A Systematic Review of Cross-Population Shifts in Medical Imaging Analysis with Deep Learning

A Systematic Review of Cross-Population Shifts in Medical Imaging Analysis with Deep Learning | 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 Systematic Review A Systematic Review of Cross-Population Shifts in Medical Imaging Analysis with Deep Learning Aminu Musa, Rajesh Prasad, Peter Onwualu, Monica Hernandez This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8066002/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 has achieved expert-level performance in medical imaging analysis. However, models often fail to generalize across patient populations due to cross-population domain shifts, distributional differences arising from demographic variability, variations in imaging protocols, scanner hardware, and differences in disease prevalence. This challenge limits the real-world deployment and can increase health inequities. This review systematically examines the nature, causes, and impact of cross-population domain shift in deep learning-based medical imaging analysis. We analyzed 50 peer-reviewed studies from 2015 to 2025, evaluating the proposed methodologies for handling population shifts, the datasets employed, and the metrics used to assess performance. Our findings demonstrate that performance degradation ranged from 10–25\% when models were tested on unseen populations, emphasizing the substantial impact of domain shifts on model generalizability. The literature reveals that mitigation strategies broadly fall into two categories: data-centric approaches, such as augmentation and harmonization, and model-centric approaches, including domain adaptation, transfer learning, adversarial learning, multi-task learning, and continual learning. While domain adaptation and transfer learning are the most widely used, their performance gains across populations remain modest, ranging from 5-15\%, and are not supported by external validation. Our synthesis indicates a significant reliance on large, publicly available datasets from limited regions, with under-representation of data from low- and middle-income countries. Evaluation practices are inconsistent, with few studies employing standardized external test sets. This review provides a structured taxonomy of mitigation techniques, a refined analysis of domain shift characteristics, and an in-depth critique of methodological challenges. We highlight the urgent need for more geographically and demographically inclusive datasets, adaptable modelling techniques, and standardized evaluation protocols to enable accurate and equitable AI-driven diagnostics across diverse populations. Finally, we outline future research directions to guide the development of robust, generalizable, and fair models for medical imaging analysis. Computational Biology Computational Neuroscience Biomedical Engineering Chest X-ray Domain adaptation Domain shift Deep learning Medical imaging 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-8066002","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Systematic Review","associatedPublications":[],"authors":[{"id":542030035,"identity":"72d804f5-a9fb-4cee-becd-fe105c5d7208","order_by":0,"name":"Aminu Musa","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA3klEQVRIiWNgGAWjYFAD9gYgYWBBihaeAyAtEqRokUgAk4QV8k87/PjDzza7xP6Zz69u+FEgwcDf3p2A3+zbaWaSvW3JiTNu55Td7AE6TOLM2Q34rbmdYMbA28ac2HA7J+0GD1CLgUQufi3yt9M/f/zbVp84/+aZtJt/iNFicDvHQJq37XDihhvsx24TZYsh0AvSMueOG288k8N2W8ZAgoegX+Rup2/++KasWnbe8ePPbr75YyPH395LwPsgwMjG4NjAwGMAYvMQVg4GfxjsgSnmAZGqR8EoGAWjYKQBANNHTXhmF3lqAAAAAElFTkSuQmCC","orcid":"","institution":"African University of Science and Technology, Abuja","correspondingAuthor":true,"prefix":"","firstName":"Aminu","middleName":"","lastName":"Musa","suffix":""},{"id":542030036,"identity":"0326b2ad-425a-4118-b3a8-970557a29d88","order_by":1,"name":"Rajesh Prasad","email":"","orcid":"","institution":"African University of Science and Technology, Abuja","correspondingAuthor":false,"prefix":"","firstName":"Rajesh","middleName":"","lastName":"Prasad","suffix":""},{"id":542030037,"identity":"ed21a923-e231-4499-86fe-91e0d5dfea63","order_by":2,"name":"Peter Onwualu","email":"","orcid":"","institution":"African University of Science and Technology, Abuja","correspondingAuthor":false,"prefix":"","firstName":"Peter","middleName":"","lastName":"Onwualu","suffix":""},{"id":542030038,"identity":"b810e86f-1b01-4ed2-9c3e-cba60740f535","order_by":3,"name":"Monica Hernandez","email":"","orcid":"","institution":"University of Zaragoza","correspondingAuthor":false,"prefix":"","firstName":"Monica","middleName":"","lastName":"Hernandez","suffix":""}],"badges":[],"createdAt":"2025-11-08 20:27:10","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-8066002/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8066002/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":95658044,"identity":"8f9d2612-7c53-4ff7-80e1-28bea953ad9a","added_by":"auto","created_at":"2025-11-11 16:22:45","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1748771,"visible":true,"origin":"","legend":"","description":"","filename":"CPDSREVIEW1.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8066002/v1_covered_4f83a6bf-29d8-43d4-8f36-4523ff652961.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003eA Systematic Review of Cross-Population Shifts in Medical Imaging Analysis with Deep Learning\u003c/p\u003e","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"African University of Science and Technology, Abuja","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":"Chest X-ray, Domain adaptation, Domain shift, Deep learning, Medical imaging","lastPublishedDoi":"10.21203/rs.3.rs-8066002/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8066002/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eDeep learning has achieved expert-level performance in medical imaging analysis. However, models often fail to generalize across patient populations due to cross-population domain shifts, distributional differences arising from demographic variability, variations in imaging protocols, scanner hardware, and differences in disease prevalence. This challenge limits the real-world deployment and can increase health inequities. This review systematically examines the nature, causes, and impact of cross-population domain shift in deep learning-based medical imaging analysis. We analyzed 50 peer-reviewed studies from 2015 to 2025, evaluating the proposed methodologies for handling population shifts, the datasets employed, and the metrics used to assess performance. Our findings demonstrate that performance degradation ranged from 10–25\\% when models were tested on unseen populations, emphasizing the substantial impact of domain shifts on model generalizability. The literature reveals that mitigation strategies broadly fall into two categories: data-centric approaches, such as augmentation and harmonization, and model-centric approaches, including domain adaptation, transfer learning, adversarial learning, multi-task learning, and continual learning. While domain adaptation and transfer learning are the most widely used, their performance gains across populations remain modest, ranging from 5-15\\%, and are not supported by external validation. \u0026nbsp;Our synthesis indicates a significant reliance on large, publicly available datasets from limited regions, with under-representation of data from low- and middle-income countries. Evaluation practices are inconsistent, with few studies employing standardized external test sets. This review provides a structured taxonomy of mitigation techniques, a refined analysis of domain shift characteristics, and an in-depth critique of methodological challenges. We highlight the urgent need for more geographically and demographically inclusive datasets, adaptable modelling techniques, and standardized evaluation protocols to enable accurate and equitable AI-driven diagnostics across diverse populations. Finally, we outline future research directions to guide the development of robust, generalizable, and fair models for medical imaging analysis.\u003c/p\u003e","manuscriptTitle":"A Systematic Review of Cross-Population Shifts in Medical Imaging Analysis with Deep Learning","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-11-11 12:09:13","doi":"10.21203/rs.3.rs-8066002/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":"3df91835-b345-4ced-a91b-e335c6afeb69","owner":[],"postedDate":"November 11th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":57666173,"name":"Computational Biology"},{"id":57666174,"name":"Computational Neuroscience"},{"id":57666175,"name":"Biomedical Engineering"}],"tags":[],"updatedAt":"2025-11-11T12:09:13+00:00","versionOfRecord":[],"versionCreatedAt":"2025-11-11 12:09:13","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8066002","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8066002","identity":"rs-8066002","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}