a diverse dataset collected from seven different research studies. This evaluation covered variations in resolutions, ages, mouse strains, drug treatments, surgical procedures, and mechanical loading. DBAHNet demonstrated excellent performance, achieving high accuracy, particularly in challenging scenarios with significantly altered bone morphology. The model’s robustness and generalization capabilities were rigorously tested under diverse and unseen conditions, confirming its effectiveness in the automated segmentation of high-resolution µCT mouse tibia scans. Our findings highlight DBAHNet’s potential to provide reliable and accurate 3D µCT mouse tibia segmentation, thereby enhancing and accelerating preclinical bone studies in drug development. The model and code are available at Github. Physical sciences/Mathematics and computing/Computer science Health sciences/Health care/Medical imaging Physical sciences/Engineering/Biomedical engineering Health sciences/Medical research/Pre clinical studies 3D Image segmentation Deep learning Microcomputed tomography µCT High-resolution Mouse tibia Robust model Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 13 Mar, 2025 Read the published version in Scientific Reports → Version 1 posted Editorial decision: Revision requested 19 Sep, 2024 Reviews received at journal 17 Sep, 2024 Reviews received at journal 09 Sep, 2024 Reviewers agreed at journal 09 Sep, 2024 Reviewers agreed at journal 08 Sep, 2024 Reviewers invited by journal 08 Sep, 2024 Editor assigned by journal 08 Sep, 2024 Editor invited by journal 14 Aug, 2024 Submission checks completed at journal 13 Aug, 2024 First submitted to journal 05 Aug, 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-4864927","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":351741636,"identity":"950ae6b0-ce2f-49bd-9ce0-0f728b393438","order_by":0,"name":"Amine Lagzouli","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABDElEQVRIiWNgGAWjYFACxgYGhgII60CCgY0ciHXgAUEtBhDmgYSKNGMIg6BNMC0MZw4nNoBY+LTwTzvc9uCDgZ3d/PYegwMP25jT54cdfgi0xU5OtwG7Fonbie2GMwySkxt7zhgcSGxjy914O80AqCXZ2OwADmtuJ7ZJ8xgwJzNL5IC08ORunJ0A0nIgcRsOLfIgLX8M6pPZIFok0g1np3/Aq8UApIXB4LAdD0hLwhmDBHnpHPy2GAK1SPYYHE+Q4DlWAAzkBMMN0jlAhgFuv8jdTn8m8aOi2l6+vXnjwx8G/+XlZ6dv/vChwk4Op/ehABIdYKeCVRrgVw4C9nCWfANuVaNgFIyCUTAyAQDfM2a47fXwywAAAABJRU5ErkJggg==","orcid":"","institution":"Queensland University of Technology","correspondingAuthor":true,"prefix":"","firstName":"Amine","middleName":"","lastName":"Lagzouli","suffix":""},{"id":351741637,"identity":"2d9f569a-b99b-4a94-9a50-8afb243d2c03","order_by":1,"name":"Peter Pivonka","email":"","orcid":"","institution":"Queensland University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Peter","middleName":"","lastName":"Pivonka","suffix":""},{"id":351741639,"identity":"83389beb-9c4a-4465-8f10-c44ba7661c97","order_by":2,"name":"David Cooper","email":"","orcid":"","institution":"University of Saskatchewan","correspondingAuthor":false,"prefix":"","firstName":"David","middleName":"","lastName":"Cooper","suffix":""},{"id":351741642,"identity":"4dff9ab8-5bc7-445e-a886-93329cd8e468","order_by":3,"name":"Vittorio Sansalone","email":"","orcid":"","institution":"Paris-Est Créteil University","correspondingAuthor":false,"prefix":"","firstName":"Vittorio","middleName":"","lastName":"Sansalone","suffix":""},{"id":351741645,"identity":"5de3605c-40fb-4297-9345-960b6b0fcf9d","order_by":4,"name":"Alice Othmani","email":"","orcid":"","institution":"Paris-Est Créteil University","correspondingAuthor":false,"prefix":"","firstName":"Alice","middleName":"","lastName":"Othmani","suffix":""}],"badges":[],"createdAt":"2024-08-06 02:23:35","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4864927/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4864927/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1038/s41598-025-92954-1","type":"published","date":"2025-03-13T15:58:35+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":78689699,"identity":"f069f640-6862-483e-93e6-47ad40150abd","added_by":"auto","created_at":"2025-03-17 16:13:06","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":2319147,"visible":true,"origin":"","legend":"","description":"","filename":"latexprojectsubmission.