Construction of segmentation and classification models for spinal tuberculosis lesions Based on CT: A multi-center study

Construction of segmentation and classification models for spinal tuberculosis lesions Based on CT: A multi-center 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 Construction of segmentation and classification models for spinal tuberculosis lesions Based on CT: A multi-center study Sen Mo, Chong Liu, Jiang Xue, Jiarui Chen, Hao Li, Zhaojun Lu, and 7 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7888539/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 5 You are reading this latest preprint version Abstract Purpose To establish a segmentation model and classification model of tuberculosis lesions based on CT images to improve the accuracy of early diagnosis of spinal tuberculosis. Methods This study adopted multicenter retrospective data (n = 1025). Firstly, the vertebral body region of the spine was extracted through the U-Net segmentation model. Then, the segmented images were input into the improved ResNet50 network. Combined with the CT bone window gradient attention mechanism, an end-to-end deep learning diagnostic model was constructed. Results In the internal validation datasets, the model achieved an AUC of 0.920, accuracy of 0.874, and sensitivity of 0.876. For External test datasets 1, the AUC was 0.867, accuracy 0.801, and sensitivity 0.794; for External test datasets 2, the AUC was 0.866, accuracy 0.769, and sensitivity 0.883; and for External test datasets 3, the AUC was 0.941, accuracy 0.843, and sensitivity 0.790. Conclusion The multi-center study built up a deep learning model for spinal tuberculosis diagnosis with the assist of the CT bone window gradient attention mechanism. The model achieved a good internal verification ability (AUC = 0.920, accuracy rate = 0.874) and external verification ability (AUC = 0.866–0.941,accuracy rate = 0.769–0.843) which showed the wide applicability of the model to different medical institutions.The main developments of this work are good performances for features that extract relevant information about trabecular micro-fractures and calcification contours’ gradients. Biological sciences/Computational biology and bioinformatics Health sciences/Diseases Health sciences/Health care Physical sciences/Mathematics and computing Health sciences/Medical research Vertebral body segmentation CT bone window Deep learning Tuberculosis of spine Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Reviewers invited by journal 12 Feb, 2026 Editor invited by journal 22 Oct, 2025 Editor assigned by journal 17 Oct, 2025 Submission checks completed at journal 17 Oct, 2025 First submitted to journal 17 Oct, 2025 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-7888539","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":590760110,"identity":"53c5b242-1a9f-4c76-9785-97be1143321c","order_by":0,"name":"Sen Mo","email":"","orcid":"","institution":"The First Affiliated Hospital of Guangxi Medical University","correspondingAuthor":false,"prefix":"","firstName":"Sen","middleName":"","lastName":"Mo","suffix":""},{"id":590760111,"identity":"b6c3286e-b486-4623-9bd1-6ee8c2a361fe","order_by":1,"name":"Chong Liu","email":"","orcid":"","institution":"The First Affiliated Hospital of Guangxi Medical University","correspondingAuthor":false,"prefix":"","firstName":"Chong","middleName":"","lastName":"Liu","suffix":""},{"id":590760112,"identity":"403cfc94-fbc1-4bcb-afec-1eca7cbfd988","order_by":2,"name":"Jiang Xue","email":"","orcid":"","institution":"The First Affiliated Hospital of Guangxi Medical University","correspondingAuthor":false,"prefix":"","firstName":"Jiang","middleName":"","lastName":"Xue","suffix":""},{"id":590760113,"identity":"0c11a87c-5856-4a88-9a10-ad98b313a087","order_by":3,"name":"Jiarui Chen","email":"","orcid":"","institution":"The First Affiliated Hospital of Guangxi Medical