Transformer-Based Diameter-Specific Segmentation of Conjunctival Vessels for Early Detection of Diabetic Vascular Changes

Transformer-Based Diameter-Specific Segmentation of Conjunctival Vessels for Early Detection of Diabetic Vascular Changes | 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 Article Transformer-Based Diameter-Specific Segmentation of Conjunctival Vessels for Early Detection of Diabetic Vascular Changes Asma Mohamed Naim, Achintha Iroshan Kondarage, Rukshani Liyanaarachchi, and 2 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7871199/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 13 You are reading this latest preprint version Abstract Early detection of systemic vascular disorders such as diabetes and arterial tortuosity syndrome relies on identifying changes in vessel morphology, including tortuosity and diameter. While retinal imaging is a clinical standard for microvascular assessment, its high cost and requirement for specialist expertise limit its accessibility for large-scale screening. The bulbar conjunctiva, by contrast, offers a non-invasive, cost-effective, and readily accessible alternative for vascular imaging. In this study, we propose a deep learning-based framework designed to extract diameter-specific conjunctival vessels using a hybrid architecture that combines dilated convolutions with transformer-based attention mechanisms. The model incorporates Multi-Head Self-Attention at the bottleneck to model long-range dependencies within the image, and Multi-Head Cross-Attention at each decoder level to enhance selective reconstruction of diameter-relevant features. Our architecture is evaluated on a custom dataset comprising healthy individuals and patients with diabetes with varying complications. Compared with state-of-the-art baselines, including IterNet and U$^2$-Net, the proposed method achieved superior segmentation performance, especially in isolating vessels within clinically relevant diameter ranges, enabling accurate quantification of vessel tortuosity. We demonstrate statistically significant differences in tortuosity across diabetic subgroups, demonstrating the translational potential of conjunctival imaging as a scalable tool for early screening and monitoring of diabetic and systemic vascular complications. Biological sciences/Computational biology and bioinformatics Health sciences/Diseases Physical sciences/Engineering Health sciences/Health care Health sciences/Medical research Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Editorial decision: Revision requested 17 Dec, 2025 Reviews received at journal 17 Dec, 2025 Reviews received at journal 16 Dec, 2025 Reviewers agreed at journal 15 Dec, 2025 Reviewers agreed at journal 15 Dec, 2025 Reviewers agreed at journal 15 Dec, 2025 Reviewers agreed at journal 15 Dec, 2025 Reviewers agreed at journal 15 Dec, 2025 Reviewers invited by journal 15 Dec, 2025 Editor assigned by journal 09 Dec, 2025 Editor invited by journal 08 Dec, 2025 Submission checks completed at journal 26 Oct, 2025 First submitted to journal 26 Oct, 2025 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-7871199","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":561429077,"identity":"9d2a6cda-53c6-4412-9b28-fc531ccf9063","order_by":0,"name":"Asma Mohamed Naim","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA8UlEQVRIiWNgGAWjYPACCQY29ubjPz4AmWzsxGrh4zmWIDkDpIWZWHvkJHIMpHlALEJa+PtPJ34uqLGIZgNqMbb5tU2ej5mB8cPHHDwuupG7WXrGMYncNp5nBcm5fbcN25gZmCVnbsNjzQ3eDdI8bEAt7MkbDuf23GYEamFj5sWjRf782c2/ef4BtTAkGDZb9ty2J6jF4EDuNmneNqAWjhRjZoYftxMJajG8kbvNmrcP5JdjaYy9DbeT25gZm/H6RQ7osNs83+py57c3H2P48ee2LZBx8MNHfN5HAYxtYLKBWPUg8IcUxaNgFIyCUTBSAABK/E+mRI7S7QAAAABJRU5ErkJggg==","orcid":"","institution":"University of Moratuwa","correspondingAuthor":true,"prefix":"","firstName":"Asma","middleName":"Mohamed","lastName":"Naim","suffix":""},{"id":561429081,"identity":"e6ddda77-6fbf-4c31-92a1-25685e7c735e","order_by":1,"name":"Achintha Iroshan Kondarage","email":"","orcid":"","institution":"University of Birmingham","correspondingAuthor":false,"prefix":"","firstName":"Achintha","middleName":"Iroshan","lastName":"Kondarage","suffix":""},{"id":561429084,"identity":"314380ee-b70d-4075-baba-7320a8b59d3e","order_by":2,"name":"Rukshani Liyanaarachchi","email":"","orcid":"","institution":"University of Moratuwa","correspondingAuthor":false,"prefix":"","firstName":"Rukshani","middleName":"","lastName":"Liyanaarachchi","suffix":""},{"id":561429089,"identity":"d3f62323-fa1d-4d87-83b8-132bc6c6acd9","order_by":3,"name":"Saroj Jayasinghe","email":"","orcid":"","institution":"University of Colombo","correspondingAuthor":false,"prefix":"","firstName":"Saroj","middleName":"","lastName":"Jayasinghe","suffix":""},{"id":561429090,"identity":"3e0d84f0-2201-446c-9b5f-4d557de3b1e5","order_by":4,"name":"Anjula De Silva","email":"","orcid":"","institution":"Ear Science Institute Australia","correspondingAuthor":false,"prefix":"","firstName":"Anjula","middleName":"","lastName":"De Silva","suffix":""}],"badges":[],"createdAt":"2025-10-15 