A Noval Approach based on Dual-Branch Encoder and Attention Skip Connections Decoder for Hard Exudate Segmentation

A Noval Approach based on Dual-Branch Encoder and Attention Skip Connections Decoder for Hard Exudate Segmentation | 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 A Noval Approach based on Dual-Branch Encoder and Attention Skip Connections Decoder for Hard Exudate Segmentation Bo Li, Beiji Zou, Xiaoxia Xiao, Qinghua Peng, Junfeng Yan, Wensheng Zhang, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4573655/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 Diabetic retinopathy (DR) is a chronic condition that can lead to significant vision loss and even blindness. Existing deep networks for hard exudate segmentation in fundus images face two primary challenges: ( 1 ) The receptive field of traditional convolution operations is limited, resulting in poor hard exudate extraction performance; ( 2 ) Due to the irregular distribution and different sizes of fine exudates, it is easy to lose information about tiny exudates during the feature extraction process. To address these challenges, we propose DBASNet, a novel lesion segmentation model. In order to solve the problem of insufficient segmentation caused by the limitations of the receptive field, we propose a new multi-scale attention feature extraction (MAT) module. Combined with the dual encoder structure, the features extracted by MAT and EfficientNet in the dual branches are fused to effectively expand the perceptual field and avoid information loss. We also propose an attentional skip connection (AS) module in the decoder to filter and retain channel and spatial information, enrich skip connections and carry feature information of tiny lesions. Experiments on publicly available datasets IDRiD and E-Ophtha-EX demonstrate effectiveness of our method. DBASNet achieves 79.48, 80.35, 79.81, and 66.64% of recall, precision, Dice, and IOU metrics on IDRiD and 52.73, 60.33, 56.16, and 39.82% on E-Ophtha-EX, respectively. DBASNet outperforms some state-of-the-art approaches. The quantitative and qualitative findings unequivocally establish the pre-eminence of DBASNet in the field of lesion segmentation relevant to diabetic retinopathy. Biological sciences/Computational biology and bioinformatics/Computational models Biological sciences/Computational biology and bioinformatics/Computational neuroscience Biological sciences/Computational biology and bioinformatics/Image processing Biological sciences/Computational biology and bioinformatics/Machine learning Biological sciences/Computational biology and bioinformatics/Predictive medicine Hard exudates segmentation Diabetic retinopathy Deep learning Fundus image Dual-branch 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-4573655","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":320560173,"identity":"953e15bc-a7e9-4ae0-83d2-9a93ba2bbce3","order_by":0,"name":"Bo Li","email":"","orcid":"","institution":"Hunan University of Chinese Medicine","correspondingAuthor":false,"prefix":"","firstName":"Bo","middleName":"","lastName":"Li","suffix":""},{"id":320560176,"identity":"3101320d-3bf2-446d-9a50-215e865b01e7","order_by":1,"name":"Beiji Zou","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAvklEQVRIiWNgGAWjYBACA4YDQLICwpEgQcsZ0rQAAWMbKVrMGY8/fMw7z87e4ADzwds8DHZ5BLVYNhxINubdlpy44QBbsjUPQ3IxYYcdOHBMmnfbgQSDAzxm0jwMBxIbCGs52CbNO+cA0GH834jVcphNmrfhAOOGAzxsxGmxbDjGbDjnWHLizMNsxpZzDJIJazGXOP7wwZsaO3u+480Pb7ypsCOshUHiAJTBDHYnQfVAwE/Y1FEwCkbBKBjpAABjYTsUZxgScQAAAABJRU5ErkJggg==","orcid":"","institution":"Central South University","correspondingAuthor":true,"prefix":"","firstName":"Beiji","middleName":"","lastName":"Zou","suffix":""},{"id":320560178,"identity":"1f9d2e57-745b-41bd-b05c-72f5be32aa51","order_by":2,"name":"Xiaoxia Xiao","email":"","orcid":"","institution":"Hunan University of Chinese Medicine","correspondingAuthor":false,"prefix":"","firstName":"Xiaoxia","middleName":"","lastName":"Xiao","suffix":""},{"id":320560179,"identity":"78f0fb33-d18c-4e82-a97a-39f5ca1fa1bb","order_by":3,"name":"Qinghua Peng","email":"","orcid":"","institution":"Hunan University of Chinese Medicine","correspondingAuthor":false,"prefix":"","firstName":"Qinghua","middleName":"","lastName":"Peng","suffix":""},{"id":320560181,"identity":"4c8c90e0-bec6-4df2-8f42-26f3c7c776ab","order_by":4,"name":"Junfeng Yan","email":"","orcid":"","institution":"Hunan University of Chinese Medicine","correspondingAuthor":false,"prefix":"","firstName":"Junfeng","middleName":"","lastName":"Yan","suffix":""},{"id":320560183,"identity":"ef7dad30-0b94-4a5e-b160-fadc4246b936","order_by":5,"name":"Wensheng