Predicting Lung Cancer Survival with Attention-based CT Slices Combination

Predicting Lung Cancer Survival with Attention-based CT Slices Combination | 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 Predicting Lung Cancer Survival with Attention-based CT Slices Combination Domenico Paolo, Carlo Greco, Edy Ippolito, Michele Fiore, Sara Ramella, and 4 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-5374277/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 prognosis of Non-Small Cell Lung Cancer (NSCLC) is crucial for enhancing patient care and treatment outcomes. Despite the advancements in deep learning, the task of overall survival prediction in NSCLC has not fully leveraged these techniques, yet. This study introduces a novel methodology for predicting 2-year overall survival (OS) in NSCLC patients using CT scans. Our approach integrates CT scan representations produced by EfficientNetB0 with a soft attention mechanism to identify the most relevant slices for survival risk prediction, which are then analyzed by a risk-assessment network. To validate our method and ensure reproducibility, we employed the public LUNG1 dataset and a smaller private dataset. Our approach was compared to a benchmark 3D network and two variants of our methodology: on the LUNG1 it outperformed the competitors achieving a mean Ctd-index of 0.584 over 10-fold cross-validation. On the LUNG1 we also demonstrated the adaptability of our method with 4 other 2D backbones replacing the EfficientNetB0, confirming that our mechanism of combining 2D slice representations to construct a 3D volume representation is more effective for OS prediction compared to a traditional 3D approach. Finally, we used transfer learning on the private dataset, showing that it can significantly enhance performance in limited data scenarios, increasing the Ctd-index by 0.076 compared to model without transfer learning. Deep Learning Non-Small Cell Lung Cancer Overall Survival Risk Analysis Soft-Attention 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-5374277","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":373788177,"identity":"b5234808-df37-4f7d-b2cb-cddf0621df7c","order_by":0,"name":"Domenico Paolo","email":"","orcid":"","institution":"Università Campus Bio-Medico","correspondingAuthor":false,"prefix":"","firstName":"Domenico","middleName":"","lastName":"Paolo","suffix":""},{"id":373788178,"identity":"ab0d6ca5-f196-4350-a069-1a00cea8ccae","order_by":1,"name":"Carlo Greco","email":"","orcid":"","institution":"Campus Bio Medico University Hospital","correspondingAuthor":false,"prefix":"","firstName":"Carlo","middleName":"","lastName":"Greco","suffix":""},{"id":373788179,"identity":"09c2bcc0-33ca-44b2-adaf-84a7480a3e83","order_by":2,"name":"Edy Ippolito","email":"","orcid":"","institution":"Campus Bio Medico University Hospital","correspondingAuthor":false,"prefix":"","firstName":"Edy","middleName":"","lastName":"Ippolito","suffix":""},{"id":373788180,"identity":"18b94efa-845c-4281-90e9-1bfe3c306063","order_by":3,"name":"Michele Fiore","email":"","orcid":"","institution":"Campus Bio Medico University Hospital","correspondingAuthor":false,"prefix":"","firstName":"Michele","middleName":"","lastName":"Fiore","suffix":""},{"id":373788181,"identity":"ca8df874-6058-4011-bf84-e77b61b91617","order_by":4,"name":"Sara Ramella","email":"","orcid":"","institution":"Campus Bio Medico University Hospital","correspondingAuthor":false,"prefix":"","firstName":"Sara","middleName":"","lastName":"Ramella","suffix":""},{"id":373788182,"identity":"aee76677-88e2-4c8e-b17f-0d7a23b23180","order_by":5,"name":"Paolo Soda","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAwklEQVRIiWNgGAWjYHACxgNg6gDzAeL1QLWwJZCshceAOOXm7IcPHPjAUCfHd/zMN6mbbQz2/IS0WPakJRycwXDYWPJM7jbp3DaGxJkNBLQYHMgxOMzDcCBxwwGIlgSDA4S0nH8D0lKXuOH8m2cgLfb2BLXcANvCnLjhRg4bSAvjBoJ+mfEM6BcDoF9uPDO2zjknkTiDkC3m/MkHH3yoAIbY+eSHt3PKbOz5Gwg5DIkEAQlCzkJWPApGwSgYBaMAFwAADFtC43ckfGMAAAAASUVORK5CYII=","orcid":"","institution":"Umeå