LIBRA: Low spectral resolution brain tumor classifier for medical hyperspectral imaging

LIBRA: Low spectral resolution brain tumor classifier for medical hyperspectral imaging | 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 LIBRA: Low spectral resolution brain tumor classifier for medical hyperspectral imaging Manuel Villa, Alberto Martín-Perez, Guillermo Vazquez, Gonzalo Rosa-Olmeda, and 8 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4668541/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 Gliomas constitute a significant challenge in neurosurgery due to their high incidence and poor prognosis. Despite advancements in tumor detection techniques using machine learning approach with hyperspectral imaging, accurately distinguishing between healthy and tumoral tissues remains challenging. Following this trend, this paper introduces Libra, a low spectral resolution classifier designed for brain tumor detection, leveraging ensemble learning techniques to enhance classification performance. Evaluated across the Helicoid and Slim Brain databases, Libra demonstrates superior tumor sensitivity and a notable increase in accuracy compared to standalone SVM and the state-of-the-art Helicoid classification chain. While facing challenges in accurately distinguishing between blood vessels and tumoral tissues, Libra performs 32 % better than Helicoid in tumor sensitivity and 25.1 % in tumor F1-score. Moreover, when using unseen data, Libra demonstrates notable improvements of 7.8 % and 6.9 % respectively. These improvements are obtained using low complexity algorithms exploiting ensemble learning techniques. Biomedical Engineering Artificial Intelligence and Machine Learning Glioblastoma hyperspectral classification ensemble learning machine learning genetic algorithms Full Text Additional Declarations The authors declare no competing interests. Supplementary Files LibraSupplementarymaterialcompressed.pdf Test patients classification maps 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-4668541","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":321263971,"identity":"a5e863bd-cced-4b70-b69b-7d072dee9438","order_by":0,"name":"Manuel Villa","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABEElEQVRIiWNgGAWjYNCCAgYGNnbmBhiX8QFhLQZALcyMcC3MBkRpYUDSwiaBT7Fu+9ljEh8MGBL7mBkbPzDusYnmlz58rJp3xzYGfv4DWLWYnclLk5wB1NLGzNgswfAsLXdmX1rabd4ztxkkZyRg13Igx0yax4DBGOQXCYYDh3M3nOExu83bdpvB4AZ2h5mdf2Mm/QeipfkHSMt+oJZikBb78zgcdgNoC9D7ckAtbRBbeHjMmMG2MOBw2I03xpY9BhJgLRYJB9JyZ5xhS5ace+Y2j8QNHFrO5xje+FFhwyPf3nz4xocDNrn9PcwHP7zdcVuOvx+7w6AAGhFwY4FxxINPPRaAiNZRMApGwSgYBQwArU9WJj2TgxYAAAAASUVORK5CYII=","orcid":"https://orcid.org/0000-0001-7000-6289","institution":"Research Center on Software Technologies and Multimedia Systems. Universidad Politécnica de Madrid (UPM)","correspondingAuthor":true,"prefix":"","firstName":"Manuel","middleName":"","lastName":"Villa","suffix":""},{"id":321263972,"identity":"7c6305a2-9ef7-4693-9356-136136162226","order_by":1,"name":"Alberto Martín-Perez","email":"","orcid":"https://orcid.org/0000-0003-4715-6814","institution":"Research Center on Software Technologies and Multimedia Systems. Universidad Politécnica de Madrid (UPM)","correspondingAuthor":false,"prefix":"","firstName":"Alberto","middleName":"","lastName":"Martín-Perez","suffix":""},{"id":321263973,"identity":"8ef50b73-b788-451c-870a-f41737647e2f","order_by":2,"name":"Guillermo Vazquez","email":"","orcid":"https://orcid.org/0000-0001-5821-0877","institution":"Research Center on Software Technologies and Multimedia Systems. Universidad Politécnica de Madrid (UPM)","correspondingAuthor":false,"prefix":"","firstName":"Guillermo","middleName":"","lastName":"Vazquez","suffix":""},{"id":321263974,"identity":"40d743d5-1998-41a2-b41d-3169362ee93a","order_by":3,"name":"Gonzalo Rosa-Olmeda","email":"","orcid":"https://orcid.org/0000-0002-3236-1236","institution":"Research Center on Software Technologies