AsymmetryNet: A Clinically Inspired Asymmetry Attention Model for Predicting HPV Status in Oropharyngeal Squamous Cell Carcinoma on Computed Tomography

AsymmetryNet: A Clinically Inspired Asymmetry Attention Model for Predicting HPV Status in Oropharyngeal Squamous Cell Carcinoma on Computed Tomography | 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 AsymmetryNet: A Clinically Inspired Asymmetry Attention Model for Predicting HPV Status in Oropharyngeal Squamous Cell Carcinoma on Computed Tomography John D. Mayfield, M.D. Ph.D. M.Sc., Elly Arizono, M.D., Karen Buch, M.D., and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8979142/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 Accurate, non-invasive HPV status prediction in oropharyngeal squamous cell carcinoma (OPSCC) is essential for risk stratification and treatment planning, yet current imaging methods lack sufficient sensitivity. We developed a novel framework combining 3D Masked Autoencoder (MAE) self-supervised learning (SSL) pretraining on a Swin Transformer encoder with 33 slice-aggregated asymmetry features (airway effacement, mass effect, midline shift, hypodensity metrics). In a multiinstitutional cohort (n = 173) using five-fold cross-validation and holdout testing, the combined model achieved CV AUC 0.909 (95% CI 0.850–0.957) and holdout AUC 0.828 (95% CI 0.643–0.964), outperforming ablations (SSL-only: 0.703/0.636; asymmetry-only: 0.545/0.588). At a highsensitivity threshold, it reached 100% sensitivity and 100% NPV. This establishes a new benchmark for imaging-based HPV prediction in OPSCC without segmentation, enabling reliable non-invasive risk assessment. Artificial Intelligence and Machine Learning Head & Neck Surgery Oncology Nuclear Medicine & Medical Imaging Medical Informatics Full Text Additional Declarations The authors declare no competing interests. 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-8979142","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":597657122,"identity":"b09af08e-a50a-49a1-9c57-a86d76e0092e","order_by":0,"name":"John D. Mayfield, M.D. Ph.D. M.Sc.","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA40lEQVRIie3PsQrCMBCA4UggdTjteoPUVxACKujDWIRO18lVRBDipLtvIQidhWInH8BdcBCFgiAORU2dnGrcBPNDQob7SMKYzfabNfTqgnAma33AmikJvCokvZyAKYmlh5Qf2GfSmsZRmmbcV0iX427YBubEm2URqW2DwWKhhK/gHHUo0Q+DINgVEWQkeWUMvnLCSJLQBKFZTNyT5FmGvmJ0kHQ3IahvYaIhRZn4PlRG5DAozVTPE5A0eThHEB//4vZX7JY9oD6d7C90HXmuEyeF5D2Br910PI+n30zbbDbb//QE9BJCNBqo3cMAAAAASUVORK5CYII=","orcid":"https://orcid.org/0000-0001-5063-6160","institution":"Massachusetts General Hospital, Harvard Medical School, Athinoula A. Martinos Center for Biomedical Imaging","correspondingAuthor":true,"prefix":"","firstName":"M.D.","middleName":"Ph.D. John D.","lastName":"Mayfield","suffix":"M.D."},{"id":597657123,"identity":"c1c896f8-aa59-43ff-b889-75452c356876","order_by":1,"name":"Elly Arizono, M.D.","email":"","orcid":"","institution":"Massachusetts General Hospital, Harvard Medical School","correspondingAuthor":false,"prefix":"","firstName":"Elly","middleName":"","lastName":"Arizono","suffix":"M.D."},{"id":597657124,"identity":"c28354fe-678a-4bf7-b8c6-97418ffc5d3d","order_by":2,"name":"Karen Buch, M.D.","email":"","orcid":"https://orcid.org/0000-0001-9579-8921","institution":"Massachusetts General Hospital, Harvard Medical School","correspondingAuthor":false,"prefix":"","firstName":"Karen","middleName":"","lastName":"Buch","suffix":"M.D."},{"id":597657125,"identity":"82ebcd4b-ccc2-43a3-a763-fe3982a2116f","order_by":3,"name":"Osamu Sakai, M.D. Ph.D.","email":"","orcid":"https://orcid.org/0000-0003-3462-5116","institution":"Massachusetts General Hospital, Harvard Medical School, Massachusetts Eye and Ear","correspondingAuthor":false,"prefix":"","firstName":"M.D.","middleName":"Osamu","lastName":"Sakai","suffix":"M.D."