FFD-YOLO11: A Lightweight and High-Precision Framework for Automated Fundus Disease Detection

FFD-YOLO11: A Lightweight and High-Precision Framework for Automated Fundus Disease Detection | 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 FFD-YOLO11: A Lightweight and High-Precision Framework for Automated Fundus Disease Detection ZIHENG CHENG, KAI LIU, XUSAN YANG This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8254879/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 Automated detection of ocular lesions from fundus images is of great significance for disease screening and early diagnosis. However, existing methods are often constrained by the trade-off between model accuracy and computational efficiency, particularly under resource-limited hardware conditions, where missed detections and false positives are common.In this paper, we propose FFD-YOLO11 (Fundus Disease Detection-YOLO11), a novel and efficient detection framework based on the YOLO11 architecture. The proposed model integrates the RepViT structure and Efficient Multi-scale Attention (EMA) into the backbone to enhance the representation of pathological features. Moreover, a Large Separable Kernel Attention (LSKA) mechanism is embedded in the Spatial Pyramid Pooling Fast (SPPF) module to expand the receptive field and strengthen contextual feature modeling.Furthermore, we design a Lightweight Shared Convolutional Detection Head (LSCD) and a Feature Diffusion Pyramid Network (FDPN), which effectively fuse multi-scale features while significantly reducing the model parameters. Experimental results show that FFD-YOLO11 achieves 97.4% mAP with only 2.6M parameters, outperforming the baseline by 5.1% and achieving the best performance among comparable models. Visualization analysis further demonstrates the model’s precise focus and localization of clinically critical lesion regions.Overall, FFD-YOLO11 provides a high-accuracy, lightweight, and robust detection solution suitable for clinical environments and embedded medical imaging systems, offering a new technological approach for intelligent ophthalmic diagnosis assistance. Biological sciences/Computational biology and bioinformatics Health sciences/Diseases Physical sciences/Engineering Physical sciences/Mathematics and computing Health sciences/Medical research Fundus disease lightweight accuracy feature fusion multi-scale 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-8254879","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":554674382,"identity":"c39094f1-a275-48c2-a119-b26e59c5442c","order_by":0,"name":"ZIHENG CHENG","email":"","orcid":"","institution":"Nanjing University of Information Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"ZIHENG","middleName":"","lastName":"CHENG","suffix":""},{"id":554674383,"identity":"4d7af60c-a8d1-40c8-910a-1194b8bce829","order_by":1,"name":"KAI LIU","email":"","orcid":"","institution":"University of Chines academy of Sciences","correspondingAuthor":false,"prefix":"","firstName":"KAI","middleName":"","lastName":"LIU","suffix":""},{"id":554674384,"identity":"88651890-649f-4b15-a557-d0d3ef2e866d","order_by":2,"name":"XUSAN YANG","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA4klEQVRIiWNgGAWjYFAD9sYGZhK18BwkWYtEAgNxWgxupD/8XNhmlycf+bjtcWEbgzx/A/OzB/i0SM7IMZae2ZZcbHg7sd14ZhuD4YwDbOYG+LTwS+QwSPO2MSdunJ3YBmQwMG5g4GGTwKeFTSL98W/etvrEjTMPgrXYE9TCL5FgBlR5OHG+BCNYSyJBLZI9b8ysec4dT9zAA/QLzzmJ5BmH2czwajE4nv74Nk9ZdeL89uPPHvOU2dj2tzc/w6sFDBjZgHoPMLABGUDFxMXOHwYG+QagFhBjFIyCUTAKRgE6AAB7UkItw7TXDgAAAABJRU5ErkJggg==","orcid":"","institution":"Chinese academy of Sciences","correspondingAuthor":true,"prefix":"","firstName":"XUSAN","middleName":"","lastName":"YANG","suffix":""}],"badges":[],"createdAt":"2025-12-02 02:08:10","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8254879/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8254879/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":97895805,"identity":"b37d050d-78fe-47d4-85f6-14622e24c051","added_by":"auto","created_at":"2025-12-10 15:35:01","extension":"docx","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":2796163,"visible":true,"origin":"","legend":"","description":"","filename":"FFDYOLO11ALightweightandHighPrecisionFrameworkforAutomatedFundusDiseaseDetection.docx","url":"https://assets-eu.researchsquare.com/files/rs-8254879/v1/f2601e134c4af45312d93b24.docx"},{"id":97792644,"identity":"cc12c747-93a2-43a9-bfa3-d4555a3e4b3e","added_by":"auto","created_at":"2025-12-09 12:14:30","extension":"json","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":5063,"visible":true,"origin":"","legend":"","description":"","filename":"015d3e6efb8a498880ea95d4a3f8589c.json","url":"https://assets-eu.researchsquare.com/files/rs-8254879/v1/1a3568a6f1dcac769ae8e6c6.json"},{"id":97792646,"identity":"6f6a7237-d049-4aa8-ad73-e74338ed6df3","added_by":"auto","created_at":"2025-12-09 