Clinically Interpretable Deep Learning Model for Bone Age Estimation Based on TW3 Scoring

Clinically Interpretable Deep Learning Model for Bone Age Estimation Based on TW3 Scoring | 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 Research Article Clinically Interpretable Deep Learning Model for Bone Age Estimation Based on TW3 Scoring Haixin Wei, Ruochen Wu, Ziyue Zhang, Panchen Zhao, Jianwei Guo, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6717646/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 Background Bone age assessment (BAA) is challenging in clinical practice due to the complicated bone age assessment process. We aim to develop a deep learning-based system to fully automate the assessment of bone age using pediatric hand radiographs, similar to a radiologist’s workflow using the Tanner-Whitehouse 3 method (TW3) method. Methods We present a new experimental framework. The framework consists of three parts. One is hand detection. In this module, a deep convolution object detection object is used to detect the left hand in the image, orientation is also detected. In the key-points detection module, another deep convolution key-point detection network is used to localize the region of interest (ROI) in the hand and get the corresponding maturity levels. Finally, we designed a bone age computer based on TW3 method to determine the final bone age. Results A total of 1309 subjects were enrolled in the study, and 241 subjects were divided into test set. The accuracy of orientation classification on the test set is 100%. The mean absolute error (MAE) of predicted radius, ulna, short bone (RUC) age and Carpal bone age were 0.35 and 0.55 respectively. In addition, the AUC of the remaining maturity level for all bone maturity assessment reached at least 0.85. Conclusion Compared with other automatic bone age assessment methods, our framework shows competitive performance with low model complexity and excellent interpretability. Our framework can deal with different noises and provide a reliable result. Automatic bone age assessment 1 Deep learning 2 Neural network 3 Image processing 4 Tanner-Whitehouse method 5 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-6717646","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":466200483,"identity":"c27ba7de-e241-4012-8f5a-e5781dcc724a","order_by":0,"name":"Haixin Wei","email":"","orcid":"","institution":"Affiliated Hospital of Qingdao University","correspondingAuthor":false,"prefix":"","firstName":"Haixin","middleName":"","lastName":"Wei","suffix":""},{"id":466200485,"identity":"f5f3c4a7-036c-46dc-9c63-910506ef572d","order_by":1,"name":"Ruochen Wu","email":"","orcid":"","institution":"Affiliated Hospital of Qingdao University","correspondingAuthor":false,"prefix":"","firstName":"Ruochen","middleName":"","lastName":"Wu","suffix":""},{"id":466200487,"identity":"e0f4e943-63de-446b-9310-d858466cf5fc","order_by":2,"name":"Ziyue Zhang","email":"","orcid":"","institution":"Qingdao Central Hospital","correspondingAuthor":false,"prefix":"","firstName":"Ziyue","middleName":"","lastName":"Zhang","suffix":""},{"id":466200490,"identity":"bdcf57e6-ecff-4996-8045-816e77560bc3","order_by":3,"name":"Panchen Zhao","email":"","orcid":"","institution":"Affiliated Hospital of Qingdao University","correspondingAuthor":false,"prefix":"","firstName":"Panchen","middleName":"","lastName":"Zhao","suffix":""},{"id":466200493,"identity":"facfb016-3c5e-44ac-ad72-eca2d1ee40cf","order_by":4,"name":"Jianwei Guo","email":"","orcid":"","institution":"Affiliated Hospital of Qingdao University","correspondingAuthor":false,"prefix":"","firstName":"Jianwei","middleName":"","lastName":"Guo","suffix":""},{"id":466200497,"identity":"40be62df-8f23-47a1-91db-26e6722cae16","order_by":5,"name":"Xuexiao Ma","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA8ElEQVRIiWNgGAWjYPACCTB5gIHBQo6Nvf0ASVokjPl4ziSQZl3iPAkHA7xKdNvPmEl8bLOQ5+c/e/BwQY1EepsEQwLDj4ptOLWYnUlLk5xxRsJw5oy8hMMzjknktkk3HmDsOXMbt5YDycekeSokGDfc4DE4zMMG1CJzIIGZsQ2PlvMP26T/GEjYbzh/Bqjln0Q6m0SCAX4tN4C2MFRIJG44kGNwmLdNIoEILc+SLXvOSCSD/cLbJ2HYBgzkg3j9cj7H8MbPtjrbfv6zhz/zfLORl29vP/jgRwVuLUiAB8E8QIx6VC2jYBSMglEwCpABAPSCVoJJqYaRAAAAAElFTkSuQmCC","orcid":"","institution":"Affiliated Hospital of Qingdao University","correspondingAuthor":true,"prefix":"","firstName":"Xuexiao","middleName":"","lastName":"Ma","suffix":""}],"badges":[],"createdAt":"2025-05-21 14:53:20","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6717646/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6717646/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":85783547,"identity":"d4414a64-1ea0-46e5-85ce-ecb430101c2c","added_by":"auto","created_at":"2025-07-01 15:38:44","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":909759,"visible":true,"origin":"","legend":"","description":"","filename":"ManuscriptClinicallyInterpretableDeepLearningModelforBoneAgeEstimationBasedonTW3Scoring.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6717646/v1_covered_2d669a06-6f6c-47de-8a3f-a34e306d4b86.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Clinically Interpretable Deep Learning Model for Bone Age Estimation Based on TW3 Scoring","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":"Automatic bone age assessment 1, Deep learning 2, Neural network 3, Image processing 4, Tanner-Whitehouse method 5","lastPublishedDoi":"10.21203/rs.3.rs-6717646/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6717646/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003ch2\u003eBackground\u003c/h2\u003e \u003cp\u003eBone age assessment (BAA) is challenging in clinical practice due to the complicated bone age assessment process. We aim to develop a deep learning-based system to fully automate the assessment of bone age using pediatric hand radiographs, similar to a radiologist\u0026rsquo;s workflow using the Tanner-Whitehouse 3 method (TW3) method.\u003c/p\u003e\u003ch2\u003eMethods\u003c/h2\u003e \u003cp\u003eWe present a new experimental framework. The framework consists of three parts. One is hand detection. In this module, a deep convolution object detection object is used to detect the left hand in the image, orientation is also detected. In the key-points detection module, another deep convolution key-point detection network is used to localize the region of interest (ROI) in the hand and get the corresponding maturity levels. Finally, we designed a bone age computer based on TW3 method to determine the final bone age.\u003c/p\u003e\u003ch2\u003eResults\u003c/h2\u003e \u003cp\u003eA total of 1309 subjects were enrolled in the study, and 241 subjects were divided into test set. The accuracy of orientation classification on the test set is 100%. The mean absolute error (MAE) of predicted radius, ulna, short bone (RUC) age and Carpal bone age were 0.35 and 0.55 respectively. In addition, the AUC of the remaining maturity level for all bone maturity assessment reached at least 0.85.\u003c/p\u003e\u003ch2\u003eConclusion\u003c/h2\u003e \u003cp\u003eCompared with other automatic bone age assessment methods, our framework shows competitive performance with low model complexity and excellent interpretability. Our framework can deal with different noises and provide a reliable result.\u003c/p\u003e","manuscriptTitle":"Clinically Interpretable Deep Learning Model for Bone Age Estimation Based on TW3 Scoring","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-06-06 12:47:42","doi":"10.21203/rs.3.rs-6717646/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":"01aa9a39-503e-4676-98e1-42262bcbc87b","owner":[],"postedDate":"June 6th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2025-07-01T15:38:33+00:00","versionOfRecord":[],"versionCreatedAt":"2025-06-06 12:47:42","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-6717646","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6717646","identity":"rs-6717646","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}