LUCID: Intelligent Informative Frame Selection in Otoscopy for Enhanced Diagnostic Utilitys

LUCID: Intelligent Informative Frame Selection in Otoscopy for Enhanced Diagnostic Utilitys | 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 LUCID: Intelligent Informative Frame Selection in Otoscopy for Enhanced Diagnostic Utilitys Hao Lu, Muhammet F. Demir, Gabriella I. Puchall, Zian Shang, Tucker Corwen, and 6 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7502743/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 diagnosis of middle ear diseases, such as acute otitis media (AOM), remains a clinical challenge due to the reliance on subjective visual assessment through otoscopy. While deep learning has shown promise in improving diagnostic accuracy using digital otoscopy videos, existing models often rely on manually selected still frames, a step that reduces their practicality in real-world clinical workflows. In this study, we present the first systematic method (LUCID) for automatically identifying the most informative frame (MIF) selection in otoscopy videos. Through analyzing of 713 videos, we identified three key factors that impact frame informativeness: eardrum visibility, eardrum coverage, and image clarity. We then develop a novel MIF pipeline that integrates (1) a ResNet-50 classifier trained on over 38,000 labeled frames to assess eardrum visibility, (2) a binary-adversarial CAM (BC-AdvCAM) method for weakly supervised eardrum segmentation and coverage estimation, and (3) a specialized blur and focus detection algorithm tailored to otoscope imagery. These components are combined into an "informative score" to rank frames automatically. Comparative evaluations using human reviewers and diagnostic AI models show that frames selected by our AI method perform comparably to expert-selected frames—achieving similar classification accuracy across multiple deep learning architectures. Notably, using the top four frames per video identified by our method significantly improves diagnostic accuracy over using a single expert-selected frame. This framework offers a scalable, expert-level tool for automating key frame selection and enhancing AI-based otoscopy diagnosis. The code is available at : https://github.com/CAIR-LAB-WFUSM/informatic_frame_selction.git Biological sciences/Computational biology and bioinformatics Health sciences/Diseases Health sciences/Health care Physical sciences/Mathematics and computing Health sciences/Medical research Frame Selection Middle Ear Diagnosis Deep Learning Eardrum Segmentation Image Quality Assessment Otologic AI 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-7502743","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":513222808,"identity":"673e715e-8e09-4a5b-a90e-f480606c5522","order_by":0,"name":"Hao Lu","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABBklEQVRIiWNgGAWjYBACgwMMDMwMDDYMDAcgAglAfgMzEVrSoFoSQFoYG5uJ0HKYFC3HDx9gZmw7L893I/ngh58/bPL42Q+2Py5gsMmXd8Cuxf5MWgJQy23DmTfSkiV7EtKKJXsSG5tnMKRZbjyAy2E5BiAtjBvOnDFj4Ek4nLjhAFALD8NhA8MGHFrOvwFpOWcP0sL4J+F/4v7zDwlouQG25UDihuM9Zsw8CUCGBNQWeVzev/Es4TDDueTkmcfbkqVl0pITZ9x42DibxyDNwACXlvPJBx//KLOz7TvMfPDjGxu7xP7+5AOfeSpsDORxOAwEDmAzChJlJAJ8toyCUTAKRsGIAgBRI2YWUSMUfgAAAABJRU5ErkJggg==","orcid":"","institution":"Wake Forest University School of Medicine","correspondingAuthor":true,"prefix":"","firstName":"Hao","middleName":"","lastName":"Lu","suffix":""},{"id":513222809,"identity":"964289bc-9498-4f8c-8a99-650cb0e3f792","order_by":1,"name":"Muhammet F. Demir","email":"","orcid":"","institution":"Wake Forest University School of Medicine","correspondingAuthor":false,"prefix":"","firstName":"Muhammet","middleName":"F.","lastName":"Demir","suffix":""},{"id":513222810,"identity":"93181dda-cadc-44b4-a375-b720b82f2a91","order_by":2,"name":"Gabriella I. Puchall","email":"","orcid":"","institution":"Wake Forest University School of Medicine","correspondingAuthor":false,"prefix":"","firstName":"Gabriella","middleName":"I.","lastName":"Puchall","suffix":""},{"id":513222811,"identity":"9cb68470-b56a-47dc-85d5-b3aec4d93917","order_by":3,"name":"Zian Shang","email":"","orcid":"","institution":"Wake Forest University School of Medicine","correspondingAuthor":false,"prefix":"","firstName":"Zian","middleName":"","lastName":"Shang","suffix":""},{"id":513222812,"identity":"5ef0c46d-11ff-40a5-a996-58103749ae78","order_by":4,"name":"Tucker Corwen","email":"","orcid":"","institution":"Wake Forest University School of Medicine","correspondingAuthor":false,"prefix":"","firstName":"Tucker","middleName":"","lastName":"Corwen","suffix":""},{"id":513222813,"identity":"2d68b4a1-4739-458b-838a-c60ea63b64a0","order_by":5,"name":"Shalaka Chavan","email":"","orcid":"","institution":"Wake Forest University School of Medicine","correspondingAuthor":false,"prefix":"","firstName":"Shalaka","middleName":"","lastName":"Chavan","suffix":""},{"id":513222814,"identity":"bab5e7ac-57f8-4e2c-8b64-89eeeffccac1","order_by":6,"name":"Carl D. Langefeld","email":"","orcid":"","institution":"Wake Forest University School of Medicine","correspondingAuthor":false,"prefix":"","firstName":"Carl","middleName":"D.","lastName":"Langefeld","suffix":""},{"id":513222815,"identity":"884c3439-4a95-467b-9d14-04bbac78abf2","order_by":7,"name":"Amy