19:23:13","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7871199/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7871199/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":98411760,"identity":"935d857a-dfd3-4dd4-a78b-d20e080b1c0e","added_by":"auto","created_at":"2025-12-17 13:55:34","extension":"json","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":7598,"visible":true,"origin":"","legend":"","description":"","filename":"1d0f4b1f8d164bd186ef435781ffc3ae.json","url":"https://assets-eu.researchsquare.com/files/rs-7871199/v1/55696636f0c8080aa6616d8a.json"},{"id":98441530,"identity":"4c0d21cb-b016-4139-9d0c-3bc5286659d7","added_by":"auto","created_at":"2025-12-17 17:05:34","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":20371348,"visible":true,"origin":"","legend":"","description":"","filename":"TransformerBasedDiameterSpecificSegmentationofConjunctivalVesselsforEarlyDetectionofDiabeticVascularChangesManuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7871199/v1_covered_5b674215-c159-4aa4-809f-b798d6052332.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Transformer-Based Diameter-Specific Segmentation of Conjunctival Vessels for Early Detection of Diabetic Vascular Changes","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":true,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"","lastPublishedDoi":"10.21203/rs.3.rs-7871199/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7871199/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Early detection of systemic vascular disorders such as diabetes and arterial tortuosity syndrome relies on identifying changes in vessel morphology, including tortuosity and diameter. While retinal imaging is a clinical standard for microvascular assessment, its high cost and requirement for specialist expertise limit its accessibility for large-scale screening. The bulbar conjunctiva, by contrast, offers a non-invasive, cost-effective, and readily accessible alternative for vascular imaging. In this study, we propose a deep learning-based framework designed to extract diameter-specific conjunctival vessels using a hybrid architecture that combines dilated convolutions with transformer-based attention mechanisms. The model incorporates Multi-Head Self-Attention at the bottleneck to model long-range dependencies within the image, and Multi-Head Cross-Attention at each decoder level to enhance selective reconstruction of diameter-relevant features. Our architecture is evaluated on a custom dataset comprising healthy individuals and patients with diabetes with varying complications. Compared with state-of-the-art baselines, including IterNet and U$^2$-Net, the proposed method achieved superior segmentation performance, especially in isolating vessels within clinically relevant diameter ranges, enabling accurate quantification of vessel tortuosity. We demonstrate statistically significant differences in tortuosity across diabetic subgroups, demonstrating the translational potential of conjunctival imaging as a scalable tool for early screening and monitoring of diabetic and systemic vascular complications.","manuscriptTitle":"Transformer-Based Diameter-Specific Segmentation of Conjunctival Vessels for Early Detection of Diabetic Vascular Changes","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-12-17 13:55:30","doi":"10.21203/rs.3.rs-7871199/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-12-17T08:55:56+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-12-17T08:26:04+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-12-16T23:40:54+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"329637566650676308987433023996581339557","date":"2025-12-15T16:19:06+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"303356674028389697524004299657451341109","date":"2025-12-15T13:43:02+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"149605162704279401097903437303808799847","date":"2025-12-15T12:52:40+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"199536924092318985071366798427847643533","date":"2025-12-15T12:35:55+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"333527940252009697450471634625509316450","date":"2025-12-15T11:40:02+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-12-15T11:34:09+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-12-09T09:53:26+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2025-12-08T05:10:03+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-10-26T22:03:23+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2025-10-26T22:01:32+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"9fbb130c-9747-498b-abbc-58561fbb4347","owner":[],"postedDate":"December 17th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[{"id":59779989,"name":"Biological sciences/Computational biology and bioinformatics"},{"id":59779990,"name":"Health sciences/Diseases"},{"id":59779991,"name":"Physical sciences/Engineering"},{"id":59779992,"name":"Health sciences/Health care"},{"id":59779993,"name":"Health sciences/Medical research"}],"tags":[],"updatedAt":"2026-04-09T06:08:48+00:00","versionOfRecord":[],"versionCreatedAt":"2025-12-17 13:55:30","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7871199","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7871199","identity":"rs-7871199","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}