Machine learning-based MRI radiomics identifies patients with degenerative cervical myelopathy and predicts baseline function

Machine learning-based MRI radiomics identifies patients with degenerative cervical myelopathy and predicts baseline function | 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 Machine learning-based MRI radiomics identifies patients with degenerative cervical myelopathy and predicts baseline function Ramesh M. Arnest, Kevin M. Koch, Matthew D. Budde, Anjishnu Banerjee, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7686194/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 7 You are reading this latest preprint version Abstract Purpose The diagnosis of Degenerative cervical myelopathy (DCM) relies on clinical evaluation and conventional MRI, yet early symptoms are subtle and non-specific, creating diagnostic uncertainty. High rates of asymptomatic cervical spinal cord compression in the older adults further complicate clinical decisions regarding surgical intervention. MRI-based radiomic analysis quantifies microstructural spinal cord pathology through texture analysis, and is a potential objective imaging biomarker. This study aimed to assess whether machine learning models using MRI radiomics can accurately classify DCM and predict disease severity. We also aim to evaluate the impact of imaging resolution on diagnostic performance. Methods We included 79 patients with clinically diagnosed DCM undergoing surgical evaluation and 51 healthy controls. Participants underwent high-resolution 3D T2-weighted MRI. Images were processed using automated spinal cord segmentation, and radiomic features were extracted using the Pyradiomics software package and filtered by correlation, variance, ANOVA, and mutual information analyses. Machine learning algorithms (XGBoost, CatBoost, LightGBM, Random Forest, SVM) underwent hyperparameter optimization with Optuna and were evaluated using 5-fold cross-validation and independent validation sets. Results Machine learning using MRI radiomics discriminated DCM from healthy controls with high accuracy (validation set AUROC = 0.93, accuracy = 0.88, F1-score = 0.90, MCC = 0.76, Precision = 93.3%, sensitivity = 87.5%, specificity = 90%). Radiomic features from high-resolution 3D MRI showed superior diagnostic performance compared to standard MRI and conventional morphometry. The models effectively classified disease severity (macro-average AUROC = 0.855 ± 0.062), significantly outperforming traditional imaging measures. Conclusion MRI-based radiomics combined with machine learning demonstrates robust accuracy in predicting DCM status and estimating disease severity, independent of clinical or demographic data. These findings underscore the potential of MRI radiomics as an objective imaging biomarker to screen for DCM. Future validation using larger, multi-vendor datasets is critical for broader clinical application. Degenerative cervical myelopathy (DCM) MRI radiomics Machine Learning Spinal Cord Compression Imaging Biomarkers Neurological Function Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Editorial decision: Revision requested 07 Apr, 2026 Reviews received at journal 10 Nov, 2025 Reviewers agreed at journal 05 Nov, 2025 Reviewers invited by journal 03 Nov, 2025 Editor assigned by journal 24 Sep, 2025 Submission checks completed at journal 24 Sep, 2025 First submitted to journal 22 Sep, 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-7686194","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":543087450,"identity":"ccd8ff33-b091-4b32-afbf-51724c95c234","order_by":0,"name":"Ramesh M. Arnest","email":"","orcid":"","institution":"Medical College of Wisconsin","correspondingAuthor":false,"prefix":"","firstName":"Ramesh","middleName":"M.","lastName":"Arnest","suffix":""},{"id":543087451,"identity":"24be4c58-7645-4b7c-ae6c-08ddc60221b0","order_by":1,"name":"Kevin M. Koch","email":"","orcid":"","institution":"Hospital for Special Surgery","correspondingAuthor":false,"prefix":"","firstName":"Kevin","middleName":"M.","lastName":"Koch","suffix":""},{"id":543087452,"identity":"c21c4d84-6ad5-467c-8d23-ebe491b56429","order_by":2,"name":"Matthew