Comparative Analysis of Convolutional and Vision Transformer Models for Automated Leukocyte Classification Enhanced by Generative Color Augmentation

Comparative Analysis of Convolutional and Vision Transformer Models for Automated Leukocyte Classification Enhanced by Generative Color Augmentation | 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 Comparative Analysis of Convolutional and Vision Transformer Models for Automated Leukocyte Classification Enhanced by Generative Color Augmentation João Kasprowicz, Alexandre Gonçalves Silva This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7926842/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 24 Apr, 2026 Read the published version in Signal, Image and Video Processing → Version 1 posted 8 You are reading this latest preprint version Abstract Manual differential leukocyte counting is a critical but time-consuming and subjective process. This study provides a rigorous comparative analysis of You OnlyLook Once v11 (YOLOv11) and Vision Transformer (ViT) architectures for classifying 14 types of leukocytes and artifacts from a private clinical dataset. We also evaluated the impact of HistAuGAN, a data augmentation technique that simulates real world staining variability, by training and evaluating models from both families with and without its application. The results demonstrated the consistent superiority of the ViT architecture over YOLOv11 in all experimental settings. Furthermore, the use of HistAuGAN promoted a universal and significant performance improvement across all tested models. The top performing configuration, the ViT-Base model trained with HistAuGAN, achieved a macro F1-Score of98.36% and an overall accuracy of 99.75% on the test set. We conclude that the synergy between an architecture capable of learning global features (ViT) and adomain-specific data augmentation technique that addresses practical challenges represents a state-of-the-art strategy, establishing a new performance benchmark for high granularity leukocyte classification and reinforcing the potentialof artificial intelligence to transform diagnostic hematology. Artificial Intelligence Leukocytes Image Interpretation Computer-Assisted Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 24 Apr, 2026 Read the published version in Signal, Image and Video Processing → Version 1 posted Editorial decision: Revision requested 24 Feb, 2026 Reviews received at journal 23 Feb, 2026 Reviewers agreed at journal 28 Oct, 2025 Reviewers agreed at journal 27 Oct, 2025 Reviewers invited by journal 27 Oct, 2025 Editor assigned by journal 23 Oct, 2025 Submission checks completed at journal 23 Oct, 2025 First submitted to journal 22 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-7926842","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":536309569,"identity":"b496fc39-4444-4873-a64b-4dd378d8a9d8","order_by":0,"name":"João Kasprowicz","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABBUlEQVRIiWNgGAWjYBACxgYIBoMDDAw2CWBWQgHxWtISGNhAWgwI2wQDhyFaGPBoYW5vfvhwRk1dnnl7j+GBH3/O5/HLdyd+eGDAIM8vdgC7DT3HjA03HDtcLHPmjMHBHp7bxZJtvJslgA4znDk7AbuWGQlmkg/YDiTOkMjdcJhB4nbihmO8G0BaEgxu49KS/k3ywb86qBaDcyAtm3/g15JjJrmxjRmqJeEASMs2/Lb0nCk2nNl3uFiC5/yHgz0HkhNntuVus0gwkMDpF8P29o0Pe77V5UmwtyV/+PHHLrGf+ezmmz8qbOT5pXFoaYDQGLISWJWDgDwDDi2jYBSMglEwCuAAABjVZ6pkByCvAAAAAElFTkSuQmCC","orcid":"","institution":"Universidade Federal de Santa Catarina","correspondingAuthor":true,"prefix":"","firstName":"João","middleName":"","lastName":"Kasprowicz","suffix":""},{"id":536309571,"identity":"d688a241-a809-4ed8-bdd9-ade556be57b9","order_by":1,"name":"Alexandre Gonçalves Silva","email":"","orcid":"","institution":"Universidade Federal de Santa Catarina","correspondingAuthor":false,"prefix":"","firstName":"Alexandre","middleName":"Gonçalves","lastName":"Silva","suffix":""}],"badges":[],"createdAt":"2025-10-22 22:23:18","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7926842/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7926842/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1007/s11760-026-05309-2","type":"published","date":"2026-04-24T15:58:52+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":95279579,"identity":"0fd5a2cd-5ca0-4aa6-b6ef-0d8aae1a5048","added_by":"auto","created_at":"2025-11-06 08:55:51","extension":"json","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":5122,"visible":true,"origin":"","legend":"","description":"","filename":"d95cb46255c047aba5706b898cfe168d.json","url":"https://assets-eu.researchsquare.com/files/rs-7926842/v1/4b544df67323e2500fb2a62d.json"},{"id":107927783,"identity":"0d840f8f-609c-49ce-83d8-1f23e641bcc0","added_by":"auto","created_at":"2026-04-27 16:04:26","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":779160,"visible":true,"origin":"","legend":"","description":"","filename":"lattex.