UltraGANet: A Class-Conditional GAN Framework for Breast Tumor Classification in Ultrasound Imaging

UltraGANet: A Class-Conditional GAN Framework for Breast Tumor Classification in Ultrasound Imaging | 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 UltraGANet: A Class-Conditional GAN Framework for Breast Tumor Classification in Ultrasound Imaging Ali Hamza, Martin Mezl This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7935406/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 Purpose This study addresses the critical challenge of limited annotated data in ultrasound-based breast cancer diagnosis by proposing a novel classification framework. The research aims to evaluate whether (cGANs) can effectively augment training datasets and enhance classification performance when integrated with a lightweight (CNN) model, UltraGANet. Methods We developed a cGAN capable of generating class-specific grayscale breast ultrasound images and corresponding segmentation masks for benign, malignant, and normal categories. These synthetic samples were combined with real ultrasound images from the BUSI dataset to create an augmented training set. UltraGANet, a task-specific CNN architecture, was trained using this dataset and evaluated through 5-fold stratified cross-validation and testing on an independent set of 146 real images. Performance metrics included accuracy, precision, recall, and F1-score. Results UltraGANet achieved an average classification accuracy of 91.4% ± 1.2% during cross-validation and 91.03% on the test set. Malignant tumor recall reached 92% , indicating high sensitivity. The model maintained balanced precision and F1-scores across all classes. Qualitative analysis confirmed that synthetic images preserved anatomical plausibility and tumor characteristics. Conclusion The integration of cGAN-based augmentation with UltraGANet substantially improved classification performance, particularly in malignant tumor detection. The proposed framework offers a scalable, computationally efficient solution for breast ultrasound diagnostics, especially valuable in data-scarce or resource-limited clinical environments. Biomedical Engineering CGAN Malignant Benign UltraGANet Segmentation Full Text Additional Declarations The authors declare no competing interests. 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-7935406","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":534433888,"identity":"a2c0b555-cba3-4860-b912-84acf9022471","order_by":0,"name":"Ali Hamza","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAvElEQVRIiWNgGAWjYDACdsYGZgijgVgtzDAtPAcYGA4QpwWMgEAigUgt/M3MDcwFNdvs+We+MZP+wGBnT1CLxGGgw2Ycu80scTvHTOIAQzIzYWtAWnjYbrMx3E5LA2o5wEZQhzxYy7/bPPI3j4G18BDUYgDSwtt2W8LgBvMxkBYJgloMgVoO8/bdNjA8k3zY4oxBsgFBLXLH2x8+5vl2217u+MHGGxUVRIQYCBxAcidRGkbBKBgFo2AUEAIAM+Q2qak0k/gAAAAASUVORK5CYII=","orcid":"","institution":"brno university of technology","correspondingAuthor":true,"prefix":"","firstName":"Ali","middleName":"","lastName":"Hamza","suffix":""},{"id":534433889,"identity":"97ba23be-3b6a-42cd-b278-6dcdee2940b1","order_by":1,"name":"Martin Mezl","email":"","orcid":"","institution":"brno university of technology","correspondingAuthor":false,"prefix":"","firstName":"Martin","middleName":"","lastName":"Mezl","suffix":""}],"badges":[],"createdAt":"2025-10-23 22:24:19","currentVersionCode":1,"declarations":{"humanSubjects":false,"vertebrateSubjects":false,"conflictsOfInterestStatement":false,"humanSubjectEthicalGuidelines":false,"humanSubjectConsent":false,"humanSubjectClinicalTrial":false,"humanSubjectCaseReport":false,"vertebrateSubjectEthicalGuidelines":false},"doi":"10.21203/rs.3.rs-7935406/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7935406/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":94451078,"identity":"9b78e798-6398-4026-bbc1-1e579401268b","added_by":"auto","created_at":"2025-10-27 14:39:48","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":785474,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7935406/v1_covered_d3d82e91-5654-4223-8e19-5b84924eb218.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003e\u003cstrong\u003eUltraGANet: A Class-Conditional GAN Framework for Breast Tumor Classification in Ultrasound Imaging\u003c/strong\u003e\u003c/p\u003e","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":"CGAN, Malignant, Benign, UltraGANet, Segmentation","lastPublishedDoi":"10.21203/rs.3.rs-7935406/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7935406/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003e\u003cstrong\u003ePurpose\u003c/strong\u003e\u003cbr\u003e\nThis study addresses the critical challenge of limited annotated data in ultrasound-based breast cancer diagnosis by proposing a novel classification framework. The research aims to evaluate whether (cGANs) can effectively augment training datasets and enhance classification performance when integrated with a lightweight (CNN) model, UltraGANet.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eMethods\u003c/strong\u003e\u003cbr\u003e\nWe developed a cGAN capable of generating class-specific grayscale breast ultrasound images and corresponding segmentation masks for benign, malignant, and normal categories. These synthetic samples were combined with real ultrasound images from the BUSI dataset to create an augmented training set. UltraGANet, a task-specific CNN architecture, was trained using this dataset and evaluated through 5-fold stratified cross-validation and testing on an independent set of 146 real images. Performance metrics included accuracy, precision, recall, and F1-score.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eResults\u003c/strong\u003e\u003cbr\u003e\nUltraGANet achieved an average classification accuracy of \u003cstrong\u003e91.4% ± 1.2%\u003c/strong\u003eduring cross-validation and \u003cstrong\u003e91.03%\u003c/strong\u003e on the test set. Malignant tumor recall reached \u003cstrong\u003e92%\u003c/strong\u003e, indicating high sensitivity. The model maintained balanced precision and F1-scores across all classes. Qualitative analysis confirmed that synthetic images preserved anatomical plausibility and tumor characteristics.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eConclusion\u003c/strong\u003e\u003cbr\u003e\nThe integration of cGAN-based augmentation with UltraGANet substantially improved classification performance, particularly in malignant tumor detection. The proposed framework offers a scalable, computationally efficient solution for breast ultrasound diagnostics, especially valuable in data-scarce or resource-limited clinical environments.\u003c/p\u003e","manuscriptTitle":"UltraGANet: A Class-Conditional GAN Framework for Breast Tumor Classification in Ultrasound Imaging","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-10-27 11:32:18","doi":"10.21203/rs.3.rs-7935406/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":"e66c87be-87d8-4fbb-b89e-2c546f603836","owner":[],"postedDate":"October 27th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":56825850,"name":"Biomedical Engineering"}],"tags":[],"updatedAt":"2025-10-27T11:32:18+00:00","versionOfRecord":[],"versionCreatedAt":"2025-10-27 11:32:18","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7935406","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7935406","identity":"rs-7935406","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}