Breaking the speed limit in two-photon microscopy via deep-learning imaging reconstruction from anisotropic sparse sampling

Breaking the speed limit in two-photon microscopy via deep-learning imaging reconstruction from anisotropic sparse sampling | 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 Breaking the speed limit in two-photon microscopy via deep-learning imaging reconstruction from anisotropic sparse sampling Biqin Dong, Ang Xuan, Yuanjie Gu, Yiqun Wang, Jianping Wang, Chengyu Li, and 3 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9267461/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 Two-photon microscopy is essential for high-resolution imaging of neural circuits, yet its serial point-scanning architecture imposes a fundamental trade-off among imaging speed, spatial resolution, and field of view. This spatiotemporal constraint limits the ability to capture fast neuronal dynamics. Here, we introduce Imaging Reconstruction from anIsotropic Sparse sampling (IRIS), a deep-learning framework that overcomes this bottleneck by strategically downsampling along the slow scanning axis and reconstructing high-fidelity images using a one-dimensional image reconstruction neural network. Without requiring hardware modifications, IRIS enables imaging at rates spanning several hundred hertz to the kilohertz regime while preserving the field of view. We show that IRIS accurately retains both the spatial structure and temporal dynamics of fluorescent signals in vivo. The framework generalizes across imaging modalities, supporting volumetric cortical imaging and large-field recording of over 1,000 neurons at 60 Hz. Applied across wakefulness-anesthesia-recovery cycles, IRIS successfully captures state-dependent shifts in neuronal synchrony across multiple layers of the motor-sensory cortex. By decoupling acquisition speed from spatial sampling, IRIS provides a robust computational paradigm for high-speed functional neuroimaging. Physical sciences/Optics and photonics/Optical techniques/Microscopy/Multiphoton microscopy Physical sciences/Optics and photonics/Optical techniques/Imaging and sensing Physical sciences/Optics and photonics/Optical techniques/Microscopy/Ca2+ imaging Full Text Additional Declarations There is a conflict of interest B.D. and C.K. are founders and equity holders of MicroLux (Shanghai) Intelligent Science & Technology Co., Ltd. All other authors declare no competing interests. Supplementary Files IRISSupplementaryv4.pdf Supplementary Information 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-9267461","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":615833085,"identity":"c3610e83-0fed-4d91-bec0-e42d7ff49fb7","order_by":0,"name":"Biqin Dong","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA1klEQVRIie3LsQqCUBTG8SNCLmbrcegdLgg2GD3LFUEXCSdpiLiTU9HakzQLQi43WwWXIHCpQQgao4Rmu25B9z+dA98PQCb7xVIAFWA6AqDtqwoT32R9SdaDGPkmu0bxCUnu1WdYOC7TjmknMXnhO7uiQsLrCQEeuEyf005CytC2hkm1IiW1UUkyl6FOREiBpAweqDzFiHUZJim2FhUmQEzObXVXeGjyW4z0EFiJHnYTI19b9yieoZEHe2yWznir8W7yboAw+Jy0fb/t36mN0Ewmk8n+txeJAkfYNxwWfgAAAABJRU5ErkJggg==","orcid":"","institution":"Fudan University","correspondingAuthor":true,"prefix":"","firstName":"Biqin","middleName":"","lastName":"Dong","suffix":""},{"id":615833086,"identity":"66c0d778-6d7e-417d-b269-29e79329bc53","order_by":1,"name":"Ang Xuan","email":"","orcid":"","institution":"Fudan University","correspondingAuthor":false,"prefix":"","firstName":"Ang","middleName":"","lastName":"Xuan","suffix":""},{"id":615833087,"identity":"6e40e614-e03f-4f25-841a-b48827701005","order_by":2,"name":"Yuanjie Gu","email":"","orcid":"","institution":"Fudan University","correspondingAuthor":false,"prefix":"","firstName":"Yuanjie","middleName":"","lastName":"Gu","suffix":""},{"id":615833088,"identity":"c866015a-e45f-4fa6-9964-61d886ed2095","order_by":3,"name":"Yiqun Wang","email":"","orcid":"","institution":"Fudan University","correspondingAuthor":false,"prefix":"","firstName":"Yiqun","middleName":"","lastName":"Wang","suffix":""},{"id":615833089,"identity":"c24a14fc-f5e0-485c-9e89-cf0bf481b5df","order_by":4,"name":"Jianping Wang","email":"","orcid":"","institution":"Fudan University","correspondingAuthor":false,"prefix":"","firstName":"Jianping","middleName":"","lastName":"Wang","suffix":""},{"id":615833090,"identity":"0f24df5a-de41-4428-9470-b4772955cfc5","order_by":5,"name":"Chengyu Li","email":"","orcid":"","institution":"Fudan University","correspondingAuthor":false,"prefix":"","firstName":"Chengyu","middleName":"","lastName":"Li","suffix":""},{"id":615833091,"identity":"1ba97eb5-977d-44f1-aeac-ddd72a731b5f","order_by":6,"name":"Su Tang","email":"","orcid":"","institution":"Fudan University Shanghai Cancer