Enhanced Confocal Microscopy with Physics-Informed Deep Autoencoders

Enhanced Confocal Microscopy with Physics-Informed Deep Autoencoders | 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 Enhanced Confocal Microscopy with Physics-Informed Deep Autoencoders Zaheer Ahmad, Junaid Shabeer, Abdullah Hidayat, Usman Saleem, and 6 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6709432/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 07 Jan, 2026 Read the published version in Scientific Reports → Version 1 posted 11 You are reading this latest preprint version Abstract We present a physics-informed deep learning framework to address common limitations in Confocal Laser Scanning Microscopy (CLSM), including diffraction-limited resolution, noise, and under sampling due to low laser power conditions. The optical system’s point spread function and primary CLSM image degradation mechanisms, namely photon shot noise, dark current noise, motion blur, speckle noise, and under sampling are explicitly incorporated into the model as physics-based constraints. A convolutional autoencoder is trained with a custom loss function that integrates these optical degradation processes, ensuring that the reconstructed images adhere to physical image formation principles. The model is evaluated on simulated CLSM datasets generated based on experimentally observed CLSM noise characteristics. Statistical comparisons, including intensity histograms, spatial frequency distributions, and structural similarity metrics, confirm that the synthetic dataset closely matches accurate CLSM data. The proposed approach is compared with traditional image reconstruction methods, including Richardson-Lucy deconvolution, non-negative least squares, and total variation regularization. Results indicate that the physics-constrained autoencoder improves structural detail recovery while maintaining consistency with known CLSM imaging physics. This study demonstrates that physics-informed deep learning can provide an alternative computational approach to CLSM enhancement, complementing existing optical correction methods. Future work will focus on further validation using experimental CLSM acquisitions. Physical sciences/Physics Physical sciences/Physics/Techniques and instrumentation Physical sciences/Physics/Techniques and instrumentation/Imaging techniques Confocal Laser Scanning Microscopy Physics-Informed Deep Learning Computational Imaging Optical Image Formation Image Restoration CLSM Noise Reduction Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 07 Jan, 2026 Read the published version in Scientific Reports → Version 1 posted Editorial decision: Revision requested 19 Jun, 2025 Reviews received at journal 18 Jun, 2025 Reviews received at journal 18 Jun, 2025 Reviewers agreed at journal 09 Jun, 2025 Reviewers agreed at journal 08 Jun, 2025 Reviewers agreed at journal 08 Jun, 2025 Reviewers invited by journal 08 Jun, 2025 Editor assigned by journal 08 Jun, 2025 Editor invited by journal 03 Jun, 2025 Submission checks completed at journal 03 Jun, 2025 First submitted to journal 20 May, 2025 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-6709432","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":459438055,"identity":"76076477-0e4d-4188-8e2c-65bd46b37a17","order_by":0,"name":"Zaheer Ahmad","email":"","orcid":"","institution":"Georgia State University","correspondingAuthor":false,"prefix":"","firstName":"Zaheer","middleName":"","lastName":"Ahmad","suffix":""},{"id":459438056,"identity":"8e14afb0-2208-43be-a63d-5d703607f8b7","order_by":1,"name":"Junaid Shabeer","email":"","orcid":"","institution":"Riphah International University","correspondingAuthor":false,"prefix":"","firstName":"Junaid","middleName":"","lastName":"Shabeer","suffix":""},{"id":459438057,"identity":"941c461d-a16c-40aa-96a7-1cf5ff45339a","order_by":2,"name":"Abdullah Hidayat","email":"","orcid":"","institution":"Florida Atlantic University","correspondingAuthor":false,"prefix":"","firstName":"Abdullah","middleName":"","lastName":"Hidayat","suffix":""},{"id":459438058,"identity":"7a28111f-87b4-42cd-ac1a-03a18507ffb8","order_by":3,"name":"Usman Saleem","email":"","orcid":"","institution":"Roots IVY","correspondingAuthor":false,"prefix":"","firstName":"Usman","middleName":"","lastName":"Saleem","suffix":""},{"id":459438059,"identity":"1434d8bc-8e09-49d2-ad91-4bc779b39280","order_by":4,"name":"Tahir Qadeer","email":"","orcid":"","institution":"Arid Agriculture University","correspondingAuthor":false,"prefix":"","firstName":"Tahir","middleName":"","lastName":"Qadeer","suffix":""},{"id":459438060,"identity":"af1228fc-3373-4a20-9d92-3fefe5413396","order_by":5,"name":"Abdul Sami","email":"","orcid":"","institution":"Roots IVY","correspondingAuthor":false,"prefix":"","firstName":"Abdul","middleName":"","lastName":"Sami","suffix":""},{"id":459438061,"identity":"ebf22849-5d39-454e-9a5b-c61c47c07a55","order_by":6,"name":"Zahira El Khalidi","email":"","orcid":"","institution":"University of Illinois","correspondingAuthor":false,"prefix":"","firstName":"Zahira","middleName":"El","lastName":"Khalidi","suffix":""},{"id":459438062,"identity":"2317129b-397c-4de7-8ab0-cdec996eb2af","order_by":7,"name":"Saad Mehmood","email":"","orcid":"","institution":"University of Central Florida","correspondingAuthor":false,"prefix":"","firstName":"Saad","middleName":"","lastName":"Mehmood","suffix":""},{"id":459438063,"identity":"7d791fbd-fab7-4006-88f6-ee1b462b0a9c","order_by":8,"name":"Shyam Pokharel","email":"","orcid":"","institution":"Lynn Cancer Institute - Radiation Oncology, Boca Raton Regional Hospital","correspondingAuthor":false,"prefix":"","firstName":"Shyam","middleName":"","lastName":"Pokharel","suffix":""},{"id":459438064,"identity":"13484380-2560-47af-9839-b7fe3e451819","order_by":9,"name":"Wazir