12:14:30","extension":"xml","order_by":2,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":92271,"visible":true,"origin":"","legend":"","description":"","filename":"015d3e6efb8a498880ea95d4a3f8589c1enriched.xml","url":"https://assets-eu.researchsquare.com/files/rs-8254879/v1/27bac7884f14bcd2afb6a053.xml"},{"id":97792645,"identity":"1a8fb35a-470b-4bdd-aa70-299a71ab1e06","added_by":"auto","created_at":"2025-12-09 12:14:30","extension":"png","order_by":3,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":408037,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-8254879/v1/86ef1986a3c173172844eee0.png"},{"id":97898337,"identity":"eb4d9179-2a05-41c9-a8b5-b576bae04349","added_by":"auto","created_at":"2025-12-10 15:39:02","extension":"jpeg","order_by":4,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":720851,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage2.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-8254879/v1/9aefb8295aedb0dc9c130601.jpeg"},{"id":97898314,"identity":"b437df0b-a2d0-453a-b81d-f5eca599b270","added_by":"auto","created_at":"2025-12-10 15:38:59","extension":"jpeg","order_by":5,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":435364,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage3.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-8254879/v1/5369dc33f18cc67a05cbb754.jpeg"},{"id":97792649,"identity":"8f9255fa-3f41-4d88-aa60-aea1bebc9987","added_by":"auto","created_at":"2025-12-09 12:14:30","extension":"jpeg","order_by":6,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":472905,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage4.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-8254879/v1/6fa3e1e50d30e90a01bfb5ef.jpeg"},{"id":97898124,"identity":"33c84dfd-3af1-4e08-b144-e0abef2346de","added_by":"auto","created_at":"2025-12-10 15:38:41","extension":"png","order_by":7,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":73771,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage5.png","url":"https://assets-eu.researchsquare.com/files/rs-8254879/v1/ee1e05971612cfb37b946b6e.png"},{"id":97897750,"identity":"a1bd844a-1b96-475a-bcbf-3dfe09943920","added_by":"auto","created_at":"2025-12-10 15:38:12","extension":"jpeg","order_by":8,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":96849,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage6.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-8254879/v1/d78a338f5cebb24aed96cd13.jpeg"},{"id":97897880,"identity":"8aa7cbb1-81bb-4ef6-b892-54490f5c2b49","added_by":"auto","created_at":"2025-12-10 15:38:23","extension":"jpeg","order_by":9,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":969937,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage7.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-8254879/v1/12c876c6dd670ce413e2721b.jpeg"},{"id":97898315,"identity":"0db0b6a8-1ca0-4331-bb11-6366c5ef943d","added_by":"auto","created_at":"2025-12-10 15:38:59","extension":"png","order_by":10,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":68527,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-8254879/v1/372f4ce8c9c4263686699ccb.png"},{"id":97792662,"identity":"0eb7602e-49c3-4aaa-a8a5-30c5502b24b5","added_by":"auto","created_at":"2025-12-09 12:14:30","extension":"png","order_by":11,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":126232,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-8254879/v1/48ccc6bb95da40bae1572eec.png"},{"id":97897944,"identity":"00fee988-2e80-4b60-a5bf-1c420f6aac90","added_by":"auto","created_at":"2025-12-10 15:38:30","extension":"png","order_by":12,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":71038,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage3.png","url":"https://assets-eu.researchsquare.com/files/rs-8254879/v1/df854d10060d92dffb94cbb0.png"},{"id":97792657,"identity":"239d90f3-9269-4e49-ab60-020c9434f3e6","added_by":"auto","created_at":"2025-12-09 12:14:30","extension":"png","order_by":13,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":114208,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage4.png","url":"https://assets-eu.researchsquare.com/files/rs-8254879/v1/409988951a092773e664ab8e.png"},{"id":97898700,"identity":"bf4715cb-9c0b-479c-8ac4-dbc6e3fbd153","added_by":"auto","created_at":"2025-12-10 15:39:29","extension":"png","order_by":14,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":25274,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage5.png","url":"https://assets-eu.researchsquare.com/files/rs-8254879/v1/0cb28946ccdc43c0c226716c.png"},{"id":97792655,"identity":"ec0ae953-72b4-444e-877d-dad2d29a10ee","added_by":"auto","created_at":"2025-12-09 12:14:30","extension":"png","order_by":15,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":16810,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage6.png","url":"https://assets-eu.researchsquare.com/files/rs-8254879/v1/0a60a70c101da4d854502ab9.png"},{"id":97792659,"identity":"fbdffa4c-6d73-45be-9ff6-2c20f4c35632","added_by":"auto","created_at":"2025-12-09 