Kernel learning enables fluorescence microscopic image deconvolution with enhanced performance and speed

Kernel learning enables fluorescence microscopic image deconvolution with enhanced performance and speed | 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 Kernel learning enables fluorescence microscopic image deconvolution with enhanced performance and speed Shenghua Cheng, Qiqi Lu, Hua Ye, Xiuli Liu, Shaoqun Zeng, Qianjin Feng This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4716501/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 The contrast and resolution of fluorescence microscopic images can be effectively improved by classic iterative Richardson-Lucy Deconvolution (RLD) algorithm, but this method is computationally expensive, particularly for three-dimensional data. Variants of RLD with manually designed unmatched backward projector can greatly accelerate deconvolution, however, they require careful parameter optimization to avoid introducing artifacts. Here, we develop Kernel Learning Deconvolution (KLD), which automatically learns forward/backward kernel in RLD from only one paired low-resolution and high-resolution images. The learned kernel reveals a similar pattern with handcrafted Wiener-Butterworth kernel but is more adaptive to data. Besides, it is robust to the signal-to-noise ratio and the number of training samples. KLD shows enhanced deconvolution performance and speed on different cellular structures and imaging modalities, including wide-field microscopy, confocal microscopy, and lattice light-sheet microscopy. Biological sciences/Computational biology and bioinformatics/Image processing Biological sciences/Computational biology and bioinformatics/Machine learning Biological sciences/Biological techniques/Imaging/Fluorescence imaging Full Text Additional Declarations There is NO Competing Interest. Supplementary Files Supplementaryinformation.pdf SupplementaryVideo.mp4 Supplementary Video 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-4716501","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":327272443,"identity":"1bab7ccc-3dce-4041-b8e8-997c5f508cb9","order_by":0,"name":"Shenghua Cheng","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA+UlEQVRIiWNgGAWjYDACCTB5QI6Nvf3gA4hQAnFajPl5ziQbkKQlceaMBDMJorTwz24+9vDLnzuMGw4kpFX+zDnMwM+eY8DwcwceS+4cSzeWbXvGbHDg4LHbvNsOM0j2vDFg7D2DW4uBRI6ZtGTDYTaDgw1ptxmBWgxu5BgwM7bh05L/TVriz2Eeg8MMZoU/gVrsCWvJYZP8wHZYQrKNwYwB5DCgCH4tEjfSzKQZ2w4b8PPwJEvzbkvnkTjzrOBgLx4t/DOSn0n++HO4vk3++cGPP7dZy/G3J2988BOPFhBg5kHigNkH8GtgYGD8QUjFKBgFo2AUjGwAACHyVSWPTpEnAAAAAElFTkSuQmCC","orcid":"https://orcid.org/0000-0003-3527-3845","institution":"School of Biomedical Engineering and Guangdong Provincial Key Laboratory of Medical Image Processing, Southern Medical University, Guangzhou, China","correspondingAuthor":true,"prefix":"","firstName":"Shenghua","middleName":"","lastName":"Cheng","suffix":""},{"id":327272444,"identity":"b947f6eb-f2dd-419a-82ca-d7622f434096","order_by":1,"name":"Qiqi Lu","email":"","orcid":"","institution":"Southern Medical University","correspondingAuthor":false,"prefix":"","firstName":"Qiqi","middleName":"","lastName":"Lu","suffix":""},{"id":327272445,"identity":"9ffae66e-377f-4cca-a3ae-64a0626c71d0","order_by":2,"name":"Hua Ye","email":"","orcid":"","institution":"Southern Medical University","correspondingAuthor":false,"prefix":"","firstName":"Hua","middleName":"","lastName":"Ye","suffix":""},{"id":327272446,"identity":"f6323b74-bdbe-47eb-8ef2-2c87f36513b4","order_by":3,"name":"Xiuli Liu","email":"","orcid":"https://orcid.org/0000-0001-6663-1647","institution":"Britton Chance Center for Biomedical Photonics, Wuhan National Laboratory for Optoelectronics-Huazhong University of Science and Technology, Wuhan, Hubei 430074, China","correspondingAuthor":false,"prefix":"","firstName":"Xiuli","middleName":"","lastName":"Liu","suffix":""},{"id":327272447,"identity":"7eb54647-9665-41b7-88e9-75f41dbaa4f0","order_by":4,"name":"Shaoqun Zeng","email":"","orcid":"","institution":"Huazhong University