Three-dimensional H&E histopathology powered by deep learning-assisted multimodal nonlinear microscopy

Three-dimensional H&E histopathology powered by deep learning-assisted multimodal nonlinear microscopy | 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 Three-dimensional H&E histopathology powered by deep learning-assisted multimodal nonlinear microscopy Virginijus Barzda, Martynas Riauka, Linas Petkevicius, Viktoras Mazeika, and 12 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7402116/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted You are reading this latest preprint version Abstract The diagnostic and prognostic potential of histopathology can be significantly enhanced with three-dimensional (3D) imaging. Histopathology relies on the gold-standard 2D inspection of hematoxylin and eosin (H&E)-stained tissue sections with a brightfield microscope. We introduce a novel methodology termed nonlinear-H&E (N-H&E) that utilizes inherent optical sectioning of nonlinear microscopy for 3D volumetric investigations. Multimodal multiphoton excitation fluorescence (MPF) and third-harmonic generation (THG) microscopy is employed to image fluorescent and nonfluorescent structures. The optical sections are used to create 3D brightfield-equivalent H&E volumes by employing a generative adversarial network (GAN)-based image-to-image translation. N-H&E generates realistic 2D and 3D brightfield images with enhanced axial resolution. Furthermore, polarimetric second-harmonic generation (P-SHG) is applied to visualize the 3D collagen architecture. The overlay of volumetric P-SHG and GAN-generated H&E images provides an enriched view of tumor microenvironment for 3D histopathology. Reconstructed images meet standards for visual quality, structural accuracy, and clinical assessment reliability. Biological sciences/Biological techniques/Microscopy/Multiphoton microscopy Biological sciences/Cancer/Cancer imaging Biological sciences/Cancer/Cancer microenvironment Biological sciences/Computational biology and bioinformatics/Image processing Biological sciences/Computational biology and bioinformatics/Machine learning Full Text Additional Declarations There is NO Competing Interest. Supplementary Files NHnESupplementaryMaterialsMR.pdf Supplementary Materials SupplementaryVideo1.mp4 Supplementary Video 1 SupplementaryVideo2.mp4 Supplementary Video 2 Cite Share Download PDF Status: Under Review 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-7402116","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":517556017,"identity":"7c781911-c16d-4aa9-9434-b243db36bf6a","order_by":0,"name":"Virginijus Barzda","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABAElEQVRIiWNgGAWjYDACZiBOACMGBgmGCtK1nAFiEDhAhE6IFsY2IrQYHOd9/OLBH4Y8/tnHH974Oe9wHb/04WOPP1QwyPM34NBymN3MIrGNoVjiXEKyZe+2wxKSfWnpBgfOMBjOwGGVZDMbm0FiA0NiwxmGYxK8QC0GZ3jMJA62AZ2KT0vCH4bE+WcY2yT/zkHSIo9DCz8zG/ODBDaGxA1nmNmkeRuQtBjg1gJU3yZRbHiGjdla5li65MwetjSJM2ckDDfi0MLGf4z5448/NnlyZ9gf3nxTY83Pz8N8TKKiwkZeDocWkC4JBmhsIANMESTA/AGf7CgYBaNgFIwCBgCru1SQFnVHzAAAAABJRU5ErkJggg==","orcid":"https://orcid.org/0000-0003-0669-9513","institution":"University of Toronto","correspondingAuthor":true,"prefix":"","firstName":"Virginijus","middleName":"","lastName":"Barzda","suffix":""},{"id":517556018,"identity":"273a7960-7716-4db0-82de-d6151b1038be","order_by":1,"name":"Martynas Riauka","email":"","orcid":"","institution":"Vilnius University","correspondingAuthor":false,"prefix":"","firstName":"Martynas","middleName":"","lastName":"Riauka","suffix":""},{"id":517556019,"identity":"3bb62763-13da-4d20-8e3c-49001a9e78b9","order_by":2,"name":"Linas Petkevicius","email":"","orcid":"","institution":"Vilnius University","correspondingAuthor":false,"prefix":"","firstName":"Linas","middleName":"","lastName":"Petkevicius","suffix":""},{"id":517556020,"identity":"2e3b02c2-2c07-4e53-b35e-6541374ed2f4","order_by":3,"name":"Viktoras Mazeika","email":"","orcid":"","institution":"Vilnius University","correspondingAuthor":false,"prefix":"","firstName":"Viktoras","middleName":"","lastName":"Mazeika","suffix":""},{"id":517556021,"identity":"f7d77a9d-d848-4454-816c-885f724353fa","order_by":4,"name":"Vincas Urbonas","email":"","orcid":"","institution":"National Cancer