Center","correspondingAuthor":false,"prefix":"","firstName":"Su","middleName":"","lastName":"Tang","suffix":""},{"id":615833092,"identity":"a8d38281-8c04-4082-92e0-a3761e05d3db","order_by":7,"name":"Yao Wu","email":"","orcid":"","institution":"MicroLux (Shanghai) Intelligent Science \u0026 Technology Co., Ltd.","correspondingAuthor":false,"prefix":"","firstName":"Yao","middleName":"","lastName":"Wu","suffix":""},{"id":615833093,"identity":"fb486085-039b-44f2-abdb-67d0ad3e8a79","order_by":8,"name":"Cihang Kong","email":"","orcid":"","institution":"Fudan University","correspondingAuthor":false,"prefix":"","firstName":"Cihang","middleName":"","lastName":"Kong","suffix":""}],"badges":[],"createdAt":"2026-03-30 13:20:30","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-9267461/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9267461/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":106414687,"identity":"507efb11-9fb9-49cd-b893-aecc49412176","added_by":"auto","created_at":"2026-04-08 10:22:20","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":6642877,"visible":true,"origin":"","legend":"Article File","description":"","filename":"IRISManuscripts202603v23.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9267461/v1_covered_eb408854-d4ab-4dcd-9938-e558f0cccf41.pdf"},{"id":105934820,"identity":"634ce10e-c580-4a6d-855e-52d444086300","added_by":"auto","created_at":"2026-04-01 14:50:15","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":5147361,"visible":true,"origin":"","legend":"Supplementary Information","description":"","filename":"IRISSupplementaryv4.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9267461/v1/faf17095057ce1c144fbf3b1.pdf"}],"financialInterests":"There is a conflict of interest\nB.D. and C.K. are founders and equity holders of MicroLux (Shanghai) Intelligent Science \u0026 Technology Co., Ltd. All other authors declare no competing interests.","formattedTitle":"Breaking the speed limit in two-photon microscopy via deep-learning imaging reconstruction from anisotropic sparse sampling","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"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":"","lastPublishedDoi":"10.21203/rs.3.rs-9267461/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9267461/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Two-photon microscopy is essential for high-resolution imaging of neural circuits, yet its serial point-scanning architecture imposes a fundamental trade-off among imaging speed, spatial resolution, and field of view. This spatiotemporal constraint limits the ability to capture fast neuronal dynamics. Here, we introduce Imaging Reconstruction from anIsotropic Sparse sampling (IRIS), a deep-learning framework that overcomes this bottleneck by strategically downsampling along the slow scanning axis and reconstructing high-fidelity images using a one-dimensional image reconstruction neural network. Without requiring hardware modifications, IRIS enables imaging at rates spanning several hundred hertz to the kilohertz regime while preserving the field of view. We show that IRIS accurately retains both the spatial structure and temporal dynamics of fluorescent signals in vivo. The framework generalizes across imaging modalities, supporting volumetric cortical imaging and large-field recording of over 1,000 neurons at 60 Hz. Applied across wakefulness-anesthesia-recovery cycles, IRIS successfully captures state-dependent shifts in neuronal synchrony across multiple layers of the motor-sensory cortex. By decoupling acquisition speed from spatial sampling, IRIS provides a robust computational paradigm for high-speed functional neuroimaging.","manuscriptTitle":"Breaking the speed limit in two-photon microscopy via deep-learning imaging reconstruction from anisotropic sparse sampling","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-04-01 14:50:11","doi":"10.21203/rs.3.rs-9267461/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":"7f832592-b44c-447c-8439-fccee97606a2","owner":[],"postedDate":"April 1st, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":65532674,"name":"Physical sciences/Optics and photonics/Optical techniques/Microscopy/Multiphoton microscopy"},{"id":65532675,"name":"Physical sciences/Optics and photonics/Optical techniques/Imaging and sensing"},{"id":65532676,"name":"Physical sciences/Optics and photonics/Optical techniques/Microscopy/Ca2+ imaging"}],"tags":[],"updatedAt":"2026-04-07T03:26:25+00:00","versionOfRecord":[],"versionCreatedAt":"2026-04-01 14:50:11","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9267461","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9267461","identity":"rs-9267461","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}