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4864927/v1_covered_bb156c41-a48c-49cb-85d0-5366a328a44d.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Robust and generalized deep learning-based approach for mouse bone segmentation from 3D high-resolution μCT imaging data","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":"3D Image segmentation, Deep learning, Microcomputed tomography µCT, High-resolution, Mouse tibia, Robust model","lastPublishedDoi":"10.21203/rs.3.rs-4864927/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4864927/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Recent advancements in deep learning have significantly enhanced the segmentation of high-resolution microcomputed tomography (µCT) bone scans. In this paper, we present the Dual-Branch Attention-based Hybrid Network (DBAHNet), a deep learning architecture designed for automatically segmenting the cortical and trabecular compartments in 3D µCT scans of mouse tibiae. DBAHNet’s hierarchical structure combines transformers and convolutional neural networks to capture long-range dependencies and local features for improved contextual representation. We trained DBAHNet on a limited dataset of 3D µCT scans of mouse tibiae and evaluated its performance on a diverse dataset collected from seven different research studies. This evaluation covered variations in resolutions, ages, mouse strains, drug treatments, surgical procedures, and mechanical loading. DBAHNet demonstrated excellent performance, achieving high accuracy, particularly in challenging scenarios with significantly altered bone morphology. The model’s robustness and generalization capabilities were rigorously tested under diverse and unseen conditions, confirming its effectiveness in the automated segmentation of high-resolution µCT mouse tibia scans. Our findings highlight DBAHNet’s potential to provide reliable and accurate 3D µCT mouse tibia segmentation, thereby enhancing and accelerating preclinical bone studies in drug development. The model and code are available at Github.","manuscriptTitle":"Robust and generalized deep learning-based approach for mouse bone segmentation from 3D high-resolution μCT imaging data","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-09-10 05:05:46","doi":"10.21203/rs.3.rs-4864927/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2024-09-19T22:59:27+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-09-18T01:42:41+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-09-10T03:51:38+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"82931503910045416599463107499453264807","date":"2024-09-09T22:25:30+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"243445818736027327305352479933659761261","date":"2024-09-09T00:42:19+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2024-09-09T00:35:05+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2024-09-09T00:30:58+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2024-08-14T13:55:37+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2024-08-13T09:06:16+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2024-08-06T02:22:19+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":"f4814845-6512-4291-8696-fdcf4e3401d9","owner":[],"postedDate":"September 10th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[{"id":37352890,"name":"Physical sciences/Mathematics and computing/Computer science"},{"id":37352891,"name":"Health sciences/Health care/Medical imaging"},{"id":37352892,"name":"Physical sciences/Engineering/Biomedical engineering"},{"id":37352893,"name":"Health sciences/Medical research/Pre clinical studies"}],"tags":[],"updatedAt":"2025-03-17T16:08:45+00:00","versionOfRecord":{"articleIdentity":"rs-4864927","link":"https://doi.org/10.1038/s41598-025-92954-1","journal":{"identity":"scientific-reports","isVorOnly":false,"title":"Scientific Reports"},"publishedOn":"2025-03-13 15:58:35","publishedOnDateReadable":"March 13th, 2025"},"versionCreatedAt":"2024-09-10 05:05:46","video":"","vorDoi":"10.1038/s41598-025-92954-1","vorDoiUrl":"https://doi.org/10.1038/s41598-025-92954-1","workflowStages":[]},"version":"v1","identity":"rs-4864927","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4864927","identity":"rs-4864927","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}