A Novel Approach to Glaucoma Detection: Leveraging Fourier Transform, Structural Similarity Index, and Self-Supervised Learning

A Novel Approach to Glaucoma Detection: Leveraging Fourier Transform, Structural Similarity Index, and Self-Supervised 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 A Novel Approach to Glaucoma Detection: Leveraging Fourier Transform, Structural Similarity Index, and Self-Supervised Learning Maria Frasca, Jianyi Lin, Davide La Torre This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-5929910/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 Glaucoma is one of the leading causes of irreversible blindness worldwide, affecting millions of people each year. Early diagnosis is crucial to prevent vision loss, but the often asymptomatic nature of the disease and the complexity of clinical signs make timely detection challenging. Advanced ocular imaging technologies, such as optical coherence tomography and fundus photography, offer new diagnostic opportunities but generate complex and voluminous data requiring significant expertise for interpretation. Artificial intelligence (AI) is revolutionizing this field, enabling efficient data analysis and supporting physicians in early risk identification and disease monitoring. In this article, we present a comprehensive approach that combines advanced image preprocessing techniques with artificial intelligence (AI) models to enhance the diagnostic accuracy of glaucoma. Using the REFUGE2 dataset, we implemented the Discrete Fourier Transform (DFT) for image preprocessing, leveraging the Fast Fourier Transform (FFT) algorithm for computational efficiency. This approach effectively preserved visual features, achieving SSIM values of 0.9225 for training, 0.8637 for validation, and 0.8247 for testing. For classification, we employed various models, including Masked Image Modeling (MIM) and Masked Autoencoder (MAE), combined with self-supervised learning techniques such as SimCLR. This multi-model approach allowed us to explore different perspectives in image analysis, achieving an accuracy of 90.06% with MIM and 90.14% with MAE on preprocessed images, surpassing the results obtained with non-preprocessed data. Moreover, the MIM model demonstrated a strong discriminative capability, highlighted by an AUC-ROC of 0.9298, a precision of 0.8154, and an F1-score of 0.6998. The results show that combining advanced preprocessing with Transformer neural networks can significantly improve efficiency and diagnostic accuracy in the early detection of glaucoma. This approach offers a scalable and robust method for disease management, contributing to improvements in traditional clinical practices. Glaucoma Artificial Intelligence Fourier Transform Transformer Networks Structural Similarity Index 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-5929910","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":411482177,"identity":"6a89b90b-5c7f-4092-8376-2faf55c8b718","order_by":0,"name":"Maria Frasca","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA0klEQVRIie3OsQrCMBDG8S8UnAI+gKJPIJwIgQ7i28RFcRNHp3YRXH2cyK3VrhlcROjkUHERdLC2CDrYdnTIf7oc/MIBLtefZoBOMaWAhJdvKskgH8TmTSrNm3jy45ef9cLd0dxAs+aaj9dhcGj3QghOS4iKxrRdgfyN1YPWNEik4orDlNEwEg+ClcgI1yBxgu0DRN048u5+LWI1WGaEzKTREvVIAm5nom+18lf7FxFLE5Uepr3LeUHUiflkb3MeqZg5XZSQIvp6iWUlcLlcLld5T9KwUPOX1HAXAAAAAElFTkSuQmCC","orcid":"","institution":"University of Milan","correspondingAuthor":true,"prefix":"","firstName":"Maria","middleName":"","lastName":"Frasca","suffix":""},{"id":411482178,"identity":"9de4bf0d-fa75-4bc0-9a64-0c35da16aee6","order_by":1,"name":"Jianyi Lin","email":"","orcid":"","institution":"Catholic University of the Sacred Heart","correspondingAuthor":false,"prefix":"","firstName":"Jianyi","middleName":"","lastName":"Lin","suffix":""},{"id":411482179,"identity":"e1c415a7-a965-43b8-8c0b-3e1d3ed7fe89","order_by":2,"name":"Davide La Torre","email":"","orcid":"","institution":"Université Côte d'Azur","correspondingAuthor":false,"prefix":"","firstName":"Davide","middleName":"La","lastName":"Torre","suffix":""}],"badges":[],"createdAt":"2025-01-30 11:38:04","currentVersionCode":1,"declarations":{"humanSubjects":false,"vertebrateSubjects":false,"conflictsOfInterestStatement":false,"humanSubjectEthicalGuidelines":false,"humanSubjectConsent":false,"humanSubjectClinicalTrial":false,"humanSubjectCaseReport":false,"vertebrateSubjectEthicalGuidelines":false},"doi":"10.21203/rs.3.rs-5929910/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-5929910/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":76539786,"identity":"0f855079-13e0-435a-ae2d-a4057f20b2c5","added_by":"auto","created_at":"2025-02-18 08:10:09","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":2494212,"visible":true,"origin":"","legend":"","description":"","filename":"OptimizationandEngineering.pdf","url":"https://assets-eu.researchsquare.com/files/rs-5929910/v1_covered_2af29ed5-3a0d-4677-be35-a3bb7a973c92.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"A Novel Approach to Glaucoma Detection: Leveraging Fourier Transform, Structural Similarity Index, and Self-Supervised 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":"Glaucoma, Artificial Intelligence, Fourier Transform, Transformer Networks, Structural Similarity Index","lastPublishedDoi":"10.21203/rs.3.rs-5929910/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-5929910/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Glaucoma is one of the leading causes of irreversible blindness worldwide, affecting millions of people each year. Early diagnosis is crucial to prevent vision loss, but the often asymptomatic nature of the disease and the complexity of clinical signs make timely detection challenging. Advanced ocular imaging technologies, such as optical coherence tomography and fundus photography, offer new diagnostic opportunities but generate complex and voluminous data requiring significant expertise for interpretation. Artificial intelligence (AI) is revolutionizing this field, enabling efficient data analysis and supporting physicians in early risk identification and disease monitoring. In this article, we present a comprehensive approach that combines advanced image preprocessing techniques with artificial intelligence (AI) models to enhance the diagnostic accuracy of glaucoma. Using the REFUGE2 dataset, we implemented the Discrete Fourier Transform (DFT) for image preprocessing, leveraging the Fast Fourier Transform (FFT) algorithm for computational efficiency. This approach effectively preserved visual features, achieving SSIM values of 0.9225 for training, 0.8637 for validation, and 0.8247 for testing. For classification, we employed various models, including Masked Image Modeling (MIM) and Masked Autoencoder (MAE), combined with self-supervised learning techniques such as SimCLR. This multi-model approach allowed us to explore different perspectives in image analysis, achieving an accuracy of 90.06\\% with MIM and 90.14\\% with MAE on preprocessed images, surpassing the results obtained with non-preprocessed data. Moreover, the MIM model demonstrated a strong discriminative capability, highlighted by an AUC-ROC of 0.9298, a precision of 0.8154, and an F1-score of 0.6998. The results show that combining advanced preprocessing with Transformer neural networks can significantly improve efficiency and diagnostic accuracy in the early detection of glaucoma. This approach offers a scalable and robust method for disease management, contributing to improvements in traditional clinical practices.","manuscriptTitle":"A Novel Approach to Glaucoma Detection: Leveraging Fourier Transform, Structural Similarity Index, and Self-Supervised Learning","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-02-07 07:27:11","doi":"10.21203/rs.3.rs-5929910/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":"8e2c56dd-2af3-478b-a7be-255e917e6392","owner":[],"postedDate":"February 7th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2025-02-18T08:09:38+00:00","versionOfRecord":[],"versionCreatedAt":"2025-02-07 07:27:11","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-5929910","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-5929910","identity":"rs-5929910","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}