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7926842/v1_covered_221cd769-d928-4b0c-88d8-9af1fe19b611.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Comparative Analysis of Convolutional and Vision Transformer Models for Automated Leukocyte Classification Enhanced by Generative Color Augmentation","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":"signal-image-and-video-processing","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"sivp","sideBox":"Learn more about [Signal, Image and Video Processing](http://link.springer.com/journal/11760)","snPcode":"11760","submissionUrl":"https://submission.nature.com/new-submission/11760/3","title":"Signal, Image and Video Processing","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Artificial Intelligence, Leukocytes, Image Interpretation, Computer-Assisted","lastPublishedDoi":"10.21203/rs.3.rs-7926842/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7926842/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Manual differential leukocyte counting is a critical but time-consuming and subjective process. This study provides a rigorous comparative analysis of You OnlyLook Once v11 (YOLOv11) and Vision Transformer (ViT) architectures for classifying 14 types of leukocytes and artifacts from a private clinical dataset. We also evaluated the impact of HistAuGAN, a data augmentation technique that simulates real world staining variability, by training and evaluating models from both families with and without its application. The results demonstrated the consistent superiority of the ViT architecture over YOLOv11 in all experimental settings. Furthermore, the use of HistAuGAN promoted a universal and significant performance improvement across all tested models. The top performing configuration, the ViT-Base model trained with HistAuGAN, achieved a macro F1-Score of98.36% and an overall accuracy of 99.75% on the test set. We conclude that the synergy between an architecture capable of learning global features (ViT) and adomain-specific data augmentation technique that addresses practical challenges represents a state-of-the-art strategy, establishing a new performance benchmark for high granularity leukocyte classification and reinforcing the potentialof artificial intelligence to transform diagnostic hematology.","manuscriptTitle":"Comparative Analysis of Convolutional and Vision Transformer Models for Automated Leukocyte Classification Enhanced by Generative Color Augmentation","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-11-06 08:55:46","doi":"10.21203/rs.3.rs-7926842/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2026-02-24T19:46:47+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-02-23T23:11:40+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"259251580947532640674160644841766186311","date":"2025-10-28T15:17:44+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"272232644647618062171054636128475088108","date":"2025-10-27T21:41:28+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-10-27T21:21:28+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-10-23T13:41:02+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-10-23T13:39:58+00:00","index":"","fulltext":""},{"type":"submitted","content":"Signal, Image and Video Processing","date":"2025-10-22T22:18:50+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"signal-image-and-video-processing","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"sivp","sideBox":"Learn more about [Signal, Image and Video Processing](http://link.springer.com/journal/11760)","snPcode":"11760","submissionUrl":"https://submission.nature.com/new-submission/11760/3","title":"Signal, Image and Video Processing","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"f5d972bd-0a10-46e9-8d3a-4d935d3ca3b1","owner":[],"postedDate":"November 6th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2026-04-27T16:02:19+00:00","versionOfRecord":{"articleIdentity":"rs-7926842","link":"https://doi.org/10.1007/s11760-026-05309-2","journal":{"identity":"signal-image-and-video-processing","isVorOnly":false,"title":"Signal, Image and Video Processing"},"publishedOn":"2026-04-24 15:58:52","publishedOnDateReadable":"April 24th, 2026"},"versionCreatedAt":"2025-11-06 08:55:46","video":"","vorDoi":"10.1007/s11760-026-05309-2","vorDoiUrl":"https://doi.org/10.1007/s11760-026-05309-2","workflowStages":[]},"version":"v1","identity":"rs-7926842","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7926842","identity":"rs-7926842","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}