Fairness in Federated Medical Imaging: A Systematic Review Through the Dual Fairness Lens

Fairness in Federated Medical Imaging: A Systematic Review Through the Dual Fairness Lens | 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 Fairness in Federated Medical Imaging: A Systematic Review Through the Dual Fairness Lens Pengyang Yu, Zhongping Dong, Sahraoui Dhelim, Chun-Mei Feng, M. Tahar Kechadi This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9556184/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 12 You are reading this latest preprint version Abstract Federated learning (FL) enables multi-institutional collaboration in medical imaging while preserving patient privacy, yet its fairness landscape remains fragmented: existing methods predominantly address either collaboration fairness (equitable performance across institutions) or group fairness (equitable outcomes across demographic subgroups), but rarely both. In this systematic review, we adopt dual fairness - the joint satisfaction of both dimensions - as the analytical lens for organizing and critically evaluating this landscape. Following the PRISMA 2020 guidelines, we analyze 132 publications and classify fairness-aware FL methods through a three-dimensional taxonomy: client-side, server-side, and communication-based approaches. Among the 29 fairness-aware methods catalogued, only three partially address both dimensions, and none provides provable joint guarantees under clinically realistic conditions. Our critical analysis identifies three fundamental challenges: the Local-Global Pareto Frontier Conflict, in which collaboration and group fairness gradients can exceed 150 degrees under severe demographic asymmetry; the Privacy-Fairness Compounding Effect, through which differential privacy mechanisms disproportionately suppress minority gradient signals; and the risk of pseudo-fairness, whereby equipment-demographic confounding masks genuine algorithmic discrimination. We further outline a seven-direction research roadmap. To the best of our knowledge, this constitutes the first systematic review to formally analyze the gradient-level conflict between collaboration fairness and group fairness in federated medical imaging, while also providing a structured causal analysis of equipment-demographic confounding, offering both a critical synthesis and actionable directions toward equitable AI-assisted healthcare. Federated learning Fairness Medical imaging Dual fairness Differential privacy Privacy-preserving machine learning Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Reviews received at journal 16 May, 2026 Reviews received at journal 12 May, 2026 Reviewers agreed at journal 07 May, 2026 Reviewers agreed at journal 06 May, 2026 Reviewers agreed at journal 05 May, 2026 Reviewers agreed at journal 04 May, 2026 Reviewers agreed at journal 04 May, 2026 Reviewers agreed at journal 04 May, 2026 Reviewers invited by journal 04 May, 2026 Editor assigned by journal 01 May, 2026 Submission checks completed at journal 28 Apr, 2026 First submitted to journal 28 Apr, 2026 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-9556184","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":635908178,"identity":"1fe6b1e9-f161-49c8-b911-44ce53efdf5a","order_by":0,"name":"Pengyang Yu","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABAElEQVRIiWNgGAWjYJADxgcMDMxwHg8xWpgNEFoSiNPCJoGsBScwZ+89/Jqn5o5dg0SOWTVPjbU8v3TvwQc/fzDI8OPQYtlzLs2a59izZJCW2zzH0g1nzjmXbNgDdJhkA3YtBjdyzIx52A4nM4C08DYcTgCJSIP8YnAAh5b7b4Ba/kG0FEO1mP8GabHHpeUGj/Fj3rbDdiAtzDBbmMG24PRLjhnj3L7DCWw8z4ol54D8MiPHWLInTYJHAoct5uxnjD+8+XbYnp89eeOHN6AQk8gx/PDDxsaeH5f3gdEhBYy1xDaBBBQJCRzOAmth/viDgcGegR+HO0bBKBgFo2AUAAAV3lOAIw6L7gAAAABJRU5ErkJggg==","orcid":"","institution":"University College Dublin","correspondingAuthor":true,"prefix":"","firstName":"Pengyang","middleName":"","lastName":"Yu","suffix":""},{"id":635908179,"identity":"26e11861-9abd-48ab-9929-cd7c866a6d55","order_by":1,"name":"Zhongping Dong","email":"","orcid":"","institution":"University College Dublin","correspondingAuthor":false,"prefix":"","firstName":"Zhongping","middleName":"","lastName":"Dong","suffix":""},{"id":635908180,"identity":"cac5a820-580b-444a-938f-b2314595eb45","order_by":2,"name":"Sahraoui Dhelim","email":"","orcid":"","institution":"Dublin City University","correspondingAuthor":false,"prefix":"","firstName":"Sahraoui","middleName":"","lastName":"Dhelim","suffix":""},{"id":635908181,"identity":"a2a9fda8-be73-47f1-a8a7-29c8cbb04985","order_by":3,"name":"Chun-Mei Feng","email":"","orcid":"","institution":"University College Dublin","correspondingAuthor":false,"prefix":"","firstName":"Chun-Mei","middleName":"","lastName":"Feng","suffix":""},{"id":635908183,"identity":"6ab107c7-a929-4e3b-b0f7-1c5c00095f68","order_by":4,"name":"M. Tahar Kechadi","email":"","orcid":"","institution":"University College Dublin","correspondingAuthor":false,"prefix":"","firstName":"M.","middleName":"Tahar","lastName":"Kechadi","suffix":""}],"badges":[],"createdAt":"2026-04-28 15:38:49","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-9556184/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9556184/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":109090130,"identity":"2af45fea-1b7a-4293-b4d4-c33b8ca43ddb","added_by":"auto","created_at":"2026-05-12 13:29:25","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1082886,"visible":true,"origin":"","legend":"","description":"","filename":"AIRsubmission.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9556184/v1_covered_fb861b23-0bcd-43eb-9022-a49f700f9d40.