}],"badges":[],"createdAt":"2026-02-26 14:51:56","currentVersionCode":1,"declarations":{"humanSubjects":true,"vertebrateSubjects":false,"conflictsOfInterestStatement":false,"humanSubjectEthicalGuidelines":true,"humanSubjectConsent":true,"humanSubjectClinicalTrial":false,"humanSubjectCaseReport":false,"vertebrateSubjectEthicalGuidelines":false},"doi":"10.21203/rs.3.rs-8979142/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8979142/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":104399111,"identity":"2c2dcc86-f996-4587-9880-6a862a584677","added_by":"auto","created_at":"2026-03-11 12:04:43","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":3150647,"visible":true,"origin":"","legend":"","description":"","filename":"AsymmetryNet022526FINAL.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8979142/v1_covered_0371204e-f08f-4538-9828-0ee05f64287b.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003eAsymmetryNet: A Clinically Inspired Asymmetry Attention Model for Predicting HPV Status in Oropharyngeal Squamous Cell Carcinoma on Computed Tomography\u003c/p\u003e","fulltext":[],"fulltextSource":"","fullText":"","funders":[{"identity":"6f3dfc17-e84a-47b0-a795-8f8ec6a96bbf","identifier":"10.13039/100005294","name":"Massachusetts General Hospital","awardNumber":"246529","order_by":0}],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"Massachusetts General Hospital","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":"","lastPublishedDoi":"10.21203/rs.3.rs-8979142/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8979142/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eAccurate, non-invasive HPV status prediction in oropharyngeal squamous cell carcinoma (OPSCC) is essential for risk stratification and treatment planning, yet current imaging methods lack sufficient sensitivity. We developed a novel framework combining 3D Masked Autoencoder (MAE) self-supervised learning (SSL) pretraining on a Swin Transformer encoder with 33 slice-aggregated asymmetry features (airway effacement, mass effect, midline shift, hypodensity metrics). In a multiinstitutional cohort (n = 173) using five-fold cross-validation and holdout testing, the combined model achieved CV AUC 0.909 (95% CI 0.850–0.957) and holdout AUC 0.828 (95% CI 0.643–0.964), outperforming ablations (SSL-only: 0.703/0.636; asymmetry-only: 0.545/0.588). At a highsensitivity threshold, it reached 100% sensitivity and 100% NPV. This establishes a new benchmark for imaging-based HPV prediction in OPSCC without segmentation, enabling reliable non-invasive risk assessment.\u003c/p\u003e","manuscriptTitle":"AsymmetryNet: A Clinically Inspired Asymmetry Attention Model for Predicting HPV Status in Oropharyngeal Squamous Cell Carcinoma on Computed Tomography","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-02-27 11:13:31","doi":"10.21203/rs.3.rs-8979142/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":"215fec4d-bdb6-4092-a3ba-fb024c46be2f","owner":[],"postedDate":"February 27th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":63647635,"name":"Artificial Intelligence and Machine Learning"},{"id":63647636,"name":"Head \u0026 Neck Surgery"},{"id":63647637,"name":"Oncology"},{"id":63647638,"name":"Nuclear Medicine \u0026 Medical Imaging"},{"id":63647639,"name":"Medical Informatics"}],"tags":[],"updatedAt":"2026-02-27T11:13:31+00:00","versionOfRecord":[],"versionCreatedAt":"2026-02-27 11:13:31","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8979142","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8979142","identity":"rs-8979142","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}