Zinnia","email":"","orcid":"","institution":"Wake Forest University School of Medicine","correspondingAuthor":false,"prefix":"","firstName":"Amy","middleName":"","lastName":"Zinnia","suffix":""},{"id":513222816,"identity":"5d028f56-c525-4625-bce8-1f85259c1e7e","order_by":8,"name":"Muhammad Khalid Khan Niazi","email":"","orcid":"","institution":"The Ohio State University","correspondingAuthor":false,"prefix":"","firstName":"Muhammad","middleName":"Khalid Khan","lastName":"Niazi","suffix":""},{"id":513222817,"identity":"1aa1fecb-5f7d-4890-b059-a82a7d23e8ec","order_by":9,"name":"Aaron C. Moberly","email":"","orcid":"","institution":"Vanderbilt University Medical Center","correspondingAuthor":false,"prefix":"","firstName":"Aaron","middleName":"C.","lastName":"Moberly","suffix":""},{"id":513222818,"identity":"2e7f6885-5c99-4b6e-ad1b-91d20133a469","order_by":10,"name":"Metin N. Gurcan","email":"","orcid":"","institution":"Wake Forest University School of Medicine","correspondingAuthor":false,"prefix":"","firstName":"Metin","middleName":"N.","lastName":"Gurcan","suffix":""}],"badges":[],"createdAt":"2025-08-31 20:53:04","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7502743/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7502743/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":93483070,"identity":"6b0505cb-aedc-4cc9-9640-dcb275e68c30","added_by":"auto","created_at":"2025-10-14 10:24:09","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":719214,"visible":true,"origin":"","legend":"","description":"","filename":"LUCID.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7502743/v1_covered_9a4b9131-a585-4d0e-99da-3c4720c63d41.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"LUCID: Intelligent Informative Frame Selection in Otoscopy for Enhanced Diagnostic Utilitys","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":"Frame Selection, Middle Ear Diagnosis, Deep Learning, Eardrum Segmentation, Image Quality Assessment, Otologic AI","lastPublishedDoi":"10.21203/rs.3.rs-7502743/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7502743/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eAccurate diagnosis of middle ear diseases, such as acute otitis media (AOM), remains a clinical challenge due to the reliance on subjective visual assessment through otoscopy. While deep learning has shown promise in improving diagnostic accuracy using digital otoscopy videos, existing models often rely on manually selected still frames, a step that reduces their practicality in real-world clinical workflows. In this study, we present the first systematic method (LUCID) for automatically identifying the most informative frame (MIF) selection in otoscopy videos. Through analyzing of 713 videos, we identified three key factors that impact frame informativeness: eardrum visibility, eardrum coverage, and image clarity. We then develop a novel MIF pipeline that integrates (1) a ResNet-50 classifier trained on over 38,000 labeled frames to assess eardrum visibility, (2) a binary-adversarial CAM (BC-AdvCAM) method for weakly supervised eardrum segmentation and coverage estimation, and (3) a specialized blur and focus detection algorithm tailored to otoscope imagery. These components are combined into an \"informative score\" to rank frames automatically. Comparative evaluations using human reviewers and diagnostic AI models show that frames selected by our AI method perform comparably to expert-selected frames\u0026mdash;achieving similar classification accuracy across multiple deep learning architectures. Notably, using the top four frames per video identified by our method significantly improves diagnostic accuracy over using a single expert-selected frame. This framework offers a scalable, expert-level tool for automating key frame selection and enhancing AI-based otoscopy diagnosis. The code is available at : \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://github.com/CAIR-LAB-WFUSM/informatic_frame_selction.git\u003c/span\u003e\u003cspan address=\"https://github.com/CAIR-LAB-WFUSM/informatic_frame_selction.git\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/p\u003e","manuscriptTitle":"LUCID: Intelligent Informative Frame Selection in Otoscopy for Enhanced Diagnostic Utilitys","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-09-15 11:08:09","doi":"10.21203/rs.3.rs-7502743/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":"dfe9856e-d201-44c4-966a-9f0b0ee35d50","owner":[],"postedDate":"September 15th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":54523323,"name":"Biological sciences/Computational biology and bioinformatics"},{"id":54523324,"name":"Health sciences/Diseases"},{"id":54523325,"name":"Health sciences/Health care"},{"id":54523326,"name":"Physical sciences/Mathematics and computing"},{"id":54523327,"name":"Health sciences/Medical research"}],"tags":[],"updatedAt":"2026-03-17T10:55:15+00:00","versionOfRecord":[],"versionCreatedAt":"2025-09-15 11:08:09","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7502743","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7502743","identity":"rs-7502743","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}