D. Budde","email":"","orcid":"","institution":"Medical College of Wisconsin","correspondingAuthor":false,"prefix":"","firstName":"Matthew","middleName":"D.","lastName":"Budde","suffix":""},{"id":543087453,"identity":"0388df6d-3360-4f81-b532-10bb5246a280","order_by":3,"name":"Anjishnu Banerjee","email":"","orcid":"","institution":"Medical College of Wisconsin","correspondingAuthor":false,"prefix":"","firstName":"Anjishnu","middleName":"","lastName":"Banerjee","suffix":""},{"id":543087454,"identity":"1145f5f5-163e-40f2-b260-cd0f15a723a7","order_by":4,"name":"Aditya Vedantam","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAwklEQVRIiWNgGAWjYJACCTDJ3gCmGBuI1GLAwMBzgGQtEglEauGfkXzwxs8df+R1Z75O/MzDYCO74QAhG26kJVv2njEw3HY7d7M0D0OaMUEtDGfOmEnwthkwArVsY85hOJxIUIv8mfPfJP+2Gdhvu3kWpOU/YS0Gx3vYpIG2JG67wQvScoCwFsPjbcbWsm3GydvOAP3yxyDZeCYhLXKHmR/efNsmZ7vt+NmNH2dU2Mn2EdKC7k7SlI+CUTAKRsEowAEA0NhGkct3GfEAAAAASUVORK5CYII=","orcid":"","institution":"Medical College of Wisconsin","correspondingAuthor":true,"prefix":"","firstName":"Aditya","middleName":"","lastName":"Vedantam","suffix":""}],"badges":[],"createdAt":"2025-09-23 01:08:42","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7686194/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7686194/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":95802115,"identity":"e10dfdb9-0c4c-4e83-9608-ab0f7600b774","added_by":"auto","created_at":"2025-11-13 08:26:56","extension":"docx","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":2062841,"visible":true,"origin":"","legend":"","description":"","filename":"RadiomicsManuscriptformatted.docx","url":"https://assets-eu.researchsquare.com/files/rs-7686194/v1/339f35a31bc9d99714d7279b.docx"},{"id":95800848,"identity":"4864e5cc-7956-46ed-954e-83695a88cb6c","added_by":"auto","created_at":"2025-11-13 08:23:43","extension":"json","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":7469,"visible":true,"origin":"","legend":"","description":"","filename":"14ebb1c42a9a401bab44320419ca31c4.json","url":"https://assets-eu.researchsquare.com/files/rs-7686194/v1/aa7066940d1d039ceda8cdee.json"},{"id":95764774,"identity":"f75c129e-4885-46e8-800b-19bd0e20ea03","added_by":"auto","created_at":"2025-11-12 19:15:42","extension":"xml","order_by":2,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":80218,"visible":true,"origin":"","legend":"","description":"","filename":"14ebb1c42a9a401bab44320419ca31c41enriched.xml","url":"https://assets-eu.researchsquare.com/files/rs-7686194/v1/f892be04335f6cb9486ed0ab.xml"},{"id":95802516,"identity":"810fc5bd-b71d-4448-a89e-d215c40c22cb","added_by":"auto","created_at":"2025-11-13 08:27:45","extension":"jpeg","order_by":3,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":322468,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage1.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-7686194/v1/8613858a78850f2f0fff7ef3.jpeg"},{"id":95800882,"identity":"0574fe25-9cb8-48fc-9612-5da1ce678f22","added_by":"auto","created_at":"2025-11-13 08:23:48","extension":"jpeg","order_by":4,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":184752,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage2.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-7686194/v1/7bc643efff71d76feecdd7b7.jpeg"},{"id":95764765,"identity":"ff885a0f-2792-4623-8557-aa36976a91bd","added_by":"auto","created_at":"2025-11-12 19:15:41","extension":"jpeg","order_by":5,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":563414,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage3.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-7686194/v1/4ee6bd7c523f819c1993e8fc.jpeg"},{"id":95764767,"identity":"adcb5731-44ad-4bd1-ba32-0c70ed841049","added_by":"auto","created_at":"2025-11-12 19:15:41","extension":"jpeg","order_by":6,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":535386,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage4.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-7686194/v1/631c12ae0a8fd94e020708c2.jpeg"},{"id":95801902,"identity":"f0b74589-df2f-40a5-bcc5-32fc55ec297c","added_by":"auto","created_at":"2025-11-13 08:26:25","extension":"jpeg","order_by":7,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":373166,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage5.