Macular segmentation using an automatic deep learning and graph cut strategy

Macular segmentation using an automatic deep learning and graph cut strategy | 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 Macular segmentation using an automatic deep learning and graph cut strategy J. S. Abril-Daza, C. H. Rodriguez-Garavito, D. F. Alfonso-Vargas, and 2 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-5829828/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 Age-related Macular Degeneration (AMD) is one of the main diseases affectingvisual health in the world, since it causes severe and irreversible vision loss inelderly people. According to the International Agency for the Prevention of Blind-ness (IAPB), by the year 2040, 288 million people are expected to be affectedworldwide, while in Colombia for the year 2020, approximately 234,200 caseswere estimated. With the improvement of computer vision techniques, automaticdiagnosis has become a reliable tool for screening and determining the degree ofthe disease. Many strategies have been proposed in the last decade, from the firstbased on manual characterization of the disease to current ones based on modeltraining using large databases of images annotated by specialists, with very highcomputational costs and data collection time. The present article proposes a novelmethod based on combining the two trends, using the best of each one. The dis-ease is characterized by segmenting its two fundamental features in cascade: theocular vascular network is segmented with a pre-trained deep learning model andtransformed into a graph for extraction of terminal nodes (which are known todelimit the macular zone); and the macula is segmented through a semi-automatic algorithm called graph cut that requires initial background and foreground infor-mation (which corresponds to the terminal nodes already obtained) to become anautomatic method. Finally, we present a comparison between macular segmen-tation using the proposed algorithm with parametric changes in its architectureand a deep learning model for macular segmentation with a reduced set of aug-mented images. It is confirmed that, with a limited database, the proposed graphcut-deep learning strategy is a viable way to obtain a method to extract the mainfeatures of the disease and generate a subsequent diagnosis. Macular segmentation vascular network segmentation graph cut fundus image deep learning 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-5829828","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":403594642,"identity":"2a352e0d-7483-413a-a285-98210dba9a0b","order_by":0,"name":"J. S. Abril-Daza","email":"","orcid":"","institution":"University of La Salle","correspondingAuthor":false,"prefix":"","firstName":"J.","middleName":"S.","lastName":"Abril-Daza","suffix":""},{"id":403594643,"identity":"fa8935d8-5e99-4841-a8f1-6d11d454fc21","order_by":1,"name":"C. H. Rodriguez-Garavito","email":"data:image/png;base64,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","orcid":"","institution":"University of La Salle","correspondingAuthor":true,"prefix":"","firstName":"C.","middleName":"H.","lastName":"Rodriguez-Garavito","suffix":""},{"id":403594644,"identity":"3fa04fae-0e0a-4c3b-843b-2a97a5993393","order_by":2,"name":"D. F. Alfonso-Vargas","email":"","orcid":"","institution":"University of La Salle","correspondingAuthor":false,"prefix":"","firstName":"D.","middleName":"F.","lastName":"Alfonso-Vargas","suffix":""},{"id":403594645,"identity":"cad486c5-4c95-480d-a522-0360969852e8","order_by":3,"name":"A. I. Tenjo-Morales","email":"","orcid":"","institution":"University of La Salle","correspondingAuthor":false,"prefix":"","firstName":"A.","middleName":"I.","lastName":"Tenjo-Morales","suffix":""},{"id":403594646,"identity":"22c492fe-9fb8-4e86-b580-2abdf851361f","order_by":4,"name":"J. C. Cuesta-Redondo","email":"","orcid":"","institution":"University of La Salle","correspondingAuthor":false,"prefix":"","firstName":"J.","middleName":"C.","lastName":"Cuesta-Redondo","suffix":""}],"badges":[],"createdAt":"2025-01-14 21:23:08","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-5829828/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-5829828/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":76148398,"identity":"792e2ef3-a417-4446-94f1-5d35e33de426","added_by":"auto","created_at":"2025-02-12 21:16:36","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":9547243,"visible":true,"origin":"","legend":"","description":"","filename":"GraphCutDeepLearningMaculaSegmantationTemplate2023.pdf","url":"https://assets-eu.researchsquare.com/files/rs-5829828/v1_covered_38c65006-7f5f-4d99-8ef6-c06455259487.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Macular segmentation using an automatic deep learning and graph cut strategy","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":"Macular segmentation, vascular network segmentation, graph cut, fundus image, deep learning","lastPublishedDoi":"10.21203/rs.3.rs-5829828/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-5829828/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Age-related Macular Degeneration (AMD) is one of the main diseases affectingvisual health in the world, since it causes severe and irreversible vision loss inelderly people. According to the International Agency for the Prevention of Blind-ness (IAPB), by the year 2040, 288 million people are expected to be affectedworldwide, while in Colombia for the year 2020, approximately 234,200 caseswere estimated. With the improvement of computer vision techniques, automaticdiagnosis has become a reliable tool for screening and determining the degree ofthe disease. Many strategies have been proposed in the last decade, from the firstbased on manual characterization of the disease to current ones based on modeltraining using large databases of images annotated by specialists, with very highcomputational costs and data collection time. The present article proposes a novelmethod based on combining the two trends, using the best of each one. The dis-ease is characterized by segmenting its two fundamental features in cascade: theocular vascular network is segmented with a pre-trained deep learning model andtransformed into a graph for extraction of terminal nodes (which are known todelimit the macular zone); and the macula is segmented through a semi-automatic algorithm called graph cut that requires initial background and foreground infor-mation (which corresponds to the terminal nodes already obtained) to become anautomatic method. Finally, we present a comparison between macular segmen-tation using the proposed algorithm with parametric changes in its architectureand a deep learning model for macular segmentation with a reduced set of aug-mented images. It is confirmed that, with a limited database, the proposed graphcut-deep learning strategy is a viable way to obtain a method to extract the mainfeatures of the disease and generate a subsequent diagnosis.","manuscriptTitle":"Macular segmentation using an automatic deep learning and graph cut strategy","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-01-20 09:49:39","doi":"10.21203/rs.3.rs-5829828/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":"e0860ab8-c09e-4d45-be01-b1067c1fadb6","owner":[],"postedDate":"January 20th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2025-02-12T21:08:26+00:00","versionOfRecord":[],"versionCreatedAt":"2025-01-20 09:49:39","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-5829828","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-5829828","identity":"rs-5829828","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}