Zhang","email":"","orcid":"","institution":"University of Chinese Academy of Sciences (UCAS)","correspondingAuthor":false,"prefix":"","firstName":"Wensheng","middleName":"","lastName":"Zhang","suffix":""},{"id":320560185,"identity":"34a43155-b8cb-4f26-8226-5491fae4db19","order_by":6,"name":"Yang Li","email":"","orcid":"","institution":"Hunan University of Chinese Medicine","correspondingAuthor":false,"prefix":"","firstName":"Yang","middleName":"","lastName":"Li","suffix":""}],"badges":[],"createdAt":"2024-06-13 05:27:16","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4573655/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4573655/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":68139950,"identity":"db34c20f-9b42-4d92-b59b-78ad1359cccb","added_by":"auto","created_at":"2024-11-04 04:39:17","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":674789,"visible":true,"origin":"","legend":"","description":"","filename":"ANovalApproachforHardExudateSegmentation.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4573655/v1_covered_1478ed52-3a46-4ddf-9726-6b57961dccfd.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"A Noval Approach based on Dual-Branch Encoder and Attention Skip Connections Decoder for Hard Exudate Segmentation","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":"Hard exudates segmentation, Diabetic retinopathy, Deep learning Fundus image, Dual-branch","lastPublishedDoi":"10.21203/rs.3.rs-4573655/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4573655/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eDiabetic retinopathy (DR) is a chronic condition that can lead to significant vision loss and even blindness. Existing deep networks for hard exudate segmentation in fundus images face two primary challenges: (\u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e1\u003c/span\u003e) The receptive field of traditional convolution operations is limited, resulting in poor hard exudate extraction performance; (\u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e) Due to the irregular distribution and different sizes of fine exudates, it is easy to lose information about tiny exudates during the feature extraction process. To address these challenges, we propose DBASNet, a novel lesion segmentation model. In order to solve the problem of insufficient segmentation caused by the limitations of the receptive field, we propose a new multi-scale attention feature extraction (MAT) module. Combined with the dual encoder structure, the features extracted by MAT and EfficientNet in the dual branches are fused to effectively expand the perceptual field and avoid information loss. We also propose an attentional skip connection (AS) module in the decoder to filter and retain channel and spatial information, enrich skip connections and carry feature information of tiny lesions. Experiments on publicly available datasets IDRiD and E-Ophtha-EX demonstrate effectiveness of our method. DBASNet achieves 79.48, 80.35, 79.81, and 66.64% of recall, precision, Dice, and IOU metrics on IDRiD and 52.73, 60.33, 56.16, and 39.82% on E-Ophtha-EX, respectively. DBASNet outperforms some state-of-the-art approaches. The quantitative and qualitative findings unequivocally establish the pre-eminence of DBASNet in the field of lesion segmentation relevant to diabetic retinopathy.\u003c/p\u003e","manuscriptTitle":"A Noval Approach based on Dual-Branch Encoder and Attention Skip Connections Decoder for Hard Exudate Segmentation","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-07-01 10:42:25","doi":"10.21203/rs.3.rs-4573655/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":"f0f7f824-f9c4-41e1-afd4-1cc8c831eddc","owner":[],"postedDate":"July 1st, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":33894370,"name":"Biological sciences/Computational biology and bioinformatics/Computational models"},{"id":33894371,"name":"Biological sciences/Computational biology and bioinformatics/Computational neuroscience"},{"id":33894372,"name":"Biological sciences/Computational biology and bioinformatics/Image processing"},{"id":33894373,"name":"Biological sciences/Computational biology and bioinformatics/Machine learning"},{"id":33894374,"name":"Biological sciences/Computational biology and bioinformatics/Predictive medicine"}],"tags":[],"updatedAt":"2024-11-04T04:38:54+00:00","versionOfRecord":[],"versionCreatedAt":"2024-07-01 10:42:25","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-4573655","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4573655","identity":"rs-4573655","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}