University","correspondingAuthor":true,"prefix":"","firstName":"Paolo","middleName":"","lastName":"Soda","suffix":""},{"id":373788183,"identity":"25176225-1246-4ca6-8213-c02ce3d3de23","order_by":6,"name":"Matteo Tortora","email":"","orcid":"","institution":"University of Genoa","correspondingAuthor":false,"prefix":"","firstName":"Matteo","middleName":"","lastName":"Tortora","suffix":""},{"id":373788184,"identity":"c6e8739f-5335-4e27-ba23-c9668e93c047","order_by":7,"name":"Alessandro Bria","email":"","orcid":"","institution":"University of Cassino and Southern Lazio","correspondingAuthor":false,"prefix":"","firstName":"Alessandro","middleName":"","lastName":"Bria","suffix":""},{"id":373788186,"identity":"e97f83f7-da0c-4523-849c-d114ae21c41c","order_by":8,"name":"Rosa Sicilia","email":"","orcid":"","institution":"Università Campus Bio-Medico","correspondingAuthor":false,"prefix":"","firstName":"Rosa","middleName":"","lastName":"Sicilia","suffix":""}],"badges":[],"createdAt":"2024-11-01 15:23:30","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-5374277/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-5374277/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":70104950,"identity":"6f579d9d-4e27-44c4-a079-a506d0246720","added_by":"auto","created_at":"2024-11-28 11:16:59","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":530557,"visible":true,"origin":"","legend":"","description":"","filename":"CTOSBMC.pdf","url":"https://assets-eu.researchsquare.com/files/rs-5374277/v1_covered_b28b09e1-e9db-489c-934f-d2842cb1dbc5.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Predicting Lung Cancer Survival with Attention-based CT Slices Combination","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":" Deep Learning, Non-Small Cell Lung Cancer, Overall Survival, Risk Analysis, Soft-Attention","lastPublishedDoi":"10.21203/rs.3.rs-5374277/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-5374277/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Accurate prognosis of Non-Small Cell Lung Cancer (NSCLC) is crucial for enhancing patient care and treatment outcomes. Despite the advancements in deep learning, the task of overall survival prediction in NSCLC has not fully leveraged these techniques, yet. This study introduces a novel methodology for predicting 2-year overall survival (OS) in NSCLC patients using CT scans. Our approach integrates CT scan representations produced by EfficientNetB0 with a soft attention mechanism to identify the most relevant slices for survival risk prediction, which are then analyzed by a risk-assessment network. To validate our method and ensure reproducibility, we employed the public LUNG1 dataset and a smaller private dataset. Our approach was compared to a benchmark 3D network and two variants of our methodology: on the LUNG1 it outperformed the competitors achieving a mean Ctd-index of 0.584 over 10-fold cross-validation. On the LUNG1 we also demonstrated the adaptability of our method with 4 other 2D backbones replacing the EfficientNetB0, confirming that our mechanism of combining 2D slice representations to construct a 3D volume representation is more effective for OS prediction compared to a traditional 3D approach. Finally, we used transfer learning on the private dataset, showing that it can significantly enhance performance in limited data scenarios, increasing the Ctd-index by 0.076 compared to model without transfer learning.","manuscriptTitle":"Predicting Lung Cancer Survival with Attention-based CT Slices Combination","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-11-14 18:15:33","doi":"10.21203/rs.3.rs-5374277/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":"106f59be-3a91-4d20-b1fe-feb61d54d93e","owner":[],"postedDate":"November 14th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2024-11-28T11:08:49+00:00","versionOfRecord":[],"versionCreatedAt":"2024-11-14 18:15:33","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-5374277","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-5374277","identity":"rs-5374277","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}