YOLO-HSD: A Multi-Module Collaborative Optimization Network for Caries Detection in Panoramic X-Ray Images

YOLO-HSD: A Multi-Module Collaborative Optimization Network for Caries Detection in Panoramic X-Ray Images | 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 YOLO-HSD: A Multi-Module Collaborative Optimization Network for Caries Detection in Panoramic X-Ray Images Weichen Zhu, Zhengchun Xu, Daoli Xu This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7430378/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 9 You are reading this latest preprint version Abstract Dental caries, one of the most prevalent oral diseases, significantly impacts quality of life and can lead to severe complications such as pulpitis and periapical periodontitis. Early detection and treatment are critical to slowing its progression , yet traditional diagnostic methods heavily rely on clinician expertise and suffer from high misdiagnosis rates. To address this, we propose YOLO-HSD, a novel caries detection model based on YOLOv11, designed to identify caries in panoramic dental X-rays. Our study utilizes a dataset of 5,290 clinical panoramic X-ray images from diverse sources, encompassing caries at various stages. To enhance image clarity across multi-source X-rays, we introduce a Histogram Transformer Block (HTB). Additionally, we mitigate feature redundancy through a Spatial and Channel Reconstruction Convolution (SCConv) module for optimized feature extraction and replace conventional upsampling with Dynamic 1 Upsampling (DySample) to improve resolution and detection accuracy. These innovations ensure high-quality data input and significantly boost performance, achieving a 28.6% improvement in mAP50-95 over YOLOv11n on the test set. Dental Caries Detection Histogram Transformer Block Spatial and Channel Reconstruction Convolution Dynamic Upsampling Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Editorial decision: Revision requested 23 Jan, 2026 Reviews received at journal 15 Jan, 2026 Reviewers agreed at journal 03 Jan, 2026 Reviews received at journal 02 Jan, 2026 Reviewers agreed at journal 02 Jan, 2026 Reviewers invited by journal 01 Dec, 2025 Editor assigned by journal 08 Sep, 2025 Submission checks completed at journal 08 Sep, 2025 First submitted to journal 21 Aug, 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-7430378","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":553511417,"identity":"a028f573-3863-4547-a1e7-fa5a429e4da6","order_by":0,"name":"Weichen Zhu","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA8ElEQVRIie3PsYrCMBzH8YZAp790TdGH+IOgCHJ9lRTB6UBHB4ccAe8Vci9yc0rALkHXgsLRxbnirBjB7e5S3RzyXbL8PiSJolDoJSOC3g6MqNbNYgxJIh4mcV4rO+2lSrffcyfQ73dWZoyC++dYyo/TfLHPhowPGMRbwEiT5vjuIbaQXWUPdKT4lDHYwZAKmn59/08GVb6i7j0xVnzNkO1gJHRMOz7yUztyMYDOMo4bQM1bSEUcEYZhNaFurdtJZnPZhbVBtAdSCz2BVBXS+5f0s6xPsDQZlrPGnC9vWZLIojl6yF8R8dw+FAqFQr+6Av1zVsmHlJ3OAAAAAElFTkSuQmCC","orcid":"","institution":"College \u0026 Hospital of Stomatology, Anhui Medical University","correspondingAuthor":true,"prefix":"","firstName":"Weichen","middleName":"","lastName":"Zhu","suffix":""},{"id":553511418,"identity":"38cba5d2-e84a-4023-93fb-377cff4f9810","order_by":1,"name":"Zhengchun Xu","email":"","orcid":"","institution":"University of Science and Technology of China","correspondingAuthor":false,"prefix":"","firstName":"Zhengchun","middleName":"","lastName":"Xu","suffix":""},{"id":553511419,"identity":"7c2e56f8-71a6-4c39-bc5f-f8e8d21b915c","order_by":2,"name":"Daoli Xu","email":"","orcid":"","institution":"Hefei Emergetech Co., Ltd","correspondingAuthor":false,"prefix":"","firstName":"Daoli","middleName":"","lastName":"Xu","suffix":""}],"badges":[],"createdAt":"2025-08-22 03:38:27","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7430378/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7430378/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":97369219,"identity":"641f4bfd-9cee-452d-905d-7f4f2f4769c1","added_by":"auto","created_at":"2025-12-03 16:23:54","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":2035719,"visible":true,"origin":"","legend":"","description":"","filename":"YOLOHSD.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7430378/v1_covered_fddae493-c011-4607-af61-27573dba8cc4.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"YOLO-HSD: A Multi-Module Collaborative Optimization Network for Caries Detection in Panoramic X-Ray Images","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":"signal-image-and-video-processing","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"sivp","sideBox":"Learn more about [Signal, Image and Video Processing](http://link.springer.com/journal/11760)","snPcode":"11760","submissionUrl":"https://submission.nature.com/new-submission/11760/3","title":"Signal, Image and Video Processing","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Dental Caries Detection, Histogram Transformer Block, Spatial and Channel Reconstruction Convolution, Dynamic Upsampling","lastPublishedDoi":"10.21203/rs.3.rs-7430378/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7430378/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Dental caries, one of the most prevalent oral diseases, significantly impacts quality of life and can lead to severe complications such as pulpitis and periapical periodontitis. Early detection and treatment are critical to slowing its progression , yet traditional diagnostic methods heavily rely on clinician expertise and suffer from high misdiagnosis rates. To address this, we propose YOLO-HSD, a novel caries detection model based on YOLOv11, designed to identify caries in panoramic dental X-rays. Our study utilizes a dataset of 5,290 clinical panoramic X-ray images from diverse sources, encompassing caries at various stages. To enhance image clarity across multi-source X-rays, we introduce a Histogram Transformer Block (HTB). Additionally, we mitigate feature redundancy through a Spatial and Channel Reconstruction Convolution (SCConv) module for optimized feature extraction and replace conventional upsampling with Dynamic 1 Upsampling (DySample) to improve resolution and detection accuracy. These innovations ensure high-quality data input and significantly boost performance, achieving a 28.6% improvement in mAP50-95 over YOLOv11n on the test set.","manuscriptTitle":"YOLO-HSD: A Multi-Module Collaborative Optimization Network for Caries Detection in Panoramic X-Ray Images","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-12-03 06:54:38","doi":"10.21203/rs.3.rs-7430378/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2026-01-23T12:28:54+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-01-15T20:27:00+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"139130280449630423475328810081830120535","date":"2026-01-03T13:05:38+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-01-03T04:49:34+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"75835023608211456689321755828738304485","date":"2026-01-03T04:43:49+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-12-01T14:52:15+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-09-08T08:32:02+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-09-08T08:31:51+00:00","index":"","fulltext":""},{"type":"submitted","content":"Signal, Image and Video Processing","date":"2025-08-22T03:29:37+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"signal-image-and-video-processing","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"sivp","sideBox":"Learn more about [Signal, Image and Video Processing](http://link.springer.com/journal/11760)","snPcode":"11760","submissionUrl":"https://submission.nature.com/new-submission/11760/3","title":"Signal, Image and Video Processing","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"e20d89aa-a9df-462e-b829-3f09dd1249e1","owner":[],"postedDate":"December 3rd, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2026-02-02T11:08:16+00:00","versionOfRecord":[],"versionCreatedAt":"2025-12-03 06:54:38","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7430378","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7430378","identity":"rs-7430378","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}