Institute","correspondingAuthor":false,"prefix":"","firstName":"Vincas","middleName":"","lastName":"Urbonas","suffix":""},{"id":517556022,"identity":"67a8e6be-440d-475e-8c75-acaef4a3e744","order_by":5,"name":"Edvardas Zurauskas","email":"","orcid":"","institution":"National Centre of Pathology","correspondingAuthor":false,"prefix":"","firstName":"Edvardas","middleName":"","lastName":"Zurauskas","suffix":""},{"id":517556023,"identity":"0c45dbc2-3a9a-4dce-b3dd-6a635fd3c3c0","order_by":6,"name":"Darius Dasevicius","email":"","orcid":"","institution":"National Center of Pathology","correspondingAuthor":false,"prefix":"","firstName":"Darius","middleName":"","lastName":"Dasevicius","suffix":""},{"id":517556024,"identity":"860aa3e4-73e7-4cf2-964c-5f6f44bc263e","order_by":7,"name":"Elena Osteikaite","email":"","orcid":"https://orcid.org/0009-0006-0574-4107","institution":"Vilnius University","correspondingAuthor":false,"prefix":"","firstName":"Elena","middleName":"","lastName":"Osteikaite","suffix":""},{"id":517556025,"identity":"a18a56bb-3ba1-4f3c-9c8f-55efb0ccc19a","order_by":8,"name":"Austeja Bareikyte","email":"","orcid":"","institution":"Vilnius University","correspondingAuthor":false,"prefix":"","firstName":"Austeja","middleName":"","lastName":"Bareikyte","suffix":""},{"id":517556026,"identity":"d8449011-f2b3-4f23-9344-306ca334e4c6","order_by":9,"name":"Mykolas Maciulis","email":"","orcid":"","institution":"Vilnius University","correspondingAuthor":false,"prefix":"","firstName":"Mykolas","middleName":"","lastName":"Maciulis","suffix":""},{"id":517556027,"identity":"2d4b7ac4-2f7c-4caf-acac-60c17e672904","order_by":10,"name":"Lukas Kontenis","email":"","orcid":"","institution":"Light Conversion","correspondingAuthor":false,"prefix":"","firstName":"Lukas","middleName":"","lastName":"Kontenis","suffix":""},{"id":517556028,"identity":"0efb66f6-91de-4789-9623-334f66b121c3","order_by":11,"name":"Povilas Malakauskas","email":"","orcid":"","institution":"National Center of Pathology","correspondingAuthor":false,"prefix":"","firstName":"Povilas","middleName":"","lastName":"Malakauskas","suffix":""},{"id":517556029,"identity":"816d0f97-b60e-47ec-91e8-76db332799b6","order_by":12,"name":"Vita Pasukoniene","email":"","orcid":"","institution":"National Cancer Institute","correspondingAuthor":false,"prefix":"","firstName":"Vita","middleName":"","lastName":"Pasukoniene","suffix":""},{"id":517556030,"identity":"95326d12-b543-42ad-8574-e06334c009fa","order_by":13,"name":"Margarita Zvirble","email":"","orcid":"","institution":"National Cancer Institute","correspondingAuthor":false,"prefix":"","firstName":"Margarita","middleName":"","lastName":"Zvirble","suffix":""},{"id":517556031,"identity":"de10d75a-7a97-4fd2-84d0-aabba0bafcf7","order_by":14,"name":"Aida Laurinaviciene","email":"","orcid":"","institution":"National Center of Pathology","correspondingAuthor":false,"prefix":"","firstName":"Aida","middleName":"","lastName":"Laurinaviciene","suffix":""},{"id":517556032,"identity":"ba6eb007-6266-44d7-927c-2f366a26f49e","order_by":15,"name":"Arvydas Laurinavicius","email":"","orcid":"","institution":"National Center of Pathology","correspondingAuthor":false,"prefix":"","firstName":"Arvydas","middleName":"","lastName":"Laurinavicius","suffix":""}],"badges":[],"createdAt":"2025-08-18 18:00:11","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7402116/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7402116/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":94595541,"identity":"e6bf7b3f-d5b4-476e-a009-57f5019ce051","added_by":"auto","created_at":"2025-10-28 18:34:27","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":12405768,"visible":true,"origin":"","legend":"Article File","description":"","filename":"NHnEMainTextMR.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7402116/v1_covered_f02ba04f-38df-4fe5-8334-7989640356ae.pdf"},{"id":94585349,"identity":"df063df6-c5ae-41af-90b8-9a24793ac5f3","added_by":"auto","created_at":"2025-10-28 18:16:05","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":7482391,"visible":true,"origin":"","legend":"Supplementary Materials","description":"","filename":"NHnESupplementaryMaterialsMR.