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-7686194/v1/06c0d1e4f898f0f681c660eb.jpeg"},{"id":95801941,"identity":"214c46ee-c510-43f4-a548-429cd836e0da","added_by":"auto","created_at":"2025-11-13 08:26:29","extension":"png","order_by":8,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":58959,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-7686194/v1/99cd222c2662cf63817142df.png"},{"id":95764768,"identity":"1e1c5cf7-6e8a-4449-854c-b367591a3d9a","added_by":"auto","created_at":"2025-11-12 19:15:42","extension":"png","order_by":9,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":21517,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-7686194/v1/1bee963fc2a72309907633f2.png"},{"id":95764777,"identity":"a5256ae9-d4c2-4c2c-b20f-e15db4c24ad8","added_by":"auto","created_at":"2025-11-12 19:15:42","extension":"png","order_by":10,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":69166,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage3.png","url":"https://assets-eu.researchsquare.com/files/rs-7686194/v1/087383ecb38acc29e09dc45f.png"},{"id":95764772,"identity":"94a860c3-d85e-4767-a1e3-93c2e19e76cd","added_by":"auto","created_at":"2025-11-12 19:15:42","extension":"png","order_by":11,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":69584,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage4.png","url":"https://assets-eu.researchsquare.com/files/rs-7686194/v1/3101160a2e54917002379d1e.png"},{"id":95764776,"identity":"2bbfa256-bd76-406d-8ead-754b4aa37a59","added_by":"auto","created_at":"2025-11-12 19:15:42","extension":"png","order_by":12,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":48436,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage5.png","url":"https://assets-eu.researchsquare.com/files/rs-7686194/v1/aecca4232bd5c13280e9730e.png"},{"id":95764779,"identity":"d60aaecc-899a-4f18-add1-99c6e7641e3c","added_by":"auto","created_at":"2025-11-12 19:15:42","extension":"xml","order_by":13,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":78793,"visible":true,"origin":"","legend":"","description":"","filename":"14ebb1c42a9a401bab44320419ca31c41structuring.xml","url":"https://assets-eu.researchsquare.com/files/rs-7686194/v1/6f6b47e0817f9d9162038e18.xml"},{"id":95764778,"identity":"db898712-a612-48c0-b379-c364a2d386e4","added_by":"auto","created_at":"2025-11-12 19:15:42","extension":"html","order_by":14,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":84311,"visible":true,"origin":"","legend":"","description":"","filename":"earlyproof.html","url":"https://assets-eu.researchsquare.com/files/rs-7686194/v1/65a11aae928fd42dcab2b43b.html"},{"id":95818821,"identity":"a0bdeb4e-a166-4fdc-8357-f84b2e205cc7","added_by":"auto","created_at":"2025-11-13 10:33:56","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":804373,"visible":true,"origin":"","legend":"","description":"","filename":"RadiomicsManuscriptformatted.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7686194/v1_covered_fd463f32-3a2f-4e27-8d9e-aa45f401856b.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Machine learning-based MRI radiomics identifies patients with degenerative cervical myelopathy and predicts baseline function","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":"european-spine-journal","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"esjo","sideBox":"Learn more about [European Spine Journal](http://link.springer.com/journal/586)","snPcode":"586","submissionUrl":"https://submission.springernature.com/new-submission/586/3","title":"European Spine Journal","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Degenerative cervical myelopathy (DCM), MRI radiomics, Machine Learning, Spinal Cord Compression, Imaging Biomarkers, Neurological Function","lastPublishedDoi":"10.21203/rs.3.rs-7686194/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7686194/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003ch2\u003ePurpose\u003c/h2\u003e\u003cp\u003eThe diagnosis of Degenerative cervical myelopathy (DCM) relies on clinical evaluation and conventional MRI, yet early symptoms are subtle and non-specific, creating diagnostic uncertainty. High rates of asymptomatic cervical spinal cord compression in the older adults further complicate clinical decisions regarding surgical intervention. MRI-based radiomic analysis quantifies microstructural spinal cord pathology through texture analysis, and is a potential objective imaging biomarker. This study aimed to assess whether machine learning models using MRI radiomics can accurately classify DCM and predict disease severity. We also aim to evaluate the impact of imaging resolution on diagnostic performance.