FluoGen: An Open-Source Generative Foundation Model for Fluorescence Microscopy Image Enhancement and Analysis

FluoGen: An Open-Source Generative Foundation Model for Fluorescence Microscopy Image Enhancement and Analysis | 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 Method Article FluoGen: An Open-Source Generative Foundation Model for Fluorescence Microscopy Image Enhancement and Analysis Huaian Chen, Shiyao Hong, Yuxuan Gu, Junkang Dai, Zhixiang Wei, and 4 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8334792/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 Fluorescence microscopy, empowered by artificial intelligence (AI), has shown great promise in advancing life science. However, the high cost and complexity of sample preparation limit the availability of training data, constraining the performance of AI-based models. Here, we present FluoGen, a diffusion-based generative foundation model designed to improve AI-based fluorescence image processing under data-constrained conditions. By pretraining on 3.5 million fluorescence images with a reformulated learning objective, FluoGen learns rich biological representations and mitigates inherent biases in conventional diffusion models. We demonstrate that FluoGen can serve as a backbone for image enhancement, enabling models to recover cellular and subcellular structures with substantially limited samples. Furthermore, FluoGen can reduce the training data required by existing AI-based analysis models to approximately 2% of the original amount while boosting the performance of state-of-the-art methods without architectural modifications. We anticipate that FluoGen serves as a foundation tool for advancing AI applications in fluorescence imaging. Artificial Intelligence and Machine Learning Biotechnology and Bioengineering Artificial intelligence diffusion model fluorescence microscopy image generation image analysis Full Text Additional Declarations The authors declare no competing interests. Supplementary Files supp.pdf 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-8334792","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Method Article","associatedPublications":[],"authors":[{"id":573992701,"identity":"93726d02-6d49-4338-a11c-05b4b62b5735","order_by":0,"name":"Huaian Chen","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAwklEQVRIiWNgGAWjYHACNiC2QWITqSUNqpoELYdJ0MI/u/nZg487zifOn9/8gOFD2WGgSAN+LRJ3jpkbzjxzO3HDMTYDxhnnDgNFDhCw5kYOmzRvG1ALGw8DM2/bYQYDiQT8OuRBWv62nUuc3wbU8pcYLQYgLYxtBxIbjgG1MBKjxfBGmplkb1uy8YZjaQYHe86l80jcIKBF7kbyM4mfbXay85sPP3zwo8xajn8GAS0o4AAQ85CgfhSMglEwCkYBLgAAt/NBOGjs8EoAAAAASUVORK5CYII=","orcid":"https://orcid.org/0000-0003-3999-2206","institution":"School of Engineering Science, University of Science and Technology of China","correspondingAuthor":true,"prefix":"","firstName":"Huaian","middleName":"","lastName":"Chen","suffix":""},{"id":573993841,"identity":"8d061877-21ba-4072-96ad-6fb19339de3f","order_by":1,"name":"Shiyao Hong","email":"","orcid":"https://orcid.org/0009-0008-5778-1203","institution":"School of Engineering Science, University of Science and Technology of China","correspondingAuthor":false,"prefix":"","firstName":"Shiyao","middleName":"","lastName":"Hong","suffix":""},{"id":573993842,"identity":"1add8dcf-76b2-4aff-b722-c30a24aac108","order_by":2,"name":"Yuxuan Gu","email":"","orcid":"https://orcid.org/0009-0004-7994-8589","institution":"School of Engineering Science, University of Science and Technology of China","correspondingAuthor":false,"prefix":"","firstName":"Yuxuan","middleName":"","lastName":"Gu","suffix":""},{"id":573999379,"identity":"4ccc543d-0da9-4108-a43e-a0779db32b16","order_by":3,"name":"Junkang Dai","email":"","orcid":"https://orcid.org/0009-0008-6652-2801","institution":"School of Engineering Science, University of Science and Technology of China","correspondingAuthor":false,"prefix":"","firstName":"Junkang","middleName":"","lastName":"Dai","suffix":""},{"id":574000352,"identity":"aa253b0e-d23d-4e3c-b2de-914caa4fba79","order_by":4,"name":"Zhixiang Wei","email":"","orcid":"https://orcid.org/0000-0003-1835-8468","institution":"School of Engineering Science, University of Science and Technology of China","correspondingAuthor":false,"prefix":"","firstName":"Zhixiang","middleName":"","lastName":"Wei","suffix":""},{"id":574002310,"identity":"c005bee9-dccd-4876-b090-047993676076","order_by":5,"name":"Liyang He","email":"","orcid":"","institution":"School of Engineering Science, University of Science and Technology of China","correspondingAuthor":false,"prefix":"","firstName":"Liyang","middleName":"","lastName":"He","suffix":""},{"id":574002311,"identity":"02fdff51-e1b6-4859-bc82-c3a99f35dcc7","order_by":6,"name":"Bo Xu","email":"","orcid":"","institution":"The Center for Reproductive and Genetics, Department of Obstetrics and Gynecology, The First Affiliated Hospital of USTC, Division of Life Sciences and Medicine, University of Science and Technology of China","correspondingAuthor":false,"prefix":"","firstName":"Bo","middleName":"","lastName":"Xu","suffix":""},{"id":574002312,"identity":"8d9c42e2-a046-45a3-89ee-6589625d6606","order_by":7,"name":"Yi