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7402116/v1/0cae2ada0fa778ce64e0b41a.pdf"},{"id":94584442,"identity":"8a37ec75-4ae5-40e7-bc57-405ceee9ca40","added_by":"auto","created_at":"2025-10-28 18:15:12","extension":"mp4","order_by":2,"title":"","display":"","copyAsset":false,"role":"supplement","size":51314023,"visible":true,"origin":"","legend":"Supplementary Video 1","description":"","filename":"SupplementaryVideo1.mp4","url":"https://assets-eu.researchsquare.com/files/rs-7402116/v1/53abb4848a908b6d2ac39551.mp4"},{"id":94584224,"identity":"ee210160-22cf-440d-9e70-0b8cd9afc8bd","added_by":"auto","created_at":"2025-10-28 18:15:03","extension":"mp4","order_by":3,"title":"","display":"","copyAsset":false,"role":"supplement","size":69338662,"visible":true,"origin":"","legend":"Supplementary Video 2","description":"","filename":"SupplementaryVideo2.mp4","url":"https://assets-eu.researchsquare.com/files/rs-7402116/v1/37476d1887fb1cd3bd85dd7c.mp4"}],"financialInterests":"There is \u003cb\u003eNO\u003c/b\u003e Competing Interest.","formattedTitle":"Three-dimensional H\u0026amp;E histopathology powered by deep learning-assisted multimodal nonlinear microscopy","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":true,"email":"[email protected]","identity":"nature-portfolio","isNatureJournal":true,"hasQc":false,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"","title":"Nature Portfolio","twitterHandle":"","acdcEnabled":false,"dfaEnabled":false,"editorialSystem":"ejp","reportingPortfolio":"","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"","lastPublishedDoi":"10.21203/rs.3.rs-7402116/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7402116/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"The diagnostic and prognostic potential of histopathology can be significantly enhanced with three-dimensional (3D) imaging. Histopathology relies on the gold-standard 2D inspection of hematoxylin and eosin (H\u0026E)-stained tissue sections with a brightfield microscope. We introduce a novel methodology termed nonlinear-H\u0026E (N-H\u0026E) that utilizes inherent optical sectioning of nonlinear microscopy for 3D volumetric investigations. Multimodal multiphoton excitation fluorescence (MPF) and third-harmonic generation (THG) microscopy is employed to image fluorescent and nonfluorescent structures. The optical sections are used to create 3D brightfield-equivalent H\u0026E volumes by employing a generative adversarial network (GAN)-based image-to-image translation. N-H\u0026E generates realistic 2D and 3D brightfield images with enhanced axial resolution. Furthermore, polarimetric second-harmonic generation (P-SHG) is applied to visualize the 3D collagen architecture. The overlay of volumetric P-SHG and GAN-generated H\u0026E images provides an enriched view of tumor microenvironment for 3D histopathology. Reconstructed images meet standards for visual quality, structural accuracy, and clinical assessment reliability.","manuscriptTitle":"Three-dimensional H\u0026amp;E histopathology powered by deep learning-assisted multimodal nonlinear microscopy","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-10-28 16:31:49","doi":"10.21203/rs.3.rs-7402116/v1","editorialEvents":[],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"communications-biology","isNatureJournal":true,"hasQc":false,"allowDirectSubmit":false,"externalIdentity":"commsbio","sideBox":"Learn more about [Communications Biology](http://www.nature.com/commsbio/)","snPcode":"","submissionUrl":"","title":"Communications Biology","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"ejp","reportingPortfolio":"Communications Series","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"f365c951-7fc5-49cf-ae55-9a4f93e30860","owner":[],"postedDate":"October 28th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[{"id":55003071,"name":"Biological sciences/Biological techniques/Microscopy/Multiphoton microscopy"},{"id":55003072,"name":"Biological sciences/Cancer/Cancer imaging"},{"id":55003073,"name":"Biological sciences/Cancer/Cancer microenvironment"},{"id":55003074,"name":"Biological sciences/Computational biology and bioinformatics/Image processing"},{"id":55003075,"name":"Biological sciences/Computational biology and bioinformatics/Machine learning"}],"tags":[],"updatedAt":"2025-10-28T16:31:49+00:00","versionOfRecord":[],"versionCreatedAt":"2025-10-28 16:31:49","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7402116","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7402116","identity":"rs-7402116","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}