Influence-driven Sample Selection for Functional Brain Network Classification: Application to Autism Diagnosis

Influence-driven Sample Selection for Functional Brain Network Classification: Application to Autism Diagnosis | 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 Influence-driven Sample Selection for Functional Brain Network Classification: Application to Autism Diagnosis Ismail Bilgen, Islem Rekik, Behçet Uğur Töreyin This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7152649/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 The proliferation of non-invasive neuroimaging datasets acquired from different modalities has driven advancements in machine learning models for diagnosing brain disorders. While prior studies have primarily focused on feature engineering and model architecture improvements, they often neglect the impact of low-quality samples in training datasets, which can significantly hinder diagnostic performance. To address this, we introduce a novel sample selection framework, Influence-based Detection of Opponent Samples (IDOS), which estimates sample quality using influences approximated by the change in loss relative to a reference point. We utilized Graph Convolutional Networks (GCN) and Differentiable Graph Pooling Modules (DIFFPOOL) in IDOS using an architecture that leverages whole-brain graphs. Excluding low-quality samples identified by IDOS significantly enhanced both models’ performance compared to the baseline, yielding average improvements of 6.89% and 7.15% across accuracy, precision, recall, and specificity, for GCN and DIFFPOOL, respectively. The proposed framework offers a generalizable solution for mitigating the impact of suboptimal samples. Neurological disorder ASD ML Sample Selection Influence 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-7152649","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":496200987,"identity":"62fdb347-211b-49be-aefb-bfcd0c17609a","order_by":0,"name":"Ismail Bilgen","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAyklEQVRIiWNgGAWjYBACNgnGxgNAWo4NwiVOSwNIizEbG1QLD0E9EgwMIC2JDURr4ZNubjj4peJOep98jwHDh7LDDPbSBwg4TOZgw2GZM89y29h4DBhnnDvMwMOXQMgviQ2HJdsOg7Uw87YBtRByGUTLv8PpbCAtf4nVcvBjw+EEsBZGorSA/MJw7LBhG1tawcGec+k8PGcIaJGf3f7w4Y+aw/LyzYc3PvhRZi3H3kNACwgww5xygIGYmAQBxh9EKRsFo2AUjIIRCwDrez29BoS7dgAAAABJRU5ErkJggg==","orcid":"","institution":"Istanbul Technical University","correspondingAuthor":true,"prefix":"","firstName":"Ismail","middleName":"","lastName":"Bilgen","suffix":""},{"id":496200992,"identity":"d784b513-275c-4deb-a586-9ee5152849ba","order_by":1,"name":"Islem Rekik","email":"","orcid":"","institution":"Imperial College London","correspondingAuthor":false,"prefix":"","firstName":"Islem","middleName":"","lastName":"Rekik","suffix":""},{"id":496200993,"identity":"0d09fd88-609f-4994-a84c-89fb9ef7bf0f","order_by":2,"name":"Behçet Uğur Töreyin","email":"","orcid":"","institution":"Istanbul Technical University","correspondingAuthor":false,"prefix":"","firstName":"Behçet","middleName":"Uğur","lastName":"Töreyin","suffix":""}],"badges":[],"createdAt":"2025-07-18 00:23:07","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7152649/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7152649/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":89290700,"identity":"4561481d-81f3-43aa-bfec-2ef983f23e67","added_by":"auto","created_at":"2025-08-18 12:17:10","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1302779,"visible":true,"origin":"","legend":"","description":"","filename":"snmanuscriptlatex.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7152649/v1_covered_b5f9bbc2-e3fd-4060-b372-f9411ea569dc.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Influence-driven Sample Selection for Functional Brain Network Classification: Application to Autism Diagnosis","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"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":"Neurological disorder, ASD, ML, Sample Selection, Influence","lastPublishedDoi":"10.21203/rs.3.rs-7152649/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7152649/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eThe proliferation of non-invasive neuroimaging datasets acquired from different modalities has driven advancements in machine learning models for diagnosing brain disorders. While prior studies have primarily focused on feature engineering and model architecture improvements, they often neglect the impact of low-quality samples in training datasets, which can significantly hinder diagnostic performance. To address this, we introduce a novel sample selection framework, Influence-based Detection of Opponent Samples (IDOS), which estimates sample quality using influences approximated by the change in loss relative to a reference point. We utilized Graph Convolutional Networks (GCN) and Differentiable Graph Pooling Modules (DIFFPOOL) in IDOS using an architecture that leverages whole-brain graphs. Excluding low-quality samples identified by IDOS significantly enhanced both models\u0026rsquo; performance compared to the baseline, yielding average improvements of 6.89% and 7.15% across accuracy, precision, recall, and specificity, for GCN and DIFFPOOL, respectively. The proposed framework offers a generalizable solution for mitigating the impact of suboptimal samples.\u003c/p\u003e","manuscriptTitle":"Influence-driven Sample Selection for Functional Brain Network Classification: Application to Autism Diagnosis","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-08-06 04:30:13","doi":"10.21203/rs.3.rs-7152649/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":"a5035184-21e0-4f29-8fa8-bf961a8cd2d9","owner":[],"postedDate":"August 6th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2025-08-18T12:09:02+00:00","versionOfRecord":[],"versionCreatedAt":"2025-08-06 04:30:13","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7152649","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7152649","identity":"rs-7152649","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}