DSGSU-Net: A U-Net-Based Model for Tomato Leaf Disease Segmentation Using Depthwise Separable Convolutions and Ghost Sampling

DSGSU-Net: A U-Net-Based Model for Tomato Leaf Disease Segmentation Using Depthwise Separable Convolutions and Ghost Sampling | 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 DSGSU-Net: A U-Net-Based Model for Tomato Leaf Disease Segmentation Using Depthwise Separable Convolutions and Ghost Sampling jansi e, kavitha B R This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6512719/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 12 You are reading this latest preprint version Abstract Tomato leaf disease poses a significant threat to global agricultural productivity, underscoring the need for accurate and automated segmentation techniques for early detection and intervention. In this study, we proposed DSGSU-Net, an enhanced U-Net-based architecture explicitly designed for the precise segmentation of tomato leaf diseases. The model incorporates depthwise separable convolutions for efficient feature extraction, dilated convolutions in deeper layers for multi-scale context aggregation, and Ghost Sampling in the decoder for improved upsampling. To further enhance segmentation performance, a hybrid loss function combining Dice Loss and Focal Loss is utilized to manage class imbalance and enhance the boundary delineation. Experiments conducted on the PlantVillage dataset (bacterial spot class) demonstrated that DSGSU-Net achieved an accuracy of 0.9572, an F1-score of 0.8276,precision of 0.7156,recall of 0.9885, IoU of 0.7102, and a Dice coefficient of 0.9822. The results show that DSGSU-Net outperforms conventional U-Net models in segmentation accuracy and computational efficiency, making it a strong contender for practical use in precision agriculture and disease surveillance. Biological sciences/Plant sciences Health sciences/Diseases Tomato leaf Deep learning enhanced U-net depthwise separable convolutions Ghost sampling dilated convolutions Segmentation Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Editorial decision: Revision requested 24 Oct, 2025 Reviews received at journal 23 Oct, 2025 Reviews received at journal 10 Oct, 2025 Reviewers agreed at journal 24 Sep, 2025 Reviewers agreed at journal 20 Sep, 2025 Reviewers agreed at journal 17 Sep, 2025 Reviewers agreed at journal 17 Sep, 2025 Reviewers invited by journal 13 Jun, 2025 Editor invited by journal 28 May, 2025 Editor assigned by journal 23 May, 2025 Submission checks completed at journal 29 Apr, 2025 First submitted to journal 29 Apr, 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-6512719","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":470936210,"identity":"0df47933-d724-4232-bcf4-18d4488d711a","order_by":0,"name":"jansi e","email":"","orcid":"","institution":"Vellore Institute of Technology University","correspondingAuthor":false,"prefix":"","firstName":"jansi","middleName":"","lastName":"e","suffix":""},{"id":470936211,"identity":"342b2ce1-9e78-4db3-a207-9e3d550247f0","order_by":1,"name":"kavitha B R","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA4UlEQVRIie3OPQrCMByH4V8IOEVcIwW9QjpJwY+rRApOegBxUBDSRXTtMQRBHFM6uFS8QkVw1kUcTf1YU0eHvJAhf/IkAVyuP4ybpckMEKAa8jUrtmUkeZGKhJQ/ErwJE/g8Y68eZX5623XR8rI7Pz3QrM2oym3EY0OhkyxEsBxtufmYH2sSCRtpYCB1oihEVt0IQ8gaRHErqV0KMjWEnQvSKyUeD7UhaUFIbki/lNTjs9YHtWfBouLncsDDOC0h/NifX8dq0mgxmiePdruziqKLlXxj3ysA+st5l8vlcll7AsgbSNvf4RrrAAAAAElFTkSuQmCC","orcid":"","institution":"Vellore Institute of Technology University","correspondingAuthor":true,"prefix":"","firstName":"kavitha","middleName":"B","lastName":"R","suffix":""}],"badges":[],"createdAt":"2025-04-23 12:38:44","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6512719/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6512719/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":84830195,"identity":"429e2522-235f-4811-91ab-f35ac4311a55","added_by":"auto","created_at":"2025-06-17 18:47:41","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":2915883,"visible":true,"origin":"","legend":"","description":"","filename":"paper.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6512719/v1_covered_5589390b-63cf-4d29-9904-9b7268c1f06f.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"\u003cp\u003eDSGSU-Net: A U-Net-Based Model for Tomato Leaf Disease Segmentation Using Depthwise Separable Convolutions and Ghost Sampling\u003c/p\u003e","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"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":"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":"Tomato leaf, Deep learning, enhanced U-net, depthwise separable convolutions, Ghost sampling, dilated convolutions, Segmentation","lastPublishedDoi":"10.21203/rs.3.rs-6512719/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6512719/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Tomato leaf disease poses a significant threat to global agricultural productivity, underscoring the need for accurate and automated segmentation techniques for early detection and intervention. In this study, we proposed DSGSU-Net, an enhanced U-Net-based architecture explicitly designed for the precise segmentation of tomato leaf diseases. The model incorporates depthwise separable convolutions for efficient feature extraction, dilated convolutions in deeper layers for multi-scale context aggregation, and Ghost Sampling in the decoder for improved upsampling. To further enhance segmentation performance, a hybrid loss function combining Dice Loss and Focal Loss is utilized to manage class imbalance and enhance the boundary delineation. Experiments conducted on the PlantVillage dataset (bacterial spot class) demonstrated that DSGSU-Net achieved an accuracy of 0.9572, an F1-score of 0.8276,precision of 0.7156,recall of 0.9885, IoU of 0.7102, and a Dice coefficient of 0.9822. The results show that DSGSU-Net outperforms conventional U-Net models in segmentation accuracy and computational efficiency, making it a strong contender for practical use in precision agriculture and disease surveillance.","manuscriptTitle":"DSGSU-Net: A U-Net-Based Model for Tomato Leaf Disease Segmentation Using Depthwise Separable Convolutions and Ghost Sampling","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-06-17 18:15:32","doi":"10.21203/rs.3.rs-6512719/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-10-24T06:02:52+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-10-23T06:41:50+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-10-10T15:24:05+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"317324859831391033007257611642535216970","date":"2025-09-24T13:08:28+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"325803773019724967680992731047009877369","date":"2025-09-20T09:26:36+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"206862671718797171393326380654596258428","date":"2025-09-17T14:16:42+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"10834482430014973299708845615591441692","date":"2025-09-17T11:29:57+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-06-13T13:16:07+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2025-05-28T09:41:18+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-05-23T08:50:38+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-04-29T06:59:34+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2025-04-29T06:58:24+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":"8b4107cb-7a8a-47e7-8cbb-91a9c750090f","owner":[],"postedDate":"June 17th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[{"id":50202559,"name":"Biological sciences/Plant sciences"},{"id":50202560,"name":"Health sciences/Diseases"}],"tags":[],"updatedAt":"2026-01-21T15:08:46+00:00","versionOfRecord":[],"versionCreatedAt":"2025-06-17 18:15:32","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-6512719","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6512719","identity":"rs-6512719","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}