Smart Diagnosis: AI and ML Powered Breast Cancer Classification

Smart Diagnosis: AI and ML Powered Breast Cancer Classification | 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 Smart Diagnosis: AI and ML Powered Breast Cancer Classification Sagar Verma, Vaibhav Sabale This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8662821/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 Background Breast cancer remains one of the leading causes of cancer-related morbidity and mortality among women worldwide. Early and accessible diagnostic tools are essential, particularly in low-resource settings where expert interpretation of ultrasound imaging may be limited. This study presents an AI- and machine learning–assisted web-based platform designed to support preliminary breast cancer lesion classification. Methods The study aimed to design and implement a Flask-based web application that accepts breast ultrasound images and patient metadata for pre-classification into benign, malignant, or normal categories. Images were preprocessed using standardized resizing and normalization, while probabilistic classification was simulated using a NumPy-based framework. Interactive visualizations, confidence scoring, and PDF report generation were incorporated to enhance clinical usability. Results The platform demonstrated rapid and consistent performance, with image processing and prediction latency ranging from 0.018 to 0.06 seconds. Simulated batch analysis showed clear separation between cancer-positive and healthy cases, with higher median confidence scores for malignant samples. The system successfully generated intuitive dashboards, region-of-interest overlays, and downloadable diagnostic reports. Conclusions This prototype highlights the feasibility of integrating AI-assisted image analysis with user-friendly web interfaces for early breast cancer screening. Although current predictions are simulated, the modular architecture allows seamless integration of real deep learning models in the future. The platform has potential implications for improving early detection, patient awareness, and equitable access to diagnostic support. Breast Cancer Classification Medical Image Processing Flask-Based Web Application AI-Assisted Diagnosis Probabilistic Inference 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-8662821","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":580047908,"identity":"99f3a355-986b-4b0c-bb45-04b8c817c9dd","order_by":0,"name":"Sagar Verma","email":"","orcid":"","institution":"Parul Institute of Applied Sciences, Parul University, Waghodia, Vadodara","correspondingAuthor":false,"prefix":"","firstName":"Sagar","middleName":"","lastName":"Verma","suffix":""},{"id":580047909,"identity":"a43a1088-42de-46e5-b7a4-939212564721","order_by":1,"name":"Vaibhav Sabale","email":"data:image/png;base64,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","orcid":"","institution":"Parul Institute of Applied Sciences, Parul University, Waghodia, Vadodara","correspondingAuthor":true,"prefix":"","firstName":"Vaibhav","middleName":"","lastName":"Sabale","suffix":""}],"badges":[],"createdAt":"2026-01-21 18:38:31","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8662821/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8662821/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":106979474,"identity":"6fd780f4-9009-4c7a-84ff-52fb264bbe47","added_by":"auto","created_at":"2026-04-15 11:28:08","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":751314,"visible":true,"origin":"","legend":"","description":"","filename":"SagarResearch22012026.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8662821/v1_covered_a1be9ee8-fad9-4104-8c98-316a91331806.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Smart Diagnosis: AI and ML Powered Breast Cancer Classification","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, Medical Image Processing, Flask-Based Web Application, AI-Assisted Diagnosis, Probabilistic Inference","lastPublishedDoi":"10.21203/rs.3.rs-8662821/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8662821/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003ch2\u003eBackground\u003c/h2\u003e \u003cp\u003eBreast cancer remains one of the leading causes of cancer-related morbidity and mortality among women worldwide. Early and accessible diagnostic tools are essential, particularly in low-resource settings where expert interpretation of ultrasound imaging may be limited. This study presents an AI- and machine learning\u0026ndash;assisted web-based platform designed to support preliminary breast cancer lesion classification.\u003c/p\u003e\u003ch2\u003eMethods\u003c/h2\u003e \u003cp\u003eThe study aimed to design and implement a Flask-based web application that accepts breast ultrasound images and patient metadata for pre-classification into benign, malignant, or normal categories. Images were preprocessed using standardized resizing and normalization, while probabilistic classification was simulated using a NumPy-based framework. Interactive visualizations, confidence scoring, and PDF report generation were incorporated to enhance clinical usability.\u003c/p\u003e\u003ch2\u003eResults\u003c/h2\u003e \u003cp\u003eThe platform demonstrated rapid and consistent performance, with image processing and prediction latency ranging from 0.018 to 0.06 seconds. Simulated batch analysis showed clear separation between cancer-positive and healthy cases, with higher median confidence scores for malignant samples. The system successfully generated intuitive dashboards, region-of-interest overlays, and downloadable diagnostic reports.\u003c/p\u003e\u003ch2\u003eConclusions\u003c/h2\u003e \u003cp\u003eThis prototype highlights the feasibility of integrating AI-assisted image analysis with user-friendly web interfaces for early breast cancer screening. Although current predictions are simulated, the modular architecture allows seamless integration of real deep learning models in the future. The platform has potential implications for improving early detection, patient awareness, and equitable access to diagnostic support.\u003c/p\u003e","manuscriptTitle":"Smart Diagnosis: AI and ML Powered Breast Cancer Classification","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-01-28 06:28:34","doi":"10.21203/rs.3.rs-8662821/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":"f326b7b9-41ec-49c7-9db9-fc27084a9a46","owner":[],"postedDate":"January 28th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2026-04-15T11:26:06+00:00","versionOfRecord":[],"versionCreatedAt":"2026-01-28 06:28:34","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8662821","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8662821","identity":"rs-8662821","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}