Automated Thyroid Nodule Classification in Ultrasound Imaging Using a Hybrid Vision Transformer and Wasserstein GAN with Gradient Penalty

Automated Thyroid Nodule Classification in Ultrasound Imaging Using a Hybrid Vision Transformer and Wasserstein GAN with Gradient Penalty | 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 Automated Thyroid Nodule Classification in Ultrasound Imaging Using a Hybrid Vision Transformer and Wasserstein GAN with Gradient Penalty Naga Sujini Ganne, Sivadi Balakrishna This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7120864/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 19 Nov, 2025 Read the published version in Scientific Reports → Version 1 posted 15 You are reading this latest preprint version Abstract This study introduces an innovative hybrid model that combines the Vision Transformer (ViT) and Wasserstein Generative Adversarial Networks with Gradient Penalty (WGAN-GP) to enhance the accuracy and robustness of thyroid nodule detection. The Vision Transformer model leverages its powerful attention mechanism to capture global contextual information from ultrasound images. At the same time, WGAN-GP generates high-quality synthetic images to augment the training dataset and address class imbalance issues. The proposed hybrid model is evaluated on a comprehensive dataset of thyroid ultrasonography images, demonstrating significant improvements in classification accuracy, sensitivity, and specificity compared to traditional Convolutional Neural Network (CNN) approaches. The experimental results highlight the potential of integrating ViT-WGAN-GP for automated, reliable thyroid nodule classification, providing a promising tool for medical professionals in diagnostic radiology. This proposed framework surpasses current state-of-the-art diagnostic methods for thyroid-related abnormalities in ultrasound and histopathological datasets and can significantly assist medical professionals by alleviating the excessive burden on the medical fraternity. Biological sciences/Computational biology and bioinformatics Health sciences/Diseases Physical sciences/Engineering Health sciences/Health care Physical sciences/Mathematics and computing Health sciences/Medical research Thyroid nodules ultrasonography Vision Transformer Wasserstein GAN with Gradient Penalty hybrid model image classification medical imaging synthetic data augmentation diagnostic radiology Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 19 Nov, 2025 Read the published version in Scientific Reports → Version 1 posted Editorial decision: Revision requested 07 Aug, 2025 Reviews received at journal 06 Aug, 2025 Reviewers agreed at journal 06 Aug, 2025 Reviews received at journal 06 Aug, 2025 Reviewers agreed at journal 02 Aug, 2025 Reviewers agreed at journal 01 Aug, 2025 Reviewers agreed at journal 31 Jul, 2025 Reviewers agreed at journal 30 Jul, 2025 Reviews received at journal 30 Jul, 2025 Reviewers agreed at journal 30 Jul, 2025 Reviewers invited by journal 30 Jul, 2025 Editor invited by journal 22 Jul, 2025 Editor assigned by journal 20 Jul, 2025 Submission checks completed at journal 17 Jul, 2025 First submitted to journal 14 Jul, 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-7120864","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":494556562,"identity":"4531f6a6-af19-46d1-9592-5ca98f6bc747","order_by":0,"name":"Naga Sujini Ganne","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAvElEQVRIiWNgGAWjYJACgwQGCTkQ48ADUrQYg7UkkGJTYgOIJEqLOf8Zg4KHOyzS54cdfgi0xU5Ot4GAFssZOQYGiWckcjfeTjMAakk2NjtAQIvBDR6gljagltkJIC0HErcR1HL+DFhLuuHs9A9EajmQA9aSIC+dQ6wtN9IKQFoMN0jnFBxIMCDGL+cPbzP82VYnLz87ffOHDxV2cgS1AAGbAcSFYJKwchBgfgAi5RuIUz0KRsEoGAUjEAAAfZpEzvA/OHIAAAAASUVORK5CYII=","orcid":"","institution":"Vignan's Foundation for Science, Technology and Research","correspondingAuthor":true,"prefix":"","firstName":"Naga","middleName":"Sujini","lastName":"Ganne","suffix":""},{"id":494556563,"identity":"6177d191-8e18-47f1-a4bd-7d173fca160b","order_by":1,"name":"Sivadi Balakrishna","email":"","orcid":"","institution":"Vignan's Foundation for Science, Technology and Research","correspondingAuthor":false,"prefix":"","firstName":"Sivadi","middleName":"","lastName":"Balakrishna","suffix":""}],"badges":[],"createdAt":"2025-07-14 11:53:26","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7120864/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7120864/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1038/s41598-025-24651-y","type":"published","date":"2025-11-19T15:57:34+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":96650946,"identity":"458a24a3-2574-4ccf-b4f9-f98c00d7fc7f","added_by":"auto","created_at":"2025-11-24 16:13:00","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1000812,"visible":true,"origin":"","legend":"","description":"","filename":"GANPaper25.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7120864/v1_covered_84171f14-cbbd-431b-8e71-a403f28cb998.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Automated Thyroid Nodule Classification in Ultrasound Imaging Using a Hybrid Vision Transformer and Wasserstein GAN with Gradient Penalty","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":"Thyroid nodules, ultrasonography, Vision Transformer, Wasserstein GAN with Gradient Penalty, hybrid model, image classification, medical imaging, synthetic data augmentation, diagnostic radiology","lastPublishedDoi":"10.21203/rs.3.rs-7120864/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7120864/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eThis study introduces an innovative hybrid model that combines the Vision Transformer (ViT) and Wasserstein Generative Adversarial Networks with Gradient Penalty (WGAN-GP) to enhance the accuracy and robustness of thyroid nodule detection. The Vision Transformer model leverages its powerful attention mechanism to capture global contextual information from ultrasound images. At the same time, WGAN-GP generates high-quality synthetic images to augment the training dataset and address class imbalance issues. The proposed hybrid model is evaluated on a comprehensive dataset of thyroid ultrasonography images, demonstrating significant improvements in classification accuracy, sensitivity, and specificity compared to traditional Convolutional Neural Network (CNN) approaches. The experimental results highlight the potential of integrating ViT-WGAN-GP for automated, reliable thyroid nodule classification, providing a promising tool for medical professionals in diagnostic radiology. This proposed framework surpasses current state-of-the-art diagnostic methods for thyroid-related abnormalities in ultrasound and histopathological datasets and can significantly assist medical professionals by alleviating the excessive burden on the medical fraternity.\u003c/p\u003e","manuscriptTitle":"Automated Thyroid Nodule Classification in Ultrasound Imaging Using a Hybrid Vision Transformer and Wasserstein GAN with Gradient Penalty","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-08-04 04:09:54","doi":"10.21203/rs.3.rs-7120864/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-08-07T06:05:38+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-08-06T17:43:32+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"294721917230863943968064692872051366885","date":"2025-08-06T17:38:38+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-08-06T06:01:01+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"2349049871144415399323294280484021271","date":"2025-08-02T04:33:42+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"253477880004512721601563578331026390400","date":"2025-08-01T08:49:57+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"326844307314073799797643942917779096895","date":"2025-07-31T07:59:44+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"220808886903107998821155877104060693922","date":"2025-07-30T20:11:57+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-07-30T17:43:00+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"118141364099904689796083681826835162721","date":"2025-07-30T14:52:01+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-07-30T14:24:15+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2025-07-22T13:31:07+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-07-21T02:33:47+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-07-17T10:30:06+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2025-07-14T11:47:14+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":"f073c2ce-45cb-414a-a7ac-27d1c826d314","owner":[],"postedDate":"August 4th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[{"id":52527495,"name":"Biological sciences/Computational biology and bioinformatics"},{"id":52527496,"name":"Health sciences/Diseases"},{"id":52527497,"name":"Physical sciences/Engineering"},{"id":52527498,"name":"Health sciences/Health care"},{"id":52527499,"name":"Physical sciences/Mathematics and computing"},{"id":52527500,"name":"Health sciences/Medical research"}],"tags":[],"updatedAt":"2025-11-24T16:09:46+00:00","versionOfRecord":{"articleIdentity":"rs-7120864","link":"https://doi.org/10.1038/s41598-025-24651-y","journal":{"identity":"scientific-reports","isVorOnly":false,"title":"Scientific Reports"},"publishedOn":"2025-11-19 15:57:34","publishedOnDateReadable":"November 19th, 2025"},"versionCreatedAt":"2025-08-04 04:09:54","video":"","vorDoi":"10.1038/s41598-025-24651-y","vorDoiUrl":"https://doi.org/10.1038/s41598-025-24651-y","workflowStages":[]},"version":"v1","identity":"rs-7120864","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7120864","identity":"rs-7120864","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}