Enhance Eye Disease Detection using Learnable Probabilis- tic Discrete Latents in Machine Learning Architectures

Enhance Eye Disease Detection using Learnable Probabilis- tic Discrete Latents in Machine Learning Architectures | 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 Enhance Eye Disease Detection using Learnable Probabilis- tic Discrete Latents in Machine Learning Architectures Anirudh Prabhakaran, YeKun Xiao, Ching-Yu Cheng, Dianbo Liu This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-5960996/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 Ocular diseases, including diabetic retinopathy and glaucoma, present a significant public health challenge due to their high prevalence and potential for causing vision impairment. Early and accurate diagnosis is crucial for effective treatment and management. In recent years, deep learning models have emerged as powerful tools for analysing medical images, such as retina imaging. However, challenges persist in model relibability and uncertainty estimation , which are critical for clinical decision-making. This study leverages the probabilis-tic framework of Generative Flow Networks (GFlowNets) to learn the posterior distribution over latent discrete dropout masks for the classification and analysis of ocular diseases using fundus images. We develop a robust and generalizable method that utilizes GFlowOut integrated with ResNet18 and ViT models as the backbone in identifying various ocular conditions. This study employs a unique set of dropout masks-none, random, bottomup, and top-down-to enhance model performance in analyzing these fundus images. Our results demonstrate that our learnable probablistic latents significantly improves accuracy, outperforming the traditional dropout approach. We utilize a gradient map calculation method, Grad-CAM, to assess model explainability, observing that the model accurately focuses on critical image regions for predictions. The integration of GFlowOut in neural networks presents a promising advancement in the automated diagnosis of ocular diseases, with implications for improving clinical workflows and patient outcomes.The source code for all these experiments can be found at https://github.com/anirudhprabhakaran3/gflowout_on_eye_images . Full Text Additional Declarations No competing interests reported. Supplementary Files BMCMedicalsupplement.pdf 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-5960996","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":445244897,"identity":"1ed6bad4-df0d-4c79-a2d1-29de1ac63838","order_by":0,"name":"Anirudh Prabhakaran","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABEklEQVRIie3RMUvDQBTA8RcC55KS9UKh+QoXsgbjR8lD6CQuQumYUDiXWtcWKn6Fuju8EtAlJGugS0RwUkhnHUxLh4DN4Sh4/+ly8OPy7gB0uj+ZBebXOAAGRtzeVBOwsuGOJHF7U016Mt2tWseoiN2/eeKOLHBmp9fV9hEuRUFG9SEhdM+OE2eZD7nINyg5Jsn8Da5EGZnenQR8oONElBe+iEYbn3EjmVgEuCqB9XsSIi9WEGK5z+z1gRR08tmQUEG8l1jSgAEeCEXMbIhx3zG+s8y8V8jOB6yZZTEnjosSJ82EHFedNzYVKYxPLff2uaprCnBWpOv6fRSEbsePAf/5uX8fDoJ+R1p1nqLT6XT/rW+Ew1wryqZwUQAAAABJRU5ErkJggg==","orcid":"","institution":"National University of Singapore","correspondingAuthor":true,"prefix":"","firstName":"Anirudh","middleName":"","lastName":"Prabhakaran","suffix":""},{"id":445244899,"identity":"3400d1f5-2183-4afb-97f8-6d969cfaef30","order_by":1,"name":"YeKun Xiao","email":"","orcid":"","institution":"National University of Singapore","correspondingAuthor":false,"prefix":"","firstName":"YeKun","middleName":"","lastName":"Xiao","suffix":""},{"id":445244900,"identity":"998ae108-914d-419e-b64d-663d867a1b49","order_by":2,"name":"Ching-Yu Cheng","email":"","orcid":"","institution":"National University of Singapore","correspondingAuthor":false,"prefix":"","firstName":"Ching-Yu","middleName":"","lastName":"Cheng","suffix":""},{"id":445244901,"identity":"1e29d875-2258-4427-a126-34a0c3cffa3e","order_by":3,"name":"Dianbo Liu","email":"","orcid":"","institution":"National University of Singapore","correspondingAuthor":false,"prefix":"","firstName":"Dianbo","middleName":"","lastName":"Liu","suffix":""}],"badges":[],"createdAt":"2025-02-04 21:53:18","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-5960996/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-5960996/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":90339584,"identity":"0497185d-bfb4-4334-b12b-bb185fbba9d3","added_by":"auto","created_at":"2025-09-01 14:53:56","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":375168,"visible":true,"origin":"","legend":"","description":"","filename":"Revisedmanuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-5960996/v1_covered_b58fe5b9-b4e4-4783-b959-005bb73ab5c3.pdf"},{"id":81093595,"identity":"8108c12c-a50e-4624-a35e-5998d76ab91d","added_by":"auto","created_at":"2025-04-22 07:37:17","extension":"pdf","order_by":2,"title":"","display":"","copyAsset":false,"role":"supplement","size":2049869,"visible":true,"origin":"","legend":"","description":"","filename":"BMCMedicalsupplement.pdf","url":"https://assets-eu.researchsquare.com/files/rs-5960996/v1/1965681b874ba49b700b6bd3.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Enhance Eye Disease Detection using Learnable Probabilis- tic Discrete Latents in Machine Learning Architectures","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":"","lastPublishedDoi":"10.21203/rs.3.rs-5960996/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-5960996/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Ocular diseases, including diabetic retinopathy and glaucoma, present a significant public health challenge due to their high prevalence and potential for causing vision impairment. Early and accurate diagnosis is crucial for effective treatment and management. In recent years, deep learning models have emerged as powerful tools for analysing medical images, such as retina imaging. However, challenges persist in model relibability and uncertainty estimation , which are critical for clinical decision-making. This study leverages the probabilis-tic framework of Generative Flow Networks (GFlowNets) to learn the posterior distribution over latent discrete dropout masks for the classification and analysis of ocular diseases using fundus images. We develop a robust and generalizable method that utilizes GFlowOut integrated with ResNet18 and ViT models as the backbone in identifying various ocular conditions. This study employs a unique set of dropout masks-none, random, bottomup, and top-down-to enhance model performance in analyzing these fundus images. Our results demonstrate that our learnable probablistic latents significantly improves accuracy, outperforming the traditional dropout approach. We utilize a gradient map calculation method, Grad-CAM, to assess model explainability, observing that the model accurately focuses on critical image regions for predictions. The integration of GFlowOut in neural networks presents a promising advancement in the automated diagnosis of ocular diseases, with implications for improving clinical workflows and patient outcomes.The source code for all these experiments can be found at https://github.com/anirudhprabhakaran3/gflowout_on_eye_images.","manuscriptTitle":"Enhance Eye Disease Detection using Learnable Probabilis- tic Discrete Latents in Machine Learning Architectures","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-04-22 07:29:12","doi":"10.21203/rs.3.rs-5960996/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":"b9f0ce6d-0686-4123-a7a0-2798601bc653","owner":[],"postedDate":"April 22nd, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2025-09-01T14:53:20+00:00","versionOfRecord":[],"versionCreatedAt":"2025-04-22 07:29:12","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-5960996","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-5960996","identity":"rs-5960996","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}