Hierarchical Owen Value Explanations for Interpretable Brain Tumor Classification in Medical Imaging

Hierarchical Owen Value Explanations for Interpretable Brain Tumor Classification in Medical Imaging | 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 Hierarchical Owen Value Explanations for Interpretable Brain Tumor Classification in Medical Imaging Shengxi Li, Jianfeng Chen, Fanxin Meng This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7117910/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 7 You are reading this latest preprint version Abstract Deep learning models have shown promising accuracy in brain tumor classification from medical images, but their black-box nature remains a barrier to clinical adoption. To address this, we propose a structured explanation framework based on the Owen value, which extends the Shapley value by incorporating spatial feature dependencies through a predefined segmentation hierarchy. Unlike traditional SHAP-based methods that treat pixels as independent features, our approach groups spatially coherent regions using superpixel segmentation and recursively distributes attribution scores through a multi-layer hierarchy. This design aligns more closely with clinical reasoning and improves both interpretability and computational efficiency. We evaluate our method using three metrics including Pointing Game Accuracy (PGA), Attribution Entropy (AE), and Area Over the Perturbation Curve (AOPC), and show that it consistently outperforms SHAP and axis-aligned Owen baselines in both explanation quality and runtime. The proposed framework offers a scalable and clinically meaningful path toward trustworthy AI-assisted diagnosis in medical imaging. Explainable artificial intelligence (XAI) Owen value Shapley value brain tumor classification medical image analysis saliency map hierarchical attribution deep learning interpretability Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Reviews received at journal 07 Nov, 2025 Reviewers agreed at journal 17 Oct, 2025 Reviewers invited by journal 15 Oct, 2025 Editor invited by journal 06 Oct, 2025 Editor assigned by journal 15 Sep, 2025 Submission checks completed at journal 12 Sep, 2025 First submitted to journal 12 Sep, 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-7117910","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":534912465,"identity":"264f87cc-3df5-4970-8ebe-3e4d3b6a6b92","order_by":0,"name":"Shengxi Li","email":"","orcid":"","institution":"Zhuhai College of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Shengxi","middleName":"","lastName":"Li","suffix":""},{"id":534912466,"identity":"0a224955-5751-4196-bc2f-5dbbe6e6aebd","order_by":1,"name":"Jianfeng Chen","email":"","orcid":"","institution":"Zhuhai College of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Jianfeng","middleName":"","lastName":"Chen","suffix":""},{"id":534912467,"identity":"5d127412-75e5-4c32-8b3f-1073f9a708c1","order_by":2,"name":"Fanxin Meng","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAq0lEQVRIiWNgGAWjYDAC5gOMD6BMAyK1sCUwg5RKkKSFTYI0LbptPGaVP2rq6hjYm7dJMNTcIazF7Bhb2g2JY4clGHiOlUkwHHtGhJb7zcduGDYckGCQyDGTYGw4TIwtjG0FiQ11Egzyb4jWwnyM4WADM9AWHqK1sCVLNhw7LNnGk1ZskXCMKC08hh+BIcbPz354440PNURogQM2EJFAgoZRMApGwSgYBXgAAAL5MxY4i8YuAAAAAElFTkSuQmCC","orcid":"","institution":"Zhuhai College of Science and Technology","correspondingAuthor":true,"prefix":"","firstName":"Fanxin","middleName":"","lastName":"Meng","suffix":""}],"badges":[],"createdAt":"2025-07-14 07:08:15","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7117910/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7117910/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":94616728,"identity":"ed3f21a4-476b-43c7-a1be-8dbad940e190","added_by":"auto","created_at":"2025-10-29 03:03:36","extension":"json","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":5227,"visible":true,"origin":"","legend":"","description":"","filename":"767897fe95ae4af2a0018597efa546be.json","url":"https://assets-eu.researchsquare.com/files/rs-7117910/v1/cbee5277094fcf4a60a15e3d.json"},{"id":94617524,"identity":"3d195edc-1ed1-4fff-a935-1f1b1cf1ae9c","added_by":"auto","created_at":"2025-10-29 03:43:30","extension":"xml","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":93443,"visible":true,"origin":"","legend":"","description":"","filename":"767897fe95ae4af2a0018597efa546be1enriched.xml","url":"https://assets-eu.researchsquare.com/files/rs-7117910/v1/2d3f9752c94b2bc34ff1b0de.xml"},{"id":94616736,"identity":"a950e949-53bf-4bd9-a6be-2d37c3fe92af","added_by":"auto","created_at":"2025-10-29 03:03:37","extension":"pdf","order_by":2,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":5875226,"visible":true,"origin":"","legend":"","description":"","filename":"BMCMedicalImaging2025.