Deep Learning-Based Bone Age Assessment Using Multi-Site MRI Epiphyseal Imaging: A Retrospective Study

Deep Learning-Based Bone Age Assessment Using Multi-Site MRI Epiphyseal Imaging: A Retrospective Study | 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 Deep Learning-Based Bone Age Assessment Using Multi-Site MRI Epiphyseal Imaging: A Retrospective Study Lei Wan, hui-ming zhou, yuan-zhe li, Wen-tao Xia, Zhi Yan, Mao-wen Wang, and 6 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6599801/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 This study presents BA-Net, a deep learning framework designed to automate juvenile bone age assessment by analyzing epiphyseal union patterns across wrist and knee MRI scans. Leveraging 474 axial wrist, 1,149 coronal knee, and 105 combined wrist-knee T1-weighted MRI scans collected between 2015 and 2021, the model integrates convolutional neural networks to extract multidimensional skeletal features and sex-specific parameters for multi-label classification. Data were partitioned into training, validation, and test sets to evaluate performance. Comparative analysis involved 1,728 subjects (mean age 14.81±1.62 years; 1,013 males), with results benchmarked against manual assessments by three specialists and chronological age. Single-site evaluations demonstrated over 90% accuracy for 12-, 14-, and 16-year thresholds (wrist marginally superior to knee), while multi-site fusion improved accuracy beyond 95%, statistically outperforming isolated anatomical assessments. Although manual evaluations achieved perfect accuracy for 16-year knee classifications—aligning with BA-Net—they lagged behind automated methods in younger age groups and alternative anatomical regions. The proposed system eliminates radiation exposure while maintaining clinical-grade precision, demonstrating that coordinated analysis of wrist and knee MRI data significantly enhances bone age prediction robustness. These findings highlight the potential of multi-site deep learning integration to standardize and streamline pediatric skeletal maturity evaluations in clinical practice. Biological sciences/Developmental biology Health sciences/Anatomy Bone age assessment MRI Convolutional neural networks Multi-site epiphyseal Full Text Additional Declarations No competing interests reported. Supplementary Files SupplementaryInformation.zip 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-6599801","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":542839573,"identity":"8fea6359-4fe3-4b00-b3ba-7c6037b9f924","order_by":0,"name":"Lei Wan","email":"","orcid":"","institution":"Key Laboratory of Forensic Science, Ministry of Justice","correspondingAuthor":false,"prefix":"","firstName":"Lei","middleName":"","lastName":"Wan","suffix":""},{"id":542839576,"identity":"a61e6230-1291-42d6-a547-b207230b03d0","order_by":1,"name":"hui-ming zhou","email":"","orcid":"","institution":"Key Laboratory of Forensic Science, Ministry of Justice","correspondingAuthor":false,"prefix":"","firstName":"hui-ming","middleName":"","lastName":"zhou","suffix":""},{"id":542839580,"identity":"d8f52b0f-2170-4c8b-9bcf-dd643d06d00a","order_by":2,"name":"yuan-zhe li","email":"","orcid":"","institution":"Shanghai Shuzhiwei Information Technology Co., LTD","correspondingAuthor":false,"prefix":"","firstName":"yuan-zhe","middleName":"","lastName":"li","suffix":""},{"id":542839581,"identity":"637163b4-bdbc-46af-87d7-e74aa915245c","order_by":3,"name":"Wen-tao Xia","email":"","orcid":"","institution":"Key Laboratory of Forensic Science, Ministry of Justice","correspondingAuthor":false,"prefix":"","firstName":"Wen-tao","middleName":"","lastName":"Xia","suffix":""},{"id":542839582,"identity":"3a8fafaa-bb5a-4254-b862-58f61aae220d","order_by":4,"name":"Zhi Yan","email":"","orcid":"","institution":"Department of Science and Technology Achievement Transformation, Capital Medical University","correspondingAuthor":false,"prefix":"","firstName":"Zhi","middleName":"","lastName":"Yan","suffix":""},{"id":542839584,"identity":"038f7499-28d8-4dec-b76a-222091800dfa","order_by":5,"name":"Mao-wen Wang","email":"","orcid":"","institution":"Key Laboratory of Forensic Science, Ministry of Justice","correspondingAuthor":false,"prefix":"","firstName":"Mao-wen","middleName":"","lastName":"Wang","suffix":""},{"id":542839593,"identity":"7c38fa8f-ce9d-4d20-9f83-4aef15f8f677","order_by":6,"name":"Tai-Ang Liu","email":"","orcid":"","institution":"Shanghai Shuzhiwei Information Technology Co., LTD","correspondingAuthor":false,"prefix":"","firstName":"Tai-Ang","middleName":"","lastName":"Liu","suffix":""},{"id":542839595,"identity":"de36a0bf-4ad5-41a1-ac83-591b18a99295","order_by":7,"name":"Hong-xia Hao","email":"","orcid":"","institution":"Key Laboratory of Forensic Science, Ministry of Justice","correspondingAuthor":false,"prefix":"","firstName":"Hong-xia","middleName":"","lastName":"Hao","suffix":""},{"id":542839596,"identity":"ff2e4a73-adb7-4579-bdcd-418c7d76ce23","order_by":8,"name":"Dan-yang Li","email":"","orcid":"","institution":"Academy of Medical Sciences, Shanxi Medical