of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Shaoqun","middleName":"","lastName":"Zeng","suffix":""},{"id":327272448,"identity":"9b9f16af-f77c-41c3-b866-6db28b9cf79a","order_by":5,"name":"Qianjin Feng","email":"","orcid":"https://orcid.org/0000-0002-3830-5120","institution":"Southern Medical University","correspondingAuthor":false,"prefix":"","firstName":"Qianjin","middleName":"","lastName":"Feng","suffix":""}],"badges":[],"createdAt":"2024-07-10 08:05:28","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4716501/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4716501/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":62045978,"identity":"22414d23-15f2-4573-98ac-412f76fdd83b","added_by":"auto","created_at":"2024-08-08 15:54:42","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":12378864,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4716501/v1_covered_0616f26d-0fcf-4554-9012-82bbcbe151ed.pdf"},{"id":60460193,"identity":"b3354be5-53a2-4223-9f1c-06b2083ab02a","added_by":"auto","created_at":"2024-07-17 03:43:53","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":2164605,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cbr\u003e\u003c/p\u003e","description":"","filename":"Supplementaryinformation.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4716501/v1/3069852f32671d1354d7df09.pdf"},{"id":60460194,"identity":"f6f0cfa3-e63c-418c-b394-bd4621832069","added_by":"auto","created_at":"2024-07-17 03:43:54","extension":"mp4","order_by":2,"title":"","display":"","copyAsset":false,"role":"supplement","size":108231858,"visible":true,"origin":"","legend":"\u003cp\u003eSupplementary Video\u003c/p\u003e","description":"","filename":"SupplementaryVideo.mp4","url":"https://assets-eu.researchsquare.com/files/rs-4716501/v1/0337fec2a4903d79e7706ce6.mp4"}],"financialInterests":"There is \u003cb\u003eNO\u003c/b\u003e Competing Interest.","formattedTitle":"Kernel learning enables fluorescence microscopic image deconvolution with enhanced performance and speed","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-4716501/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4716501/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"The contrast and resolution of fluorescence microscopic images can be effectively improved by classic iterative Richardson-Lucy Deconvolution (RLD) algorithm, but this method is computationally expensive, particularly for three-dimensional data. Variants of RLD with manually designed unmatched backward projector can greatly accelerate deconvolution, however, they require careful parameter optimization to avoid introducing artifacts. Here, we develop Kernel Learning Deconvolution (KLD), which automatically learns forward/backward kernel in RLD from only one paired low-resolution and high-resolution images. The learned kernel reveals a similar pattern with handcrafted Wiener-Butterworth kernel but is more adaptive to data. Besides, it is robust to the signal-to-noise ratio and the number of training samples. KLD shows enhanced deconvolution performance and speed on different cellular structures and imaging modalities, including wide-field microscopy, confocal microscopy, and lattice light-sheet microscopy.","manuscriptTitle":"Kernel learning enables fluorescence microscopic image deconvolution with enhanced performance and speed","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-07-17 03:43:48","doi":"10.21203/rs.3.rs-4716501/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":"93acb53d-9699-4c4e-aae5-0088e4aa8af4","owner":[],"postedDate":"July 17th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":34637355,"name":"Biological sciences/Computational biology and bioinformatics/Image processing"},{"id":34637356,"name":"Biological sciences/Computational biology and bioinformatics/Machine learning"},{"id":34637357,"name":"Biological sciences/Biological techniques/Imaging/Fluorescence imaging"}],"tags":[],"updatedAt":"2024-08-08T15:46:32+00:00","versionOfRecord":[],"versionCreatedAt":"2024-07-17 03:43:48","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-4716501","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4716501","identity":"rs-4716501","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}