12:14:30","extension":"png","order_by":16,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":244652,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage7.png","url":"https://assets-eu.researchsquare.com/files/rs-8254879/v1/bef6ee4eb502d70688fbff4f.png"},{"id":97897307,"identity":"3c01f49d-8295-40a0-a4da-cad7848b2d45","added_by":"auto","created_at":"2025-12-10 15:37:44","extension":"xml","order_by":17,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":91587,"visible":true,"origin":"","legend":"","description":"","filename":"015d3e6efb8a498880ea95d4a3f8589c1structuring.xml","url":"https://assets-eu.researchsquare.com/files/rs-8254879/v1/5dd37e025ddaa8be9d61f826.xml"},{"id":97897337,"identity":"9e607556-2809-4894-a1c4-52c024369fbb","added_by":"auto","created_at":"2025-12-10 15:37:45","extension":"html","order_by":18,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":103787,"visible":true,"origin":"","legend":"","description":"","filename":"earlyproof.html","url":"https://assets-eu.researchsquare.com/files/rs-8254879/v1/39defd12d54fed4dd2637189.html"},{"id":98775839,"identity":"c45b1b06-841d-464d-8c5b-974763de85ce","added_by":"auto","created_at":"2025-12-22 12:21:18","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1156191,"visible":true,"origin":"","legend":"","description":"","filename":"FFDYOLO11ALightweightandHighPrecisionFrameworkforAutomatedFundusDiseaseDetection.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8254879/v1_covered_2e1b2af6-6d66-47a4-9d0b-0674ee076a8d.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"FFD-YOLO11: A Lightweight and High-Precision Framework for Automated Fundus Disease Detection","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"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":"Fundus disease, lightweight, accuracy, feature fusion, multi-scale","lastPublishedDoi":"10.21203/rs.3.rs-8254879/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8254879/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eAutomated detection of ocular lesions from fundus images is of great significance for disease screening and early diagnosis. However, existing methods are often constrained by the trade-off between model accuracy and computational efficiency, particularly under resource-limited hardware conditions, where missed detections and false positives are common.In this paper, we propose FFD-YOLO11 (Fundus Disease Detection-YOLO11), a novel and efficient detection framework based on the YOLO11 architecture. The proposed model integrates the RepViT structure and Efficient Multi-scale Attention (EMA) into the backbone to enhance the representation of pathological features. Moreover, a Large Separable Kernel Attention (LSKA) mechanism is embedded in the Spatial Pyramid Pooling Fast (SPPF) module to expand the receptive field and strengthen contextual feature modeling.Furthermore, we design a Lightweight Shared Convolutional Detection Head (LSCD) and a Feature Diffusion Pyramid Network (FDPN), which effectively fuse multi-scale features while significantly reducing the model parameters. Experimental results show that FFD-YOLO11 achieves 97.4% mAP with only 2.6M parameters, outperforming the baseline by 5.1% and achieving the best performance among comparable models. Visualization analysis further demonstrates the model\u0026rsquo;s precise focus and localization of clinically critical lesion regions.Overall, FFD-YOLO11 provides a high-accuracy, lightweight, and robust detection solution suitable for clinical environments and embedded medical imaging systems, offering a new technological approach for intelligent ophthalmic diagnosis assistance.\u003c/p\u003e","manuscriptTitle":"FFD-YOLO11: A Lightweight and High-Precision Framework for Automated Fundus Disease Detection","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-12-09 12:14:25","doi":"10.21203/rs.3.rs-8254879/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":"f0b83bf4-e9d8-41ea-bf46-0702629bf8fd","owner":[],"postedDate":"December 9th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":59028998,"name":"Biological sciences/Computational biology and bioinformatics"},{"id":59028999,"name":"Health sciences/Diseases"},{"id":59029000,"name":"Physical sciences/Engineering"},{"id":59029001,"name":"Physical sciences/Mathematics and computing"},{"id":59029002,"name":"Health sciences/Medical research"}],"tags":[],"updatedAt":"2025-12-20T06:53:57+00:00","versionOfRecord":[],"versionCreatedAt":"2025-12-09 12:14:25","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8254879","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8254879","identity":"rs-8254879","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}