Prediction of PD-L1 tumor positive score in lung squamous cell carcinoma with H&E staining whole slide images and deep learning

Prediction of PD-L1 tumor positive score in lung squamous cell carcinoma with H&E staining whole slide images and deep learning | 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 Research Article Prediction of PD-L1 tumor positive score in lung squamous cell carcinoma with H&E staining whole slide images and deep learning Qiushi Wang, Xixiang Deng, Pan Huang, Qiang Ma, Lianhua Zhao, and 8 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-3887214/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 Purpose Detecting programmed death ligand 1 (PD-L1) expression based on immunohistochemical (IHC) staining is an important guide for the treatment of lung cancer with immune checkpoint inhibitors. However, this method has problems such as high staining costs, tumor heterogeneity, and subjective differences among pathologists. Therefore, the application of deep learning models to segment and quantitatively predict PD-L1 expression in digital sections of Hematoxylin and eosin (H&E) stained lung squamous cell carcinoma is of great significance. Materials and Methods We constructed a dataset comprising H&E-stained digital sections of lung squamous cell carcinoma and used a Transformer Unet (TransUnet) deep learning network with an encoder-decoder design to segment PD-L1 negative and positive regions and quantitatively predict the tumor cell positive score (TPS). Results The results showed that the dice similarity coefficient (DSC) and intersection overunion(IoU) of deep learning for PD-L1 expression segmentation of H&E-stained digital slides of lung squamous cell carcinoma were 80% and 72%, respectively, which were better than the other seven cutting-edge segmentation models. The root mean square error (RMSE) of quantitative prediction TPS was 26.8, and the intra-group correlation coefficients with the gold standard was 0.92 (95% CI: 0.90–0.93), which was better than the consistency between the results of five pathologists and the gold standard. Conclusion The deep learning model is capable of segmenting and quantitatively predicting PD-L1 expression in H&E-stained digital sections of lung squamous cell carcinoma, which has significant implications for the application and guidance of immune checkpoint inhibitor treatments. Lung squamous cell carcinoma PD-L1 Deep learning TransUnet H&E staining Full Text Additional Declarations No competing interests reported. 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-3887214","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":268581028,"identity":"498d9434-825b-4217-b16e-1f338030a3bd","order_by":0,"name":"Qiushi Wang","email":"","orcid":"","institution":"Army Medical University","correspondingAuthor":false,"prefix":"","firstName":"Qiushi","middleName":"","lastName":"Wang","suffix":""},{"id":268581029,"identity":"d5869b67-e05a-401e-ae98-0e16b9804319","order_by":1,"name":"Xixiang Deng","email":"","orcid":"","institution":"Chongqing University","correspondingAuthor":false,"prefix":"","firstName":"Xixiang","middleName":"","lastName":"Deng","suffix":""},{"id":268581030,"identity":"c629e840-0f95-43c5-8b5f-d93ed15e6235","order_by":2,"name":"Pan Huang","email":"","orcid":"","institution":"Chongqing University","correspondingAuthor":false,"prefix":"","firstName":"Pan","middleName":"","lastName":"Huang","suffix":""},{"id":268581031,"identity":"3f0a00fb-5774-41b1-9c77-5607ba4ea76a","order_by":3,"name":"Qiang Ma","email":"","orcid":"","institution":"Army Medical University","correspondingAuthor":false,"prefix":"","firstName":"Qiang","middleName":"","lastName":"Ma","suffix":""},{"id":268581032,"identity":"b8341990-b149-4cd2-9e1d-743881d48eb8","order_by":4,"name":"Lianhua Zhao","email":"","orcid":"","institution":"Army Medical University","correspondingAuthor":false,"prefix":"","firstName":"Lianhua","middleName":"","lastName":"Zhao","suffix":""},{"id":268581033,"identity":"c3eaabb0-6ec4-44fa-b561-05424102f718","order_by":5,"name":"Yangyang Feng","email":"","orcid":"","institution":"Army Medical University","correspondingAuthor":false,"prefix":"","firstName":"Yangyang","middleName":"","lastName":"Feng","suffix":""},{"id":268581034,"identity":"52037733-e7d1-482a-93d8-9d9fa114d32f","order_by":6,"name":"Yiying Wang","email":"","orcid":"","institution":"Army Medical University","correspondingAuthor":false,"prefix":"","firstName":"Yiying","middleName":"","lastName":"Wang","suffix":""},{"id":268581035,"identity":"a437a604-cdc0-468d-8f47-6db4479d3984","order_by":7,"name":"Yuan Zhao","email":"","orcid":"","institution":"Army Medical University","correspondingAuthor":false,"prefix":"","firstName":"Yuan","middleName":"","lastName":"Zhao","suffix":""},{"id":268581036,"identity":"0964498d-e71b-46fe-98e7-87df67e36bac","order_by":8,"name":"Yan Chen","email":"","orcid":"","institution":"Army Medical University","correspondingAuthor":false,"prefix":"","firstName":"Yan","middleName":"","lastName":"Chen","suffix":""},{"id":268581037,"identity":"89355a3c-ab03-4c25-a190-799d02d68f94","order_by":9,"name":"Peng Zhong","email":"","orcid":"","institution":"Army