\u003c/p\u003e\u003ch2\u003eMethods\u003c/h2\u003e\u003cp\u003eWe included 79 patients with clinically diagnosed DCM undergoing surgical evaluation and 51 healthy controls. Participants underwent high-resolution 3D T2-weighted MRI. Images were processed using automated spinal cord segmentation, and radiomic features were extracted using the Pyradiomics software package and filtered by correlation, variance, ANOVA, and mutual information analyses. Machine learning algorithms (XGBoost, CatBoost, LightGBM, Random Forest, SVM) underwent hyperparameter optimization with Optuna and were evaluated using 5-fold cross-validation and independent validation sets.\u003c/p\u003e\u003ch2\u003eResults\u003c/h2\u003e\u003cp\u003eMachine learning using MRI radiomics discriminated DCM from healthy controls with high accuracy (validation set AUROC\u0026thinsp;=\u0026thinsp;0.93, accuracy\u0026thinsp;=\u0026thinsp;0.88, F1-score\u0026thinsp;=\u0026thinsp;0.90, MCC\u0026thinsp;=\u0026thinsp;0.76, Precision\u0026thinsp;=\u0026thinsp;93.3%, sensitivity\u0026thinsp;=\u0026thinsp;87.5%, specificity\u0026thinsp;=\u0026thinsp;90%). Radiomic features from high-resolution 3D MRI showed superior diagnostic performance compared to standard MRI and conventional morphometry. The models effectively classified disease severity (macro-average AUROC\u0026thinsp;=\u0026thinsp;0.855\u0026thinsp;\u0026plusmn;\u0026thinsp;0.062), significantly outperforming traditional imaging measures.\u003c/p\u003e\u003ch2\u003eConclusion\u003c/h2\u003e\u003cp\u003eMRI-based radiomics combined with machine learning demonstrates robust accuracy in predicting DCM status and estimating disease severity, independent of clinical or demographic data. These findings underscore the potential of MRI radiomics as an objective imaging biomarker to screen for DCM. Future validation using larger, multi-vendor datasets is critical for broader clinical application.\u003c/p\u003e","manuscriptTitle":"Machine learning-based MRI radiomics identifies patients with degenerative cervical myelopathy and predicts baseline function","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-11-12 19:15:37","doi":"10.21203/rs.3.rs-7686194/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2026-04-07T06:23:45+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-11-10T14:32:26+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"321089264401313566039066666428386652245","date":"2025-11-05T15:43:01+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-11-03T05:16:33+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-09-25T03:53:52+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-09-25T01:50:38+00:00","index":"","fulltext":""},{"type":"submitted","content":"European Spine Journal","date":"2025-09-22T15:26:24+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"european-spine-journal","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"esjo","sideBox":"Learn more about [European Spine Journal](http://link.springer.com/journal/586)","snPcode":"586","submissionUrl":"https://submission.springernature.com/new-submission/586/3","title":"European Spine Journal","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"7fbca793-173f-4968-b72a-90afbd4a8b9a","owner":[],"postedDate":"November 12th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2026-05-23T05:53:52+00:00","versionOfRecord":[],"versionCreatedAt":"2025-11-12 19:15:37","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7686194","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7686194","identity":"rs-7686194","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}