Deep Learning with Transfer Learning for Detecting Abnormalities in X-ray Images

Deep Learning with Transfer Learning for Detecting Abnormalities in X-ray Images | 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 Deep Learning with Transfer Learning for Detecting Abnormalities in X-ray Images Dina Jasim Abd, Sabah Abdulazeez Jebur, Lafta Raheem Ali, Riyam M. Alsammarraie, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6784939/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 Deep learning (DL) applications with medical imaging systems revolutionized the process of detecting abnormalities especially in chest X-ray examination. The existing difficulties in medical imaging analysis stem from insufficient data availability as well as unbalanced classes. The emergence of transfer learning (TL) as an effective strategy allows models to use pre-trained data for better performance and speed in their operations. This paper employed InceptionV3 model with modified layers to detect chest X-ray images which fall into COVID-19, Lung Opacity, Normal, and Viral Pneumonia categories. The proposed method adjusts InceptionV3 by fine-tuning it for better feature extraction and classifier performance improvement. The proposed model demonstrated superior performance by scoring 90.06% accuracy alongside 88.02% recall value and 92.19% precision along with 89.75% F1-score in chest X-ray classification. The research proves that applying transfer learning from InceptionV3 enhances medical imaging abnormality detection leading to a dependable automated diagnostic system. Artificial Intelligence and Machine Learning COVID-19 Transfer Learning InceptionV3 RFMiD dataset 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-6784939","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":464185209,"identity":"a70bda98-2d57-4e1d-8cb1-59656fb481a3","order_by":0,"name":"Dina Jasim Abd","email":"","orcid":"","institution":"Imam Alkadhim University College, Baghdad, Iraq","correspondingAuthor":false,"prefix":"","firstName":"Dina","middleName":"Jasim","lastName":"Abd","suffix":""},{"id":464185210,"identity":"4d61c3c4-2580-40e3-bac0-c8906a61c35f","order_by":1,"name":"Sabah Abdulazeez Jebur","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABGklEQVRIie2QwUrDMBjHUwLZJazXlCF7hYxCUSrbqzQUusssg10KDowU4rFXH2OP0BFoL/Ue8eRdRPFSEKbpZBdJGXoSyY8v+UjgR/75ALBY/iQYQL1HoIR8f3Yh6hrc1xHF+VK8/McKLQ9KD+Obu+3bEkzToWLXr212PvNrlBCQhYwP4Mak0CaNR7cgXnmK5YQ0CQwkqgho5oxDtDQqYEFHOhvbKMbJREgUyIEgjpBawdQYrHjy3zG46pS8ZbsP7OedsutXgFoE+hXZKYJseUko1MEc3q9Q9ZyEmNYrr3kUZ7yKKZEoPo2quS96/jIuLuQDzi7TYR3L+3Y9nblFNVEv6/CkcKVxYochfCPSCxnuj/MLxWKxWP4hn7GdXUetMOAtAAAAAElFTkSuQmCC","orcid":"https://orcid.org/0000-0003-4653-6778","institution":"Imam Alkadhim University College, Baghdad, Iraq","correspondingAuthor":true,"prefix":"","firstName":"Sabah","middleName":"Abdulazeez","lastName":"Jebur","suffix":""},{"id":464185211,"identity":"11f54d18-76e0-4800-ba54-4254934c6191","order_by":2,"name":"Lafta Raheem Ali","email":"","orcid":"","institution":"General Directorate of Education of Salahuddin Salahuddin, Iraq","correspondingAuthor":false,"prefix":"","firstName":"Lafta","middleName":"Raheem","lastName":"Ali","suffix":""},{"id":464185212,"identity":"18510813-4973-4883-9205-a7c1ee88936a","order_by":3,"name":"Riyam M. Alsammarraie","email":"","orcid":"","institution":"Department of Computer Engineering, Madenat Alelem University College, Baghdad, Iraq","correspondingAuthor":false,"prefix":"","firstName":"Riyam","middleName":"M.","lastName":"Alsammarraie","suffix":""},{"id":464185213,"identity":"3c977109-7f3e-48b0-a99b-0c2a8293fd23","order_by":4,"name":"Abir Jaafar Hussain","email":"","orcid":"","institution":"Department of Electrical Engineering, University of Sharjah, Sharjah, United Arab Emirates","correspondingAuthor":false,"prefix":"","firstName":"Abir","middleName":"Jaafar","lastName":"Hussain","suffix":""}],"badges":[],"createdAt":"2025-05-30 12:54:02","currentVersionCode":1,"declarations":{"humanSubjects":true,"vertebrateSubjects":false,"conflictsOfInterestStatement":false,"humanSubjectEthicalGuidelines":true,"humanSubjectConsent":true,"humanSubjectClinicalTrial":true,"humanSubjectCaseReport":true,"vertebrateSubjectEthicalGuidelines":false},"doi":"10.21203/rs.3.rs-6784939/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6784939/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":83763963,"identity":"1e6d38e5-778f-446c-8cb0-693144251824","added_by":"auto","created_at":"2025-06-02 10:23:58","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":559079,"visible":true,"origin":"","legend":"","description":"","filename":"finalversionDeepLearningwithTransferLearningforDetectingAbnormalitiesinXrayImages.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6784939/v1_covered_95e71851-5476-47a7-98f5-9b7102eb97c6.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003eDeep Learning with Transfer Learning for Detecting Abnormalities in X-ray Images\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":"COVID-19, Transfer Learning, InceptionV3, RFMiD dataset","lastPublishedDoi":"10.21203/rs.3.rs-6784939/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6784939/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eDeep learning (DL) applications with medical imaging systems revolutionized the process of detecting abnormalities especially in chest X-ray examination. The existing difficulties in medical imaging analysis stem from insufficient data availability as well as unbalanced classes. The emergence of transfer learning (TL) as an effective strategy allows models to use pre-trained data for better performance and speed in their operations. This paper employed InceptionV3 model with modified layers to detect chest X-ray images which fall into COVID-19, Lung Opacity, Normal, and Viral Pneumonia categories. The proposed method adjusts InceptionV3 by fine-tuning it for better feature extraction and classifier performance improvement. The proposed model demonstrated superior performance by scoring 90.06% accuracy alongside 88.02% recall value and 92.19% precision along with 89.75% F1-score in chest X-ray classification. The research proves that applying transfer learning from InceptionV3 enhances medical imaging abnormality detection leading to a dependable automated diagnostic system.\u003c/p\u003e","manuscriptTitle":"Deep Learning with Transfer Learning for Detecting Abnormalities in X-ray Images","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-06-02 10:23:37","doi":"10.21203/rs.3.rs-6784939/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":"30b7afdf-4942-420e-a336-73a67acb522e","owner":[],"postedDate":"June 2nd, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":49291175,"name":"Artificial Intelligence and Machine Learning"}],"tags":[],"updatedAt":"2025-06-02T10:23:37+00:00","versionOfRecord":[],"versionCreatedAt":"2025-06-02 10:23:37","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-6784939","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6784939","identity":"rs-6784939","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}