Muhammad","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAvklEQVRIiWNgGAWjYHACNgh1vPEBiGJsIF7LmcMGpGq5kUykFoNrZ8we/MzZJs938zHjZx4GG9kNBwhpuZ1jbti77bbhzNvJzNI8DGnGBLWY3c4xk+Dddptxw+38A0AthxOJ0iL5d9tt+w03DzP/5mH4T5wWaaAtiRtuMLMBbTlAWIv97bQyadltt5Nnnklms5xjkGw8k5AWydnJ2yTfbrtt23f8MPONNxV2sn2EtKABA9KUj4JRMApGwSjAAQAonUg+YYZbbgAAAABJRU5ErkJggg==","orcid":"","institution":"Florida Atlantic University","correspondingAuthor":true,"prefix":"","firstName":"Wazir","middleName":"","lastName":"Muhammad","suffix":""}],"badges":[],"createdAt":"2025-05-20 15:53:14","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6709432/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6709432/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1038/s41598-025-34839-x","type":"published","date":"2026-01-07T15:57:28+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":100069130,"identity":"d6cff51f-73f7-494c-b212-7381ddfda944","added_by":"auto","created_at":"2026-01-12 16:10:09","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":2018643,"visible":true,"origin":"","legend":"","description":"","filename":"Manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6709432/v1_covered_be49ccb5-ed87-4b7e-a638-35e77eae0d41.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Enhanced Confocal Microscopy with Physics-Informed Deep Autoencoders","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":true,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"Confocal Laser Scanning Microscopy, Physics-Informed Deep Learning, Computational Imaging, Optical Image Formation, Image Restoration, CLSM Noise Reduction","lastPublishedDoi":"10.21203/rs.3.rs-6709432/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6709432/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eWe present a physics-informed deep learning framework to address common limitations in Confocal Laser Scanning Microscopy (CLSM), including diffraction-limited resolution, noise, and under sampling due to low laser power conditions. The optical system\u0026rsquo;s point spread function and primary CLSM image degradation mechanisms, namely photon shot noise, dark current noise, motion blur, speckle noise, and under sampling are explicitly incorporated into the model as physics-based constraints. A convolutional autoencoder is trained with a custom loss function that integrates these optical degradation processes, ensuring that the reconstructed images adhere to physical image formation principles. The model is evaluated on simulated CLSM datasets generated based on experimentally observed CLSM noise characteristics. Statistical comparisons, including intensity histograms, spatial frequency distributions, and structural similarity metrics, confirm that the synthetic dataset closely matches accurate CLSM data. The proposed approach is compared with traditional image reconstruction methods, including Richardson-Lucy deconvolution, non-negative least squares, and total variation regularization. Results indicate that the physics-constrained autoencoder improves structural detail recovery while maintaining consistency with known CLSM imaging physics. This study demonstrates that physics-informed deep learning can provide an alternative computational approach to CLSM enhancement, complementing existing optical correction methods. Future work will focus on further validation using experimental CLSM acquisitions.\u003c/p\u003e","manuscriptTitle":"Enhanced Confocal Microscopy with Physics-Informed Deep Autoencoders","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-05-22 04:09:18","doi":"10.21203/rs.3.rs-6709432/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-06-19T06:45:50+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-06-18T11:46:11+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-06-18T07:57:16+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"2220587884733512839231444048832514560","date":"2025-06-09T09:03:34+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"266898177439296189785528692570132159745","date":"2025-06-09T01:51:08+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"119236630340825477757812896512464424624","date":"2025-06-08T20:50:21+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-06-08T19:25:55+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-06-08T19:17:58+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2025-06-03T11:32:06+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-06-03T05:17:42+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2025-05-20T15:44:09+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"5a3504ef-f5d1-4fa3-8365-f87800dccc3a","owner":[],"postedDate":"May 22nd, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[{"id":48807696,"name":"Physical sciences/Physics"},{"id":48807697,"name":"Physical sciences/Physics/Techniques and instrumentation"},{"id":48807698,"name":"Physical sciences/Physics/Techniques and instrumentation/Imaging techniques"}],"tags":[],"updatedAt":"2026-01-12T16:01:22+00:00","versionOfRecord":{"articleIdentity":"rs-6709432","link":"https://doi.org/10.1038/s41598-025-34839-x","journal":{"identity":"scientific-reports","isVorOnly":false,"title":"Scientific Reports"},"publishedOn":"2026-01-07 15:57:28","publishedOnDateReadable":"January 7th, 2026"},"versionCreatedAt":"2025-05-22 04:09:18","video":"","vorDoi":"10.1038/s41598-025-34839-x","vorDoiUrl":"https://doi.org/10.1038/s41598-025-34839-x","workflowStages":[]},"version":"v1","identity":"rs-6709432","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6709432","identity":"rs-6709432","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}