University","correspondingAuthor":false,"prefix":"","firstName":"Jiarui","middleName":"","lastName":"Chen","suffix":""},{"id":590760114,"identity":"c96b9a59-29aa-4b1d-82bb-417b31153e90","order_by":4,"name":"Hao Li","email":"","orcid":"","institution":"The First Affiliated Hospital of Guangxi Medical University","correspondingAuthor":false,"prefix":"","firstName":"Hao","middleName":"","lastName":"Li","suffix":""},{"id":590760115,"identity":"00949a69-d8bc-4df0-b247-030e53514e9a","order_by":5,"name":"Zhaojun Lu","email":"","orcid":"","institution":"The First Affiliated Hospital of Guangxi Medical University","correspondingAuthor":false,"prefix":"","firstName":"Zhaojun","middleName":"","lastName":"Lu","suffix":""},{"id":590760116,"identity":"7077891d-ccde-4b88-9c2d-32d712f497e6","order_by":6,"name":"Zhongxian Zhou","email":"","orcid":"","institution":"The First Affiliated Hospital of Guangxi Medical University","correspondingAuthor":false,"prefix":"","firstName":"Zhongxian","middleName":"","lastName":"Zhou","suffix":""},{"id":590760117,"identity":"c5586f80-e411-4db0-a6fb-343fc1d79c01","order_by":7,"name":"Xiaopeng Qin","email":"","orcid":"","institution":"The First Affiliated Hospital of Guangxi Medical University","correspondingAuthor":false,"prefix":"","firstName":"Xiaopeng","middleName":"","lastName":"Qin","suffix":""},{"id":590760118,"identity":"ea2be05a-b502-409c-92e9-9b5896c7c2ff","order_by":8,"name":"Rongqing He","email":"","orcid":"","institution":"The First Affiliated Hospital of Guangxi Medical University","correspondingAuthor":false,"prefix":"","firstName":"Rongqing","middleName":"","lastName":"He","suffix":""},{"id":590760119,"identity":"f46aa1ab-98af-40d1-b590-d451011d6fd6","order_by":9,"name":"Boli Qin","email":"","orcid":"","institution":"The First Affiliated Hospital of Guangxi Medical University","correspondingAuthor":false,"prefix":"","firstName":"Boli","middleName":"","lastName":"Qin","suffix":""},{"id":590760120,"identity":"289afe44-0e2e-47c2-a322-06ecb84f59ce","order_by":10,"name":"Yahui Huang","email":"","orcid":"","institution":"Nanning Fourth People's Hospital","correspondingAuthor":false,"prefix":"","firstName":"Yahui","middleName":"","lastName":"Huang","suffix":""},{"id":590760121,"identity":"c7864c84-215c-487f-8b99-a6f0926ead19","order_by":11,"name":"Wei Wei","email":"","orcid":"","institution":"Wuming Hospital Affiliated to Guangxi Medical University","correspondingAuthor":false,"prefix":"","firstName":"Wei","middleName":"","lastName":"Wei","suffix":""},{"id":590760122,"identity":"f52c18b3-23bb-4346-95b0-73e1290d6262","order_by":12,"name":"Xinli Zhan","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABAklEQVRIiWNgGAWjYDACCRBhwCDDxt6AJMpDhBYeNp4DjAhNhLWA1EgkEKlFfnbzs8c8BXd4+CSfP3/Mw1CbuHZGAuODt20M8uY4tDDOOWZuOMPgGQ+bdI5hMw/DcWOzGwnMhnPbGAx3NmDXwiyRYCbxweAwSAsjUMsxOaAWNmneNoYEgwPYtbBJpH+TSABpkTz+EKSFB6iF/Tc+LTwSOVBbJBhADqsB28KMT4uERE6Z5AyQFp4cw5lzDA4Ym5152Cw555yE4QYcWuRnpG+T5vlzWE6+/fiDD28q6hK3HU8++OFNmY08LlvQgMFhIAGOHwmi1INAHdEqR8EoGAWjYOQAAGu/UZIxkBQzAAAAAElFTkSuQmCC","orcid":"","institution":"The First Affiliated Hospital of Guangxi Medical University","correspondingAuthor":true,"prefix":"","firstName":"Xinli","middleName":"","lastName":"Zhan","suffix":""}],"badges":[],"createdAt":"2025-10-17 16:38:15","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7888539/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7888539/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":102944121,"identity":"7faea41e-8f60-4dde-ac8c-ab7de0f2de66","added_by":"auto","created_at":"2026-02-18 17:54:56","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":866362,"visible":true,"origin":"","legend":"","description":"","filename":"revisedmanuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7888539/v1_covered_af16fff1-1eda-4ec1-acb6-7be4a1ac6a4d.