AirwayNet: Constructing Fine-Grained Airway Atlases

AirwayNet: Constructing Fine-Grained Airway Atlases | 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 AirwayNet: Constructing Fine-Grained Airway Atlases Yun Gu, Minghui Zhang, Chenyu Li, Fangfang Xie, Yaoyu Liu, Hanxiao Zhang, and 5 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6712546/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 Accurate anatomical labeling and analysis of the pulmonary structure and its surrounding anatomy from thoracic CT is becoming increasingly important for understanding the etiology of abnormalities or supporting targetted therapy and early interventions. Whilst lung and airway cell atlases have been attempted, there is a lack of fine-grained morphological atlases that are clinically deployable. In this work, we introduce AirwayNet, a robust, end-to-end deep learning pipeline enabling fully automatic and comprehensive airway anatomical labeling at lobar, segmental, and subsegmental resolutions that can be used to create digital atlases of the lung. Evaluated across large-scale multi-center datasets comprising diverse pulmonary conditions, the AirwayNet consistently outperformed existing analytical and labeling methods in terms of accuracy, topological consistency, and completeness. To simplify clinical interpretation, we further introduce a compact anatomical signature quantifying critical morphological airway features—including stenosis, ectasia, tortuosity, divergence, length, and complexity. When applied to various pulmonary diseases such as pulmonary fibrosis, emphysema, atelectasis, consolidation, and reticular opacities, it demonstrates strong discriminative power, revealing disease-specific morphological patterns with high interpretability and explainability. Additionally, the fine-grained atlas derived supports efficient automated branching pattern analysis, potentially enhancing bronchoscopic navigation planning and procedural safety, offering a valuable clinical tool for improved diagnosis, targeted treatment, and personalized patient care. Biological sciences/Computational biology and bioinformatics/Machine learning Biological sciences/Computational biology and bioinformatics/Image processing Pulmonary Airway Digital Atlas Topology Modeling Graph Transformer Full Text Additional Declarations There is NO Competing Interest. Supplementary Files supplmat.pdf The supplementary material 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-6712546","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":478682562,"identity":"fef1a5bb-d7e8-4566-9544-0e99df3a3da3","order_by":0,"name":"Yun Gu","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA6ElEQVRIiWNgGAWjYLACxn82cvwMDAlgdgNxetjSjCUbGBIbSNFyKHHDAYhqwlrk3XsfPi7gOcC4+fyB5495GGxkNxxgfvYAnxbDM8eNjWdI3GE2u5GQ2MzDkGa84QCbuQFeLTPS2KR5DJ6xmd1gAGk5DHQhD5sEXi3znwG1JBzmMe4/ANLyn7AWeQk2oJYDhyUMGMAOO0BYiwFPGrMxb0OagQTQLzPnGCQbzzzMZobflvZjjI95G2zq+/vPJHx4U2En23e8+Rl+Ww7AmTwJQC6QZsanHmRLA5zJfgCnqlEwCkbBKBjZAABd9khP/QswCAAAAABJRU5ErkJggg==","orcid":"https://orcid.org/0000-0002-4199-0675","institution":"Shanghai Jiao Tong University","correspondingAuthor":true,"prefix":"","firstName":"Yun","middleName":"","lastName":"Gu","suffix":""},{"id":478682563,"identity":"5041ace0-a4bd-448b-87d1-ec5e2ff68906","order_by":1,"name":"Minghui Zhang","email":"","orcid":"","institution":"Shanghai Jiao Tong University","correspondingAuthor":false,"prefix":"","firstName":"Minghui","middleName":"","lastName":"Zhang","suffix":""},{"id":478682564,"identity":"fc68f19b-8824-4d27-a6ed-a18c49439a8a","order_by":2,"name":"Chenyu Li","email":"","orcid":"https://orcid.org/0009-0001-2826-0926","institution":"Shanghai Jiao Tong University","correspondingAuthor":false,"prefix":"","firstName":"Chenyu","middleName":"","lastName":"Li","suffix":""},{"id":478682565,"identity":"04f90809-508a-42bf-802f-3f46e4c3ca2c","order_by":3,"name":"Fangfang Xie","email":"","orcid":"","institution":"Shanghai Chest Hospital","correspondingAuthor":false,"prefix":"","firstName":"Fangfang","middleName":"","lastName":"Xie","suffix":""},{"id":478682566,"identity":"99d7cf62-e359-4cc6-81b6-dadf59bec40e","order_by":4,"name":"Yaoyu Liu","email":"","orcid":"","institution":"Shanghai Jiao Tong University","correspondingAuthor":false,"prefix":"","firstName":"Yaoyu","middleName":"","lastName":"Liu","suffix":""},{"id":478682567,"identity":"c88b5cf5-c9e7-402d-b80b-1fc0ae8ba0e5","order_by":5,"name":"Hanxiao Zhang","email":"","orcid":"","institution":"Shanghai Jiao Tong University","correspondingAuthor":false,"prefix":"","firstName":"Hanxiao","middleName":"","lastName":"Zhang","suffix":""},{"id":478682568,"identity":"0c8ab723-4fc4-4924-a4ab-bc1cd96c6c54","order_by":6,"name":"Junyang Wu","email":"","orcid":"","institution":"Shanghai Jiao Tong University","correspondingAuthor":false,"prefix":"","firstName":"Junyang","middleName":"","lastName":"Wu","suffix":""},{"id":478682569,"identity":"2e5a3dab-fe71-44f4-b807-02ca65f634f4","order_by":7,"name":"Chunxi Zhang","email":"","orcid":"","institution":"Shanghai Chest Hospital","correspondingAuthor":false,"prefix":"","firstName":"Chunxi","middleName":"","lastName":"Zhang","suffix":""},{"id":478682570,"identity":"2d00ba1d-3758-4b05-a764-ea499a573e2f","order_by":8,"name":"Jie Yang","email":"","orcid":"","institution":"Shanghai Jiao Tong University","correspondingAuthor":false,"prefix":"","firstName":"Jie","middleName":"","lastName":"Yang","suffix":""},{"id":478682571,"identity":"0ec522bc-8b07-486b-a554-b188ce6c7567","order_by":9,"name":"Jiayuan Sun","email":"","orcid":"","institution":"Shanghai Chest Hospital","correspondingAuthor":false,"prefix":"","firstName":"Jiayuan","middleName":"","lastName":"Sun","suffix":""},{"id":478682572,"identity":"1ec6f450-ec78-4525-bd3b-27ba063fcc24","order_by":10,"name":"Guang-Zhong Yang","email":"","orcid":"https://orcid.org/0000-0003-4060-4020","institution":"Shanghai Jiao Tong University","correspondingAuthor":false,"prefix":"","firstName":"Guang-Zhong","middleName":"","lastName":"Yang","suffix":""}],"badges":[],"createdAt":"2025-05-21 05:00:40","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6712546/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6712546/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":98430659,"identity":"0a56f9e2-2451-4f38-8a8b-2aafe5f24a7d","added_by":"auto","created_at":"2025-12-17 16:45:59","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":6200368,"visible":true,"origin":"","legend":"Article File","description":"","filename":"main.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6712546/v1_covered_97f3758f-670e-46a2-ab94-a2c7ecec5e11.pdf"},{"id":85959822,"identity":"00677d48-78c8-4968-a13f-e9b3492498b8","added_by":"auto","created_at":"2025-07-03 15:31:51","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":10775785,"visible":true,"origin":"","legend":"The supplementary material","description":"","filename":"supplmat.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6712546/v1/87272776e456c7a0401819e8.pdf"}],"financialInterests":"There is \u003cb\u003eNO\u003c/b\u003e Competing Interest.","formattedTitle":"AirwayNet: Constructing Fine-Grained Airway Atlases","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":"Pulmonary Airway, Digital Atlas, Topology Modeling, Graph Transformer","lastPublishedDoi":"10.21203/rs.3.rs-6712546/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6712546/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Accurate anatomical labeling and analysis of the pulmonary structure and its surrounding anatomy from thoracic CT is becoming increasingly important for understanding the etiology of abnormalities or supporting targetted therapy and early interventions. Whilst lung and airway cell atlases have been attempted, there is a lack of fine-grained morphological atlases that are clinically deployable. In this work, we introduce AirwayNet, a robust, end-to-end deep learning pipeline enabling fully automatic and comprehensive airway anatomical labeling at lobar, segmental, and subsegmental resolutions that can be used to create digital atlases of the lung. Evaluated across large-scale multi-center datasets comprising diverse pulmonary conditions, the AirwayNet consistently outperformed existing analytical and labeling methods in terms of accuracy, topological consistency, and completeness. To simplify clinical interpretation, we further introduce a compact anatomical signature quantifying critical morphological airway features—including stenosis, ectasia, tortuosity, divergence, length, and complexity. When applied to various pulmonary diseases such as pulmonary fibrosis, emphysema, atelectasis, consolidation, and reticular opacities, it demonstrates strong discriminative power, revealing disease-specific morphological patterns with high interpretability and explainability. Additionally, the fine-grained atlas derived supports efficient automated branching pattern analysis, potentially enhancing bronchoscopic navigation planning and procedural safety, offering a valuable clinical tool for improved diagnosis, targeted treatment, and personalized patient care.","manuscriptTitle":"AirwayNet: Constructing Fine-Grained Airway Atlases","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-07-03 15:31:46","doi":"10.21203/rs.3.rs-6712546/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":"b817b735-51e3-4bc8-8228-7d6dd378d51f","owner":[],"postedDate":"July 3rd, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":50825463,"name":"Biological sciences/Computational biology and bioinformatics/Machine learning"},{"id":50825464,"name":"Biological sciences/Computational biology and bioinformatics/Image processing"}],"tags":[],"updatedAt":"2025-12-14T00:50:27+00:00","versionOfRecord":[],"versionCreatedAt":"2025-07-03 15:31:46","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-6712546","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6712546","identity":"rs-6712546","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}