Jin","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA0ElEQVRIiWNgGAWjYBACxmYgkWBgIwflMxOrpSLNGKqaCC0QcOZwYgPRWpjbeY9JPGxLS99w/vzBDwwV1okN7GcPEHAYX5pEYptN7oYbycwSDGfSExt48hIIaOExA2pJA2phZmNgbAO6UILHgBgth9MNzh8GavlHrJaEM4cTDA4kA7U0EKfF2AIYyIYzbyQbSyQcSzdu48nBr8Ww/4zhzR8GNvJ85w8+/PChxlq2n/0MAS0NDCwScF4CELPhVQ8E8sCo+UBI0SgYBaNgFIxwAAB5VEI2g7ecHAAAAABJRU5ErkJggg==","orcid":"","institution":"School of Engineering Science, University of Science and Technology of China","correspondingAuthor":true,"prefix":"","firstName":"Yi","middleName":"","lastName":"Jin","suffix":""},{"id":574002313,"identity":"a970b039-bb59-4547-b067-861ec756cc7d","order_by":8,"name":"Enhong Chen","email":"","orcid":"https://orcid.org/0000-0002-4835-4102","institution":"The School of Computer Science and Technology, University of Science and Technology of China","correspondingAuthor":false,"prefix":"","firstName":"Enhong","middleName":"","lastName":"Chen","suffix":""}],"badges":[],"createdAt":"2025-12-11 09:20:59","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-8334792/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8334792/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":100371456,"identity":"6426bf8a-7e0d-4d32-963d-d4d4205893a1","added_by":"auto","created_at":"2026-01-16 08:10:16","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":7443614,"visible":true,"origin":"","legend":"","description":"","filename":"fluogen.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8334792/v1_covered_163ca4c9-9760-472a-b623-b49e9564978a.pdf"},{"id":100240514,"identity":"da12dc1f-359e-49a4-963d-8f4bb49a57f4","added_by":"auto","created_at":"2026-01-14 13:20:49","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":666988,"visible":true,"origin":"","legend":"","description":"","filename":"supp.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8334792/v1/52e864a163904caa31c094a9.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003eFluoGen: An Open-Source Generative Foundation Model for Fluorescence Microscopy Image Enhancement and Analysis\u003c/p\u003e","fulltext":[],"fulltextSource":"","fullText":"","funders":[{"identity":"7495edad-3ffc-4c7d-87a4-841d78ddf173","identifier":"10.13039/501100001809","name":"National Natural Science Foundation of China","awardNumber":"62571506","order_by":0},{"identity":"b36e34d5-6a22-4a44-a0b1-e0a951d37044","identifier":"10.13039/501100001809","name":"National Natural Science Foundation of China","awardNumber":"62401532","order_by":1},{"identity":"72971d0b-a18a-47a3-8cea-ee3aececb8fd","identifier":"10.13039/501100003995","name":"Natural Science Foundation of Anhui Province","awardNumber":"2408085J024","order_by":2},{"identity":"d47aaf12-ea83-4d25-92a6-102e9916936f","identifier":"10.13039/501100003995","name":"Natural Science Foundation of Anhui Province","awardNumber":"2308085QF226","order_by":3}],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"University of Science and Technology of China","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":"Artificial intelligence, diffusion model, fluorescence microscopy, image generation, image analysis","lastPublishedDoi":"10.21203/rs.3.rs-8334792/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8334792/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eFluorescence microscopy, empowered by artificial intelligence (AI), has shown great promise in advancing life science. However, the high cost and complexity of sample preparation limit the availability of training data, constraining the performance of AI-based models. Here, we present FluoGen, a diffusion-based generative foundation model designed to improve AI-based fluorescence image processing under data-constrained conditions. By pretraining on 3.5 million fluorescence images with a reformulated learning objective, FluoGen learns rich biological representations and mitigates inherent biases in conventional diffusion models. We demonstrate that FluoGen can serve as a backbone for image enhancement, enabling models to recover cellular and subcellular structures with substantially limited samples. Furthermore, FluoGen can reduce the training data required by existing AI-based analysis models to approximately 2% of the original amount while boosting the performance of state-of-the-art methods without architectural modifications. We anticipate that FluoGen serves as a foundation tool for advancing AI applications in fluorescence imaging.\u003c/p\u003e","manuscriptTitle":"FluoGen: An Open-Source Generative Foundation Model for Fluorescence Microscopy Image Enhancement and Analysis","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-01-14 13:20:45","doi":"10.21203/rs.3.rs-8334792/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":"50a27b00-0f14-4542-bf6c-fc096ffc6d9b","owner":[],"postedDate":"January 14th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":61078265,"name":"Artificial Intelligence and Machine Learning"},{"id":61078266,"name":"Biotechnology and Bioengineering"}],"tags":[],"updatedAt":"2026-01-14T13:20:45+00:00","versionOfRecord":[],"versionCreatedAt":"2026-01-14 13:20:45","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8334792","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8334792","identity":"rs-8334792","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}