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Construction of segmentation and classification models for spinal tuberculosis lesions Based on CT: A multi-center study","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"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":"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":"Vertebral body segmentation, CT bone window, Deep learning, Tuberculosis of spine","lastPublishedDoi":"10.21203/rs.3.rs-7888539/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7888539/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003e\u003cb\u003ePurpose\u003c/b\u003e\u003c/p\u003e \u003cp\u003eTo establish a segmentation model and classification model of tuberculosis lesions based on CT images to improve the accuracy of early diagnosis of spinal tuberculosis.\u003c/p\u003e\u003cp\u003e\u003cb\u003eMethods\u003c/b\u003e\u003c/p\u003e \u003cp\u003eThis study adopted multicenter retrospective data (n\u0026thinsp;=\u0026thinsp;1025). Firstly, the vertebral body region of the spine was extracted through the U-Net segmentation model. Then, the segmented images were input into the improved ResNet50 network. Combined with the CT bone window gradient attention mechanism, an end-to-end deep learning diagnostic model was constructed.\u003c/p\u003e\u003cp\u003e\u003cb\u003eResults\u003c/b\u003e\u003c/p\u003e \u003cp\u003eIn the internal validation datasets, the model achieved an AUC of 0.920, accuracy of 0.874, and sensitivity of 0.876. For External test datasets 1, the AUC was 0.867, accuracy 0.801, and sensitivity 0.794; for External test datasets 2, the AUC was 0.866, accuracy 0.769, and sensitivity 0.883; and for External test datasets 3, the AUC was 0.941, accuracy 0.843, and sensitivity 0.790.\u003c/p\u003e\u003cp\u003e\u003cb\u003eConclusion\u003c/b\u003e\u003c/p\u003e \u003cp\u003eThe multi-center study built up a deep learning model for spinal tuberculosis diagnosis with the assist of the CT bone window gradient attention mechanism. The model achieved a good internal verification ability (AUC\u0026thinsp;=\u0026thinsp;0.920, accuracy rate\u0026thinsp;=\u0026thinsp;0.874) and external verification ability (AUC\u0026thinsp;=\u0026thinsp;0.866\u0026ndash;0.941,accuracy rate\u0026thinsp;=\u0026thinsp;0.769\u0026ndash;0.843) which showed the wide applicability of the model to different medical institutions.The main developments of this work are good performances for features that extract relevant information about trabecular micro-fractures and calcification contours\u0026rsquo; gradients.\u003c/p\u003e","manuscriptTitle":"Construction of segmentation and classification models for spinal tuberculosis lesions Based on CT: A multi-center study","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-02-18 17:54:24","doi":"10.21203/rs.3.rs-7888539/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"reviewersInvited","content":"","date":"2026-02-13T04:56:44+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2025-10-22T13:54:22+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-10-18T03:09:29+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-10-18T03:09:12+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2025-10-17T16:32:39+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":"3f24285f-bcd9-4fee-9285-6ee585126810","owner":[],"postedDate":"February 18th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[{"id":62864826,"name":"Biological sciences/Computational biology and bioinformatics"},{"id":62864827,"name":"Health sciences/Diseases"},{"id":62864828,"name":"Health sciences/Health care"},{"id":62864829,"name":"Physical sciences/Mathematics and computing"},{"id":62864830,"name":"Health sciences/Medical research"}],"tags":[],"updatedAt":"2026-02-18T17:54:25+00:00","versionOfRecord":[],"versionCreatedAt":"2026-02-18 17:54:24","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7888539","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7888539","identity":"rs-7888539","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}