Medical University","correspondingAuthor":false,"prefix":"","firstName":"Peng","middleName":"","lastName":"Zhong","suffix":""},{"id":268581038,"identity":"1a330ba4-fd0e-46f4-b6f1-936dd98276fa","order_by":10,"name":"Peng He","email":"","orcid":"","institution":"Chongqing University","correspondingAuthor":false,"prefix":"","firstName":"Peng","middleName":"","lastName":"He","suffix":""},{"id":268581039,"identity":"c2581d4c-e61d-4bda-a086-70f6c7fe0a05","order_by":11,"name":"Peng Feng","email":"","orcid":"","institution":"Chongqing University","correspondingAuthor":false,"prefix":"","firstName":"Peng","middleName":"","lastName":"Feng","suffix":""},{"id":268581040,"identity":"142b0a8a-cff3-46d3-b932-f9464a758ee3","order_by":12,"name":"Hualiang Xiao","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAuElEQVRIiWNgGAWjYDCCAzyMB4CkDD8z88EHxGphAGnhkWxnSzYgTYvBeR4zAaJ08N3uPXCAse0Oj/FhBjMGhhqbaIJaJO+cSzjAcOYZj9lhhrQHDMfSchsIaTG4kWNwgKHiMEjLcQPGhsPEajE4zGPczNgmQYIWoC0GzMxsxGmB+uUwj8RhNmaDBGL8Agyxgw8Y2w7L8fef//jgQ40NYS0MEgwMzH9gnASCyqFaRsEoGAWjYBTgBwCed0PIsSBzcwAAAABJRU5ErkJggg==","orcid":"","institution":"Army Medical University","correspondingAuthor":true,"prefix":"","firstName":"Hualiang","middleName":"","lastName":"Xiao","suffix":""}],"badges":[],"createdAt":"2024-01-22 07:29:12","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-3887214/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-3887214/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":51199361,"identity":"2a9b070f-d5fe-4915-9aeb-62f9f1b97b62","added_by":"auto","created_at":"2024-02-15 20:08:50","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1313980,"visible":true,"origin":"","legend":"","description":"","filename":"ManuscriptV32024.01.22.pdf","url":"https://assets-eu.researchsquare.com/files/rs-3887214/v1_covered_deb00030-26c3-466e-b0dc-02dfba1200a2.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Prediction of PD-L1 tumor positive score in lung squamous cell carcinoma with H\u0026E staining whole slide images and deep learning","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"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":"Lung squamous cell carcinoma, PD-L1, Deep learning, TransUnet, H\u0026E staining","lastPublishedDoi":"10.21203/rs.3.rs-3887214/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-3887214/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003ch2\u003ePurpose\u003c/h2\u003e \u003cp\u003eDetecting programmed death ligand 1 (PD-L1) expression based on immunohistochemical (IHC) staining is an important guide for the treatment of lung cancer with immune checkpoint inhibitors. However, this method has problems such as high staining costs, tumor heterogeneity, and subjective differences among pathologists. Therefore, the application of deep learning models to segment and quantitatively predict PD-L1 expression in digital sections of Hematoxylin and eosin (H\u0026amp;E) stained lung squamous cell carcinoma is of great significance.\u003c/p\u003e\u003ch2\u003eMaterials and Methods\u003c/h2\u003e \u003cp\u003eWe constructed a dataset comprising H\u0026amp;E-stained digital sections of lung squamous cell carcinoma and used a Transformer Unet (TransUnet) deep learning network with an encoder-decoder design to segment PD-L1 negative and positive regions and quantitatively predict the tumor cell positive score (TPS).\u003c/p\u003e\u003ch2\u003eResults\u003c/h2\u003e \u003cp\u003eThe results showed that the dice similarity coefficient (DSC) and intersection overunion(IoU) of deep learning for PD-L1 expression segmentation of H\u0026amp;E-stained digital slides of lung squamous cell carcinoma were 80% and 72%, respectively, which were better than the other seven cutting-edge segmentation models. The root mean square error (RMSE) of quantitative prediction TPS was 26.8, and the intra-group correlation coefficients with the gold standard was 0.92 (95% CI: 0.90\u0026ndash;0.93), which was better than the consistency between the results of five pathologists and the gold standard.\u003c/p\u003e\u003ch2\u003eConclusion\u003c/h2\u003e \u003cp\u003eThe deep learning model is capable of segmenting and quantitatively predicting PD-L1 expression in H\u0026amp;E-stained digital sections of lung squamous cell carcinoma, which has significant implications for the application and guidance of immune checkpoint inhibitor treatments.\u003c/p\u003e","manuscriptTitle":"Prediction of PD-L1 tumor positive score in lung squamous cell carcinoma with H\u0026amp;E staining whole slide images and deep learning","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-01-24 05:31:21","doi":"10.21203/rs.3.rs-3887214/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":"24f3f896-61a8-4e40-9384-a210ba87b5f3","owner":[],"postedDate":"January 24th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2024-02-15T20:00:37+00:00","versionOfRecord":[],"versionCreatedAt":"2024-01-24 05:31:21","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-3887214","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-3887214","identity":"rs-3887214","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}