University","correspondingAuthor":false,"prefix":"","firstName":"Dan-yang","middleName":"","lastName":"Li","suffix":""},{"id":542839597,"identity":"7b62c66e-09bd-4e30-8014-72a7a1d7d47e","order_by":9,"name":"Ze-yu Wang","email":"","orcid":"","institution":"Key Laboratory of Forensic Science, Ministry of Justice","correspondingAuthor":false,"prefix":"","firstName":"Ze-yu","middleName":"","lastName":"Wang","suffix":""},{"id":542839598,"identity":"ebf625b4-5fa8-4134-8857-8d00e990bf5d","order_by":10,"name":"Zheng-dong Li","email":"","orcid":"","institution":"Key Laboratory of Forensic Science, Ministry of Justice","correspondingAuthor":false,"prefix":"","firstName":"Zheng-dong","middleName":"","lastName":"Li","suffix":""},{"id":542839599,"identity":"c58460f3-7a20-49c3-84f9-dcefa50d141e","order_by":11,"name":"Ya-Hui Wang","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAArklEQVRIiWNgGAWjYLACxgYbBgbmAwYkaUljYGBLIE3LYRK0GBw/e/g1747z9vJtzBsYfu4gRsuZvDRr3jO3EzccYytg7D1DhBazAzlmxrxttxMM5HsMmBnbiNFy/g1Iyzmgw3iI1XIjx/gxb9sBxoZjxGqxv/HGjHFuWzLYLwd7idEi2Z9j/OFtmx0oxDY++EmMFiBgk+KBsg4QpwGYUj7+IFbpKBgFo2AUjEwAACmhN9e3CIPjAAAAAElFTkSuQmCC","orcid":"","institution":"Key Laboratory of Forensic Science, Ministry of Justice","correspondingAuthor":true,"prefix":"","firstName":"Ya-Hui","middleName":"","lastName":"Wang","suffix":""}],"badges":[],"createdAt":"2025-05-06 06:53:32","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6599801/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6599801/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":102295569,"identity":"0bd467cf-d705-4874-9b9d-f5dfb4fef022","added_by":"auto","created_at":"2026-02-10 10:12:43","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":830185,"visible":true,"origin":"","legend":"","description":"","filename":"scientificreportmanuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6599801/v1_covered_602e7e7e-f367-44cc-861c-9a4e3931e228.pdf"},{"id":95770523,"identity":"d2556fb5-6a3e-4f20-b7f8-cd55f0658c9b","added_by":"auto","created_at":"2025-11-12 22:36:30","extension":"zip","order_by":0,"title":"","display":"","copyAsset":false,"role":"supplement","size":5154564,"visible":true,"origin":"","legend":"","description":"","filename":"SupplementaryInformation.zip","url":"https://assets-eu.researchsquare.com/files/rs-6599801/v1/174feb47c1b7d148407aac74.zip"}],"financialInterests":"No competing interests reported.","formattedTitle":"Deep Learning-Based Bone Age Assessment Using Multi-Site MRI Epiphyseal Imaging: A Retrospective Study","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":"Bone age assessment, MRI, Convolutional neural networks, Multi-site epiphyseal","lastPublishedDoi":"10.21203/rs.3.rs-6599801/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6599801/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"This study presents BA-Net, a deep learning framework designed to automate juvenile bone age assessment by analyzing epiphyseal union patterns across wrist and knee MRI scans. Leveraging 474 axial wrist, 1,149 coronal knee, and 105 combined wrist-knee T1-weighted MRI scans collected between 2015 and 2021, the model integrates convolutional neural networks to extract multidimensional skeletal features and sex-specific parameters for multi-label classification. Data were partitioned into training, validation, and test sets to evaluate performance. Comparative analysis involved 1,728 subjects (mean age 14.81±1.62 years; 1,013 males), with results benchmarked against manual assessments by three specialists and chronological age. Single-site evaluations demonstrated over 90% accuracy for 12-, 14-, and 16-year thresholds (wrist marginally superior to knee), while multi-site fusion improved accuracy beyond 95%, statistically outperforming isolated anatomical assessments. Although manual evaluations achieved perfect accuracy for 16-year knee classifications—aligning with BA-Net—they lagged behind automated methods in younger age groups and alternative anatomical regions. The proposed system eliminates radiation exposure while maintaining clinical-grade precision, demonstrating that coordinated analysis of wrist and knee MRI data significantly enhances bone age prediction robustness. These findings highlight the potential of multi-site deep learning integration to standardize and streamline pediatric skeletal maturity evaluations in clinical practice.","manuscriptTitle":"Deep Learning-Based Bone Age Assessment Using Multi-Site MRI Epiphyseal Imaging: A Retrospective Study","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-11-12 22:36:25","doi":"10.21203/rs.3.rs-6599801/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":"63311a0d-0192-407f-aa83-881561307874","owner":[],"postedDate":"November 12th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":57747658,"name":"Biological sciences/Developmental biology"},{"id":57747659,"name":"Health sciences/Anatomy"}],"tags":[],"updatedAt":"2026-02-06T12:41:45+00:00","versionOfRecord":[],"versionCreatedAt":"2025-11-12 22:36:25","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-6599801","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6599801","identity":"rs-6599801","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}