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Fairness in Federated Medical Imaging: A Systematic Review Through the Dual Fairness Lens","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"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":"artificial-intelligence-review","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"aire","sideBox":"Learn more about [Artificial Intelligence Review](http://link.springer.com/journal/10462)","snPcode":"10462","submissionUrl":"https://submission.nature.com/new-submission/10462/3","title":"Artificial Intelligence Review","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Federated learning, Fairness, Medical imaging, Dual fairness, Differential privacy, Privacy-preserving machine learning","lastPublishedDoi":"10.21203/rs.3.rs-9556184/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9556184/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Federated learning (FL) enables multi-institutional collaboration in medical imaging while preserving patient privacy, yet its fairness landscape remains fragmented: existing methods predominantly address either collaboration fairness (equitable performance across institutions) or group fairness (equitable outcomes across demographic subgroups), but rarely both. In this systematic review, we adopt dual fairness - the joint satisfaction of both dimensions - as the analytical lens for organizing and critically evaluating this landscape. Following the PRISMA 2020 guidelines, we analyze 132 publications and classify fairness-aware FL methods through a three-dimensional taxonomy: client-side, server-side, and communication-based approaches. Among the 29 fairness-aware methods catalogued, only three partially address both dimensions, and none provides provable joint guarantees under clinically realistic conditions. Our critical analysis identifies three fundamental challenges: the Local-Global Pareto Frontier Conflict, in which collaboration and group fairness gradients can exceed 150 degrees under severe demographic asymmetry; the Privacy-Fairness Compounding Effect, through which differential privacy mechanisms disproportionately suppress minority gradient signals; and the risk of pseudo-fairness, whereby equipment-demographic confounding masks genuine algorithmic discrimination. We further outline a seven-direction research roadmap. To the best of our knowledge, this constitutes the first systematic review to formally analyze the gradient-level conflict between collaboration fairness and group fairness in federated medical imaging, while also providing a structured causal analysis of equipment-demographic confounding, offering both a critical synthesis and actionable directions toward equitable AI-assisted healthcare.","manuscriptTitle":"Fairness in Federated Medical Imaging: A Systematic Review Through the Dual Fairness Lens","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-05-12 12:47:38","doi":"10.21203/rs.3.rs-9556184/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"editorInvitedReview","content":"","date":"2026-05-16T20:02:34+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-05-12T06:06:58+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"133041940704189726910823295573687596289","date":"2026-05-07T05:27:57+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"307074569291769222330635003487052700636","date":"2026-05-06T19:27:34+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"77001598584303514029910033183221317076","date":"2026-05-05T04:26:18+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"285167824982354948838880571541213853034","date":"2026-05-04T13:33:57+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"323849776992055124645653471299649570721","date":"2026-05-04T13:15:10+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"102368117167161052385784397716243380121","date":"2026-05-04T11:58:04+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-05-04T10:58:09+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-05-01T14:05:16+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-04-29T01:50:27+00:00","index":"","fulltext":""},{"type":"submitted","content":"Artificial Intelligence Review","date":"2026-04-28T15:23:49+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"artificial-intelligence-review","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"aire","sideBox":"Learn more about [Artificial Intelligence Review](http://link.springer.com/journal/10462)","snPcode":"10462","submissionUrl":"https://submission.nature.com/new-submission/10462/3","title":"Artificial Intelligence Review","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"4e8d7beb-fc31-42a9-b4b9-f04fe3d6c060","owner":[],"postedDate":"May 12th, 2026","published":true,"recentEditorialEvents":[{"type":"editorInvitedReview","content":"","date":"2026-05-16T20:02:34+00:00","index":23,"fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-05-12T06:06:58+00:00","index":22,"fulltext":""},{"type":"reviewerAgreed","content":"133041940704189726910823295573687596289","date":"2026-05-07T05:27:57+00:00","index":21,"fulltext":""},{"type":"reviewerAgreed","content":"307074569291769222330635003487052700636","date":"2026-05-06T19:27:34+00:00","index":20,"fulltext":""},{"type":"reviewerAgreed","content":"77001598584303514029910033183221317076","date":"2026-05-05T04:26:18+00:00","index":17,"fulltext":""},{"type":"reviewerAgreed","content":"285167824982354948838880571541213853034","date":"2026-05-04T13:33:57+00:00","index":16,"fulltext":""},{"type":"reviewerAgreed","content":"323849776992055124645653471299649570721","date":"2026-05-04T13:15:10+00:00","index":15,"fulltext":""},{"type":"reviewerAgreed","content":"102368117167161052385784397716243380121","date":"2026-05-04T11:58:04+00:00","index":14,"fulltext":""},{"type":"reviewersInvited","content":"10","date":"2026-05-04T10:58:09+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-05-01T14:05:16+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-04-29T01:50:27+00:00","index":"","fulltext":""}],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2026-05-12T12:47:39+00:00","versionOfRecord":[],"versionCreatedAt":"2026-05-12 12:47:38","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9556184","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9556184","identity":"rs-9556184","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}