Full text
14,591 characters
· extracted from
preprint-html
· click to expand
From Time-Lapse to Morphokinetics: Neural ODE Dynamics for Reliable Embryo Stage Transition Timing | 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 From Time-Lapse to Morphokinetics: Neural ODE Dynamics for Reliable Embryo Stage Transition Timing Mohammed El Amine Bechar, Jean-Marie Guyader, Marwa Elbouz, Frédéric Morel, and 2 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9139745/v1 This work is licensed under a CC BY 4.0 License Status: Under Revision Version 1 posted 9 You are reading this latest preprint version Abstract Problem : Time-lapse imaging (TLI) enables continuous embryo monitoring in IVF, yet morphokinetic annotation remains labor-intensive and subject to interoperator variability. Automated detection of developmental phase transitions is challenging due to subtle morphological changes, heterogeneous acquisition conditions, and the need for temporally consistent predictions. Aim : We aim to detect morphokinetic phase transitions in embryo TLI videos using a robust, clinically oriented framework designed to support human-in-theloop annotation rather than replace clinical decision-making. Methods : We propose a spatio-temporal Neural Ordinary Differential Equation (Neural ODE) model for continuous-time representation learning, coupled with a transition scoring mechanism and an online, one-class training strategy. The method named Reference-Based Neural ODE Change Detector (RBNODE) is transition-agnostic and relies on a reference trajectory learned from normal developmental dynamics to detect change points. Experiments are conducted on the public dataset of Gomez et al. (704 embryo videos, seven focal planes, 16 developmental phases). Results : The proposed method achieves an AUC of 0.988 for transition detection and reaches 0.873 detection accuracy within a 5-frame tolerance (Det@5f). The estimated transition time is close to expert annotations, with a mean absolute error of 2.64 frames and a median error of 1 frame. Performance remains stable across key transitions, including blastocyst-related stages, highlighting the benefit of continuous-time temporal modeling for reducing temporal instability. Conclusion : Continuous-time spatio-temporal modeling with Neural ODEs provides a promising and reproducible approach for robust morphokinetic transition detection in embryo TLI, offering practical support for standardized annotation workflows and future prospective validation in clinical settings. Embryo time-lapse imaging IVF morphokinetics phase transition detection continuous-time deep learning neural ordinary differential equations human-in-the-loop AI Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Revision Version 1 posted Editorial decision: Revision requested 06 May, 2026 Reviews received at journal 23 Apr, 2026 Reviews received at journal 13 Apr, 2026 Reviewers agreed at journal 08 Apr, 2026 Reviewers agreed at journal 07 Apr, 2026 Reviewers invited by journal 19 Mar, 2026 Editor assigned by journal 19 Mar, 2026 Submission checks completed at journal 18 Mar, 2026 First submitted to journal 16 Mar, 2026 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-9139745","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":609122131,"identity":"4f1cee5c-9ab5-4c89-96e3-a69b375aa883","order_by":0,"name":"Mohammed El Amine Bechar","email":"","orcid":"","institution":"ISEN Ouest","correspondingAuthor":false,"prefix":"","firstName":"Mohammed","middleName":"El Amine","lastName":"Bechar","suffix":""},{"id":609122132,"identity":"944a662d-3f4a-4af1-b41a-bc98cb4b19be","order_by":1,"name":"Jean-Marie Guyader","email":"","orcid":"","institution":"ISEN Ouest","correspondingAuthor":false,"prefix":"","firstName":"Jean-Marie","middleName":"","lastName":"Guyader","suffix":""},{"id":609122133,"identity":"5e9bb82d-1a2f-473d-912d-6a80fea396c2","order_by":2,"name":"Marwa Elbouz","email":"","orcid":"","institution":"ISEN Ouest","correspondingAuthor":false,"prefix":"","firstName":"Marwa","middleName":"","lastName":"Elbouz","suffix":""},{"id":609122134,"identity":"e8475040-4540-4d04-9157-45c67296b604","order_by":3,"name":"Frédéric Morel","email":"","orcid":"","institution":"Centre Hospitalier Régional Universitaire de Brest","correspondingAuthor":false,"prefix":"","firstName":"Frédéric","middleName":"","lastName":"Morel","suffix":""},{"id":609122135,"identity":"eb6b9db0-717e-49b8-a7ea-0e5cf9092f20","order_by":4,"name":"Aurore Perrin","email":"","orcid":"","institution":"Centre Hospitalier Régional Universitaire de Brest","correspondingAuthor":false,"prefix":"","firstName":"Aurore","middleName":"","lastName":"Perrin","suffix":""},{"id":609122136,"identity":"6e85fcc9-82d7-46a8-8a92-3d413cf8f1f0","order_by":5,"name":"Nesma Settouti","email":"data:image/png;base64,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","orcid":"","institution":"ISEN Ouest","correspondingAuthor":true,"prefix":"","firstName":"Nesma","middleName":"","lastName":"Settouti","suffix":""}],"badges":[],"createdAt":"2026-03-16 15:28:26","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-9139745/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9139745/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":105564618,"identity":"dee41768-42ca-4792-a321-e2dc717cf51a","added_by":"auto","created_at":"2026-03-27 12:50:13","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1353538,"visible":true,"origin":"","legend":"","description":"","filename":"NNODEEVEpaper1.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9139745/v1_covered_3f073d1b-ed86-4306-98f5-6266ef7f6b5e.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"From Time-Lapse to Morphokinetics: Neural ODE Dynamics for Reliable Embryo Stage Transition Timing","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":false,"email":"","identity":"journal-of-assisted-reproduction-and-genetics","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"","title":"Journal of Assisted Reproduction and Genetics","twitterHandle":"","acdcEnabled":false,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"VoR Journals","inReviewEnabled":false,"inReviewRevisionsEnabled":false},"keywords":"Embryo time-lapse imaging, IVF, morphokinetics, phase transition detection, continuous-time deep learning, neural ordinary differential equations, human-in-the-loop AI","lastPublishedDoi":"10.21203/rs.3.rs-9139745/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9139745/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003e\u003cstrong\u003eProblem\u003c/strong\u003e: Time-lapse imaging (TLI) enables continuous embryo monitoring in IVF, yet morphokinetic annotation remains labor-intensive and subject to interoperator variability. Automated detection of developmental phase transitions is challenging due to subtle morphological changes, heterogeneous acquisition conditions, and the need for temporally consistent predictions.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eAim\u003c/strong\u003e: We aim to detect morphokinetic phase transitions in embryo TLI videos using a robust, clinically oriented framework designed to support human-in-theloop annotation rather than replace clinical decision-making.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eMethods\u003c/strong\u003e: We propose a spatio-temporal Neural Ordinary Differential Equation (Neural ODE) model for continuous-time representation learning, coupled with a transition scoring mechanism and an online, one-class training strategy. The method named Reference-Based Neural ODE Change Detector (RBNODE) is transition-agnostic and relies on a reference trajectory learned from normal developmental dynamics to detect change points. Experiments are conducted on the public dataset of Gomez et al. (704 embryo videos, seven focal planes, 16 developmental phases).\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eResults\u003c/strong\u003e: The proposed method achieves an AUC of 0.988 for transition detection and reaches 0.873 detection accuracy within a 5-frame tolerance (Det@5f). The estimated transition time is close to expert annotations, with a mean absolute error of 2.64 frames and a median error of 1 frame. Performance remains stable across key transitions, including blastocyst-related stages, highlighting the benefit of continuous-time temporal modeling for reducing temporal instability.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eConclusion\u003c/strong\u003e: Continuous-time spatio-temporal modeling with Neural ODEs provides a promising and reproducible approach for robust morphokinetic transition detection in embryo TLI, offering practical support for standardized annotation workflows and future prospective validation in clinical settings.\u003c/p\u003e","manuscriptTitle":"From Time-Lapse to Morphokinetics: Neural ODE Dynamics for Reliable Embryo Stage Transition Timing","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-03-24 04:45:07","doi":"10.21203/rs.3.rs-9139745/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2026-05-06T13:19:49+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-04-23T11:27:24+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-04-13T13:07:54+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"152002448651090129156524968814391419067","date":"2026-04-08T09:15:59+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"217141391300244676824313933397768720254","date":"2026-04-07T04:36:02+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-03-19T15:57:25+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-03-19T15:33:57+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-03-19T00:56:25+00:00","index":"","fulltext":""},{"type":"submitted","content":"Journal of Assisted Reproduction and Genetics","date":"2026-03-16T15:16:29+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":false,"email":"","identity":"journal-of-assisted-reproduction-and-genetics","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"","title":"Journal of Assisted Reproduction and Genetics","twitterHandle":"","acdcEnabled":false,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"VoR Journals","inReviewEnabled":false,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"3cf6e8ce-0c11-4040-90f6-a194b8b56f83","owner":[],"postedDate":"March 24th, 2026","published":true,"recentEditorialEvents":[{"type":"decision","content":"Revision requested","date":"2026-05-06T13:19:49+00:00","index":"","fulltext":""}],"rejectedJournal":[],"revision":"","amendment":"","status":"in-revision","subjectAreas":[],"tags":[],"updatedAt":"2026-05-06T13:24:46+00:00","versionOfRecord":[],"versionCreatedAt":"2026-03-24 04:45:07","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9139745","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9139745","identity":"rs-9139745","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}
Text is read by the "Ask this paper" AI Q&A widget below.
Extraction quality varies by source — PMC NXML preserves structure
cleanly, OA-HTML may include some navigation residue, and OA-PDF can
have broken hyphenation. The publisher copy
(via DOI)
is the canonical version.