Comet Former: A Novel Deep Learning Architecture using the U-MixFormer Model to optimize Comet Assay Segmentation

Comet Former: A Novel Deep Learning Architecture using the U-MixFormer Model to optimize Comet Assay Segmentation | 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 Comet Former: A Novel Deep Learning Architecture using the U-MixFormer Model to optimize Comet Assay Segmentation Ronit Katikaneni This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6467170/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 Increased levels of DNA damage and ineffective repair mechanisms are the underlying bio-molecular events in the pathogenesis of most life-threatening diseases like cancer and degenerative diseases. The comet assay is a widely used method to quantify the amount of DNA damage from chemotherapeutic and radiotherapy agents. However, current methods for quantifying DNA damage, which involve manual segmentation and identification of comet areas, are time-consuming and inefficient. New Deep Learning models are used to complete this process as they are much more effective. To address this limitation, we propose a novel deep learning-based architecture, CometAI, which utilizes the U-MixFormer model to segment and identify comets in Comet Assay images efficiently. CometAI achieved high scores in intersection over union(IoU) and F1 Score, essential image segmentation metrics. Compared with current segmentation tools, CometAI offers a significant improvement in segmenting both the comet head and tail, allowing for more accurate DNA damage assessment in various fields. 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-6467170","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":451598456,"identity":"7119994c-029d-4680-bd4a-93e72315e9a1","order_by":0,"name":"Ronit Katikaneni","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA20lEQVRIiWNgGAWjYJCCA0DIwMbeDCQZJGSI03LgAIMEP8+xBJAWHiKtAWqRnJFjAGIT1mLe3nvw8IczdnUGZ858fnWjxoKHgf3w0Q34tMicOZdw4MCNZAmD473brHOOAR3Gk5Z2A58WCYkcgwMHPjBLGJw5u804hw2oRYLHjBgt9RIGN3KeGef8I1rLjcMg7zM/zm0jRgvPGYMDZ84cl+znOWbGnNsnwcNG0C/sPcYfKo5V8wOj8vHnnG91cvzsh4/h1YIM2CTAJLHKQYD5AymqR8EoGAWjYOQAABO+TmVFhqhdAAAAAElFTkSuQmCC","orcid":"","institution":"","correspondingAuthor":true,"prefix":"","firstName":"Ronit","middleName":"","lastName":"Katikaneni","suffix":""}],"badges":[],"createdAt":"2025-04-17 02:23:11","currentVersionCode":1,"declarations":{"humanSubjects":false,"vertebrateSubjects":false,"conflictsOfInterestStatement":false,"humanSubjectEthicalGuidelines":false,"humanSubjectConsent":false,"humanSubjectClinicalTrial":false,"humanSubjectCaseReport":false,"vertebrateSubjectEthicalGuidelines":false},"doi":"10.21203/rs.3.rs-6467170/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6467170/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":83064076,"identity":"5ff54ae8-d5bc-4e98-9c70-bf78224b71fc","added_by":"auto","created_at":"2025-05-19 15:17:09","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":380635,"visible":true,"origin":"","legend":"","description":"","filename":"CometFormerANovelDeepLearningArchitectureusingtheUMixFormerModeltooptimizeCometAssaySegmentation11.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6467170/v1_covered_5779bbca-bc2b-43a7-89f0-9c15501e4324.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Comet Former: A Novel Deep Learning Architecture using the U-MixFormer Model to optimize Comet Assay Segmentation","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":true,"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-6467170/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6467170/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eIncreased levels of DNA damage and ineffective repair mechanisms are the underlying bio-molecular events in the pathogenesis of most life-threatening diseases like cancer and degenerative diseases. The comet assay is a widely used method to quantify the amount of DNA damage from chemotherapeutic and radiotherapy agents. However, current methods for quantifying DNA damage, which involve manual segmentation and identification of comet areas, are time-consuming and inefficient. New Deep Learning models are used to complete this process as they are much more effective. To address this limitation, we propose a novel deep learning-based architecture, CometAI, which utilizes the U-MixFormer model to segment and identify comets in Comet Assay images efficiently. CometAI achieved high scores in intersection over union(IoU) and F1 Score, essential image segmentation metrics. Compared with current segmentation tools, CometAI offers a significant improvement in segmenting both the comet head and tail, allowing for more accurate DNA damage assessment in various fields. \u003c/p\u003e","manuscriptTitle":"Comet Former: A Novel Deep Learning Architecture using the U-MixFormer Model to optimize Comet Assay Segmentation","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-05-06 18:23:07","doi":"10.21203/rs.3.rs-6467170/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":"75e1a879-9c9c-4c39-a6d3-bec7f976ee10","owner":[],"postedDate":"May 6th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2025-05-19T15:09:01+00:00","versionOfRecord":[],"versionCreatedAt":"2025-05-06 18:23:07","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-6467170","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6467170","identity":"rs-6467170","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}