and Multimedia Systems. Universidad Politécnica de Madrid (UPM)","correspondingAuthor":false,"prefix":"","firstName":"Gonzalo","middleName":"","lastName":"Rosa-Olmeda","suffix":""},{"id":321263975,"identity":"49af8c6e-a31a-4d67-8b46-2f7a2b32b8a7","order_by":4,"name":"Jaime Sancho","email":"","orcid":"https://orcid.org/0000-0001-8767-6596","institution":"Research Center on Software Technologies and Multimedia Systems. Universidad Politécnica de Madrid (UPM)","correspondingAuthor":false,"prefix":"","firstName":"Jaime","middleName":"","lastName":"Sancho","suffix":""},{"id":321263976,"identity":"bc87894d-c699-4513-a673-29d017f7031c","order_by":5,"name":"Pallab Sutradhar","email":"","orcid":"https://orcid.org/0000-0002-5731-5199","institution":"Research Center on Software Technologies and Multimedia Systems. Universidad Politécnica de Madrid (UPM)","correspondingAuthor":false,"prefix":"","firstName":"Pallab","middleName":"","lastName":"Sutradhar","suffix":""},{"id":321263977,"identity":"11d75640-ad15-4ec6-ad5e-5c2860e8a90c","order_by":6,"name":"Miguel Chavarrías","email":"","orcid":"https://orcid.org/0000-0003-0280-3440","institution":"Research Center on Software Technologies and Multimedia Systems. Universidad Politécnica de Madrid (UPM)","correspondingAuthor":false,"prefix":"","firstName":"Miguel","middleName":"","lastName":"Chavarrías","suffix":""},{"id":321263978,"identity":"8592ba9a-16c8-4007-a636-adf738da4e42","order_by":7,"name":"Luis Jimenez-Roldan","email":"","orcid":"https://orcid.org/0000-0002-9864-0385","institution":"Neurosurgery Department, Hospital Universitario 12 de Octubre; Medicine Faculty, UniversidadComplutense de 10 Madrid (UCM); Instituto de Investigacion Sanitaria Hospital 12 de Octubre (imas12)","correspondingAuthor":false,"prefix":"","firstName":"Luis","middleName":"","lastName":"Jimenez-Roldan","suffix":""},{"id":321263979,"identity":"b5ce4640-f486-413d-9d7c-9c6361a710e5","order_by":8,"name":"Angel Perez-Nuñez","email":"","orcid":"https://orcid.org/0000-0002-2391-6586","institution":"Neurosurgery Department, Hospital Universitario 12 de Octubre; Medicine Faculty, UniversidadComplutense de 10 Madrid (UCM); Instituto de Investigacion Sanitaria Hospital 12 de Octubre (imas12)","correspondingAuthor":false,"prefix":"","firstName":"Angel","middleName":"","lastName":"Perez-Nuñez","suffix":""},{"id":321263980,"identity":"79351dc6-cdb8-4be3-a011-0da2f73898b3","order_by":9,"name":"Alfonso Lagares","email":"","orcid":"https://orcid.org/0000-0003-3996-0554","institution":"Neurosurgery Department, Hospital Universitario 12 de Octubre; Medicine Faculty, UniversidadComplutense de 10 Madrid (UCM); Instituto de Investigacion Sanitaria Hospital 12 de Octubre (imas12)","correspondingAuthor":false,"prefix":"","firstName":"Alfonso","middleName":"","lastName":"Lagares","suffix":""},{"id":321263981,"identity":"771109dd-67ae-4230-a80c-f104660af283","order_by":10,"name":"Eduardo Juarez","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA6UlEQVRIiWNgGAWjYFCCBCBmY2BgbADzbEjXkkaCFig4TFgDP3uO4eeKMhsG5hnJzz58+HM+cbvYAcaHP/Bokex5Yyx55lwaA+OMNOOZM3huJ+6cncBszINHi8GNHAPJxrbDQC0Jxsw8ErcTN9xOYJPG5zD7GznGPyFa0j8z/zE4B9LC/hOfwwwkcsygtuQYMzMkHADbwoDPYRJnnpVZNpxL42HseVPM2HMg2Xjn7MRmaXxa+NuTN99sKLORM2xP38zw44+d7Hbp5IMf8TkMBngMG2BOhcUqQSAPYxgQp34UjIJRMApGEAAA8vlNjZjBqSkAAAAASUVORK5CYII=","orcid":"https://orcid.org/0000-0002-6096-1511","institution":"Research Center on Software Technologies and Multimedia Systems. Universidad Politécnica de Madrid (UPM)","correspondingAuthor":true,"prefix":"","firstName":"Eduardo","middleName":"","lastName":"Juarez","suffix":""},{"id":321263982,"identity":"70fe7966-2814-4c94-b4f4-227536fc73b4","order_by":11,"name":"Cesar Sanz","email":"","orcid":"https://orcid.org/0000-0002-2411-9132","institution":"Research Center on Software Technologies and Multimedia Systems. Universidad Politécnica de Madrid (UPM)","correspondingAuthor":false,"prefix":"","firstName":"Cesar","middleName":"","lastName":"Sanz","suffix":""}],"badges":[],"createdAt":"2024-07-01 13:52:48","currentVersionCode":1,"declarations":{"humanSubjects":true,"vertebrateSubjects":false,"conflictsOfInterestStatement":false,"humanSubjectEthicalGuidelines":true,"humanSubjectConsent":true,"humanSubjectClinicalTrial":false,"humanSubjectCaseReport":false,"vertebrateSubjectEthicalGuidelines":false},"doi":"10.21203/rs.3.rs-4668541/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4668541/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":59458418,"identity":"54b078bc-45a0-4662-913f-70527814c87c","added_by":"auto","created_at":"2024-07-02 04:27:38","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1948632,"visible":true,"origin":"","legend":"","description":"","filename":"Librapreprint.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4668541/v1_covered_d245b629-945d-4952-83b3-590402474b17.pdf"},{"id":59458000,"identity":"12617137-a200-4976-aee0-da6a7c3b059f","added_by":"auto","created_at":"2024-07-02 04:19:34","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":18994548,"visible":true,"origin":"","legend":"\u003cp\u003eTest patients classification maps\u003c/p\u003e","description":"","filename":"LibraSupplementarymaterialcompressed.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4668541/v1/5722ac633c062960b07f7978.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003eLIBRA: Low spectral resolution brain tumor classifier for medical hyperspectral imaging\u003c/p\u003e","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"Research Center on Software Technologies and Multimedia Systems. Universidad Politécnica de Madrid (UPM)","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":"Glioblastoma, hyperspectral, classification, ensemble learning, machine learning, genetic algorithms","lastPublishedDoi":"10.21203/rs.3.rs-4668541/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4668541/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eGliomas constitute a significant challenge in neurosurgery due to their high incidence and poor prognosis. Despite advancements in tumor detection techniques using machine learning approach with hyperspectral imaging, accurately distinguishing between healthy and tumoral tissues remains challenging. Following this trend, this paper introduces Libra, a low spectral resolution classifier designed for brain tumor detection, leveraging ensemble learning techniques to enhance classification performance. Evaluated across the Helicoid and Slim Brain databases, Libra demonstrates superior tumor sensitivity and a notable increase in accuracy compared to standalone SVM and the state-of-the-art Helicoid classification chain. While facing challenges in accurately distinguishing between blood vessels and tumoral tissues, Libra performs 32 % better than Helicoid in tumor sensitivity and 25.1 % in tumor F1-score. Moreover, when using unseen data, Libra demonstrates notable improvements of 7.8 % and 6.9 % respectively. These improvements are obtained using low complexity algorithms exploiting ensemble learning techniques.\u003c/p\u003e","manuscriptTitle":"LIBRA: Low spectral resolution brain tumor classifier for medical hyperspectral imaging","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-07-02 04:19:29","doi":"10.21203/rs.3.rs-4668541/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":"531cea5d-fbca-4b83-8359-82ad22d28ebc","owner":[],"postedDate":"July 2nd, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":33972179,"name":"Biomedical Engineering"},{"id":33972180,"name":"Artificial Intelligence and Machine Learning"}],"tags":[],"updatedAt":"2024-07-02T04:19:29+00:00","versionOfRecord":[],"versionCreatedAt":"2024-07-02 04:19:29","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-4668541","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4668541","identity":"rs-4668541","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}