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7117910/v1/2e56fc4c0716e04d86dd18f7.pdf"},{"id":94616733,"identity":"70c723d5-625e-4273-b754-4fe7cd03dea6","added_by":"auto","created_at":"2025-10-29 03:03:36","extension":"pdf","order_by":4,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":125628,"visible":true,"origin":"","legend":"","description":"","filename":"responseletter.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7117910/v1/a5b74826494ccf8fbc58b2dc.pdf"},{"id":94617510,"identity":"9525fa3b-dca3-4688-b19a-a97f2954041d","added_by":"auto","created_at":"2025-10-29 03:41:07","extension":"cls","order_by":7,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":55854,"visible":true,"origin":"","legend":"","description":"","filename":"snjnl.cls","url":"https://assets-eu.researchsquare.com/files/rs-7117910/v1/9a4be63266ec4cf5c6d63a61.cls"},{"id":94616730,"identity":"8d1d4ed0-ea2e-49c2-bbd8-d387cf0fbb14","added_by":"auto","created_at":"2025-10-29 03:03:36","extension":"bst","order_by":8,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":64166,"visible":true,"origin":"","legend":"","description":"","filename":"snmathphysnum.bst","url":"https://assets-eu.researchsquare.com/files/rs-7117910/v1/dc705fb946682356caa4ca1f.bst"},{"id":94616732,"identity":"5548db7c-7909-4c02-8abf-bf8fc24fcb46","added_by":"auto","created_at":"2025-10-29 03:03:36","extension":"bst","order_by":9,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":37333,"visible":true,"origin":"","legend":"","description":"","filename":"snnature.bst","url":"https://assets-eu.researchsquare.com/files/rs-7117910/v1/4b719ae62e51d627b92bd4fd.bst"},{"id":94616734,"identity":"1fe8388e-a4dc-4eb9-ae6b-b6de040cf63e","added_by":"auto","created_at":"2025-10-29 03:03:36","extension":"xml","order_by":11,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":100095,"visible":true,"origin":"","legend":"","description":"","filename":"767897fe95ae4af2a0018597efa546be1structuring.xml","url":"https://assets-eu.researchsquare.com/files/rs-7117910/v1/a90cfbe4628b5b206e9b221c.xml"},{"id":94616735,"identity":"b7a6be44-f145-431f-8e7a-ca3c0fd88260","added_by":"auto","created_at":"2025-10-29 03:03:37","extension":"html","order_by":12,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":112343,"visible":true,"origin":"","legend":"","description":"","filename":"earlyproof.html","url":"https://assets-eu.researchsquare.com/files/rs-7117910/v1/5244c0785875252657995639.html"},{"id":94618341,"identity":"3850298a-1c9d-4b70-9a29-7162c7e20aa7","added_by":"auto","created_at":"2025-10-29 03:48:40","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":964351,"visible":true,"origin":"","legend":"","description":"","filename":"BMCMedicalImaging2025.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7117910/v1_covered_743b641e-4857-43b6-b117-3f86b6ccc41e.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Hierarchical Owen Value Explanations for Interpretable Brain Tumor Classification in Medical Imaging","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":"bmc-medical-imaging","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"bmim","sideBox":"Learn more about [BMC Medical Imaging](http://bmcmedimaging.biomedcentral.com/)","snPcode":"","submissionUrl":"https://www.editorialmanager.com/bmim/default.aspx","title":"BMC Medical Imaging","twitterHandle":"BMC_series","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"em","reportingPortfolio":"BMC Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"Explainable artificial intelligence (XAI), Owen value, Shapley value, brain tumor classification, medical image analysis, saliency map, hierarchical attribution, deep learning interpretability","lastPublