Pixels to Prognosis: ResNet50 Hyper-parameter Analysis for Predicting Benign vs. Malignant Breast Cancer from Biopsy Scans

Pixels to Prognosis: ResNet50 Hyper-parameter Analysis for Predicting Benign vs. Malignant Breast Cancer from Biopsy Scans | 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 Pixels to Prognosis: ResNet50 Hyper-parameter Analysis for Predicting Benign vs. Malignant Breast Cancer from Biopsy Scans Naman Dhariwal This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7880251/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 Breast cancer diagnosis is a critical task that can benefit from advancements in deep learning and computer vision. This study focuses on the analysis and application of the ResNet50 architecture to classify benign and malignant breast cancer types using RCL biopsy images. Three versions of the ResNet50 model were trained and evaluated using diverse hyperparameter configurations, optimization strategies, and learning rate schedulers to determine the most accurate and robust classifier. The performance of each model was assessed using metrics such as precision, recall, F1-score, and accuracy, with additional validation through k-fold cross-validation. ResNet50 (Classifier 3), utilizing the AdamW optimizer and ReduceLROnPlateau scheduler, emerged as the top performer with an average accuracy of 90% and balanced performance across all metrics. These findings underscore the potential of ResNet50, when optimized effectively, for reliable breast cancer classification. The research highlights the importance of model tuning and evaluation in developing robust AI-driven diagnostic tools. Breast Cancer Classification ResNet50 Deep Learning Medical Imaging Hyperparameter Optimization Computer Vision Biopsy Image Analysis Diagnostic AI 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-7880251","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":580794839,"identity":"19fc2d45-09a1-49fb-a9a1-8cc8260ccea0","order_by":0,"name":"Naman Dhariwal","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAArUlEQVRIiWNgGAWjYNACNhsGBmYGNgYQSayWNNK1HAaTxGkxZz+d+Lmg7Hzi2nbmZw8YKqwTGwhpsezJ3Sw949ztxG2H2cwNGM6kE9ZicCB3gzRvG0gLD5sEY9thIrScf7v5N2/bOaiWf8RouZG7DWjLAaiWBqK0vN1mzXMu2RjoFzOJhGPpxkQ4LHfzbZ4yO9lt5w8/k/hQYy1LUAsqSCBN+SgYBaNgFIwCXAAAtTY+htoRLcYAAAAASUVORK5CYII=","orcid":"","institution":"University of Michigan","correspondingAuthor":true,"prefix":"","firstName":"Naman","middleName":"","lastName":"Dhariwal","suffix":""}],"badges":[],"createdAt":"2025-10-16 18:08:22","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7880251/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7880251/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":101190675,"identity":"ae5e901b-2176-415f-bc03-b84958e2468e","added_by":"auto","created_at":"2026-01-27 07:02:38","extension":"json","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":3221,"visible":true,"origin":"","legend":"","description":"","filename":"4f778780d12248c3843574d078dc05ff.json","url":"https://assets-eu.researchsquare.com/files/rs-7880251/v1/2a4bbb4038715f95627baf52.json"},{"id":101190676,"identity":"eca976c3-89f6-4e4c-94f7-b6fbcae39592","added_by":"auto","created_at":"2026-01-27 07:02:42","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":525730,"visible":true,"origin":"","legend":"","description":"","filename":"PixelstoPrognosisJMS.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7880251/v1_covered_06a9ca27-8e85-4a89-8854-86431018906e.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Pixels to Prognosis: ResNet50 Hyper-parameter Analysis for Predicting Benign vs. Malignant Breast Cancer from Biopsy Scans","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":"Breast Cancer Classification, ResNet50, Deep Learning, Medical Imaging, Hyperparameter Optimization, Computer Vision, Biopsy Image Analysis, Diagnostic AI","lastPublishedDoi":"10.21203/rs.3.rs-7880251/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7880251/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Breast cancer diagnosis is a critical task that can benefit from advancements in deep learning and computer vision. This study focuses on the analysis and application of the ResNet50 architecture to classify benign and malignant breast cancer types using RCL biopsy images. Three versions of the ResNet50 model were trained and evaluated using diverse hyperparameter configurations, optimization strategies, and learning rate schedulers to determine the most accurate and robust classifier. The performance of each model was assessed using metrics such as precision, recall, F1-score, and accuracy, with additional validation through k-fold cross-validation. ResNet50 (Classifier 3), utilizing the AdamW optimizer and ReduceLROnPlateau scheduler, emerged as the top performer with an average accuracy of 90% and balanced performance across all metrics. These findings underscore the potential of ResNet50, when optimized effectively, for reliable breast cancer classification. The research highlights the importance of model tuning and evaluation in developing robust AI-driven diagnostic tools.","manuscriptTitle":"Pixels to Prognosis: ResNet50 Hyper-parameter Analysis for Predicting Benign vs. Malignant Breast Cancer from Biopsy Scans","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-01-27 07:02:33","doi":"10.21203/rs.3.rs-7880251/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":"3e031d18-ecc4-4f18-a8b3-69570ce74381","owner":[],"postedDate":"January 27th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2026-01-27T07:02:33+00:00","versionOfRecord":[],"versionCreatedAt":"2026-01-27 07:02:33","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7880251","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7880251","identity":"rs-7880251","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}