Knowing When Not to Decide: Multi-Pathology Chest X-Ray Classification with Rejection Mechanisms

Knowing When Not to Decide: Multi-Pathology Chest X-Ray Classification with Rejection Mechanisms | 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 Article Knowing When Not to Decide: Multi-Pathology Chest X-Ray Classification with Rejection Mechanisms Aperstein Yehudit, Tzahar Amit, Gottlib Alon, Verber Tal, Shagan Damti Ravit, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6644332/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 10 You are reading this latest preprint version Abstract Overconfidence in deep learning models poses a significant risk in high-stakes medical imaging tasks, particularly in multi-label classification of chest X-rays, where multiple co-occurring pathologies must be detected simultaneously. This study introduces an uncertainty-aware framework for chest X-ray diagnosis based on a DenseNet-121 backbone, enhanced with two selective prediction mechanisms: entropy-based rejection and confidence interval-based rejection. Both methods enable the model to abstain from uncertain predictions, improving reliability by deferring ambiguous cases to clinical experts. A quantile-based calibration procedure is employed to tune rejection thresholds using either global or class-specific strategies. Experiments conducted on three large public datasets (PadChest, NIH ChestX-ray14, and MIMIC-CXR) demonstrate that selective rejection improves the trade-off between diagnostic accuracy and coverage, with entropy-based rejection yielding the highest average AuC across all pathologies. These results support the integration of selective prediction into AI-assisted diagnostic workflows, providing a practical step toward safer, uncertainty-aware deployment of deep learning in clinical settings. Health sciences/Diseases Health sciences/Diseases/Cardiovascular diseases Health sciences/Diseases/Respiratory tract diseases Chest X-ray classification Rejection mechanism Multi-label diagnosis Selective prediction Uncertainty estimation Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Editorial decision: Revision requested 05 Aug, 2025 Reviews received at journal 12 Jul, 2025 Reviews received at journal 20 Jun, 2025 Reviewers agreed at journal 04 Jun, 2025 Reviewers agreed at journal 04 Jun, 2025 Reviewers invited by journal 04 Jun, 2025 Editor assigned by journal 04 Jun, 2025 Editor invited by journal 26 May, 2025 Submission checks completed at journal 26 May, 2025 First submitted to journal 12 May, 2025 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-6644332","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":466387158,"identity":"f31ff09c-bb06-4123-aad9-784a63d45b50","order_by":0,"name":"Aperstein Yehudit","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA/ElEQVRIiWNgGAWjYBADHgYG5gMMFQwJEG5CASENCSAtbAkMZ+BaDAhrAVlkgNDCgEcL/+zmYx9//rCRMZfI+fjhQEWaPAP74QcMD/BokbhzLHk2T0Iaj+WM3M0SB87kGDbwpBngd9iNHGNmhoTDPAY3cjdIf2yrYGxgyMHvF/kb+Z8ZfyT8B2rJefzj4L8K+wb+N/i1AFUyM/AkHABpYZM42JCT2CBBwBbDO8eMmXnSknkMzjwzszhwLC25TeKZwQF8WuRuNz9m/GFjZ29wPPnxjQM1ybb9/MkPH/6owON9CRhDIAFCswHxATwakLTw41c3CkbBKBgFIxgAADNGU3RuyfR8AAAAAElFTkSuQmCC","orcid":"","institution":"Afeka College of Engineering","correspondingAuthor":true,"prefix":"","firstName":"Aperstein","middleName":"","lastName":"Yehudit","suffix":""},{"id":466387159,"identity":"f06bcd2e-1113-4677-b54c-859862762540","order_by":1,"name":"Tzahar Amit","email":"","orcid":"","institution":"Afeka College of Engineering","correspondingAuthor":false,"prefix":"","firstName":"Tzahar","middleName":"","lastName":"Amit","suffix":""},{"id":466387166,"identity":"33139b5d-476f-4c66-a3ab-f4bbdf7874cf","order_by":2,"name":"Gottlib Alon","email":"","orcid":"","institution":"Afeka College of Engineering","correspondingAuthor":false,"prefix":"","firstName":"Gottlib","middleName":"","lastName":"Alon","suffix":""},{"id":466387168,"identity":"05cec7af-46ad-489f-9a6c-6ae117c9d8f0","order_by":3,"name":"Verber Tal","email":"","orcid":"","institution":"Afeka College of Engineering","correspondingAuthor":false,"prefix":"","firstName":"Verber","middleName":"","lastName":"Tal","suffix":""},{"id":466387169,"identity":"ce8f073d-732d-4da0-9c19-c6cf31c705b9","order_by":4,"name":"Shagan Damti Ravit","email":"","orcid":"","institution":"Afeka College of Engineering","correspondingAuthor":false,"prefix":"","firstName":"Shagan","middleName":"Damti","lastName":"Ravit","suffix":""},{"id":466387170,"identity":"15e92fa3-01e5-4dfa-a20b-688de5f31ded","order_by":5,"name":"Apartsin Alexander","email":"","orcid":"","institution":"Holon Institute of Technology","correspondingAuthor":false,"prefix":"","firstName":"Apartsin","middleName":"","lastName":"Alexander","suffix":""}],"badges":[],"createdAt":"2025-05-12 08:08:39","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6644332/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6644332/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":84076183,"identity":"81e234dc-03de-4495-a0bd-64f35984ebcc","added_by":"auto","created_at":"2025-06-06 13:14:02","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":440004,"visible":true,"origin":"","legend":"","description":"","filename":"CHESTXRAYCLASSIFICATIONWITHREJECTIONMECHANISMSfixed.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6644332/v1_covered_9e9120b5-c582-46ac-a3bf-cf2cd1340da5.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"\u003cp\u003eKnowing When Not to Decide: Multi-Pathology Chest X-Ray Classification with Rejection Mechanisms\u003c/p\u003e","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":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"Chest X-ray classification, Rejection mechanism, Multi-label diagnosis, Selective prediction, Uncertainty estimation","lastPublishedDoi":"10.21203/rs.3.rs-6644332/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6644332/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eOverconfidence in deep learning models poses a significant risk in high-stakes medical imaging tasks, particularly in multi-label classification of chest X-rays, where multiple co-occurring pathologies must be detected simultaneously. This study introduces an uncertainty-aware framework for chest X-ray diagnosis based on a DenseNet-121 backbone, enhanced with two selective prediction mechanisms: entropy-based rejection and confidence interval-based rejection. Both methods enable the model to abstain from uncertain predictions, improving reliability by deferring ambiguous cases to clinical experts. A quantile-based calibration procedure is employed to tune rejection thresholds using either global or class-specific strategies. Experiments conducted on three large public datasets (PadChest, NIH ChestX-ray14, and MIMIC-CXR) demonstrate that selective rejection improves the trade-off between diagnostic accuracy and coverage, with entropy-based rejection yielding the highest average AuC across all pathologies. These results support the integration of selective prediction into AI-assisted diagnostic workflows, providing a practical step toward safer, uncertainty-aware deployment of deep learning in clinical settings.\u003c/p\u003e","manuscriptTitle":"Knowing When Not to Decide: Multi-Pathology Chest X-Ray Classification with Rejection Mechanisms","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-06-06 13:05:51","doi":"10.21203/rs.3.rs-6644332/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-08-05T10:27:45+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-07-12T18:49:56+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-06-20T17:00:29+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"182775873281685565434292060111866330894","date":"2025-06-04T10:41:05+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"311025683897014216314285865399402237385","date":"2025-06-04T10:38:41+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-06-04T10:15:23+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-06-04T10:08:30+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2025-05-26T07:53:27+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-05-26T06:04:30+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2025-05-12T08:06:45+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"0ea176d0-7f9a-44d6-9d71-24a00eb33a03","owner":[],"postedDate":"June 6th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[{"id":49646689,"name":"Health sciences/Diseases"},{"id":49646690,"name":"Health sciences/Diseases/Cardiovascular diseases"},{"id":49646691,"name":"Health sciences/Diseases/Respiratory tract diseases"}],"tags":[],"updatedAt":"2026-02-19T09:53:26+00:00","versionOfRecord":[],"versionCreatedAt":"2025-06-06 13:05:51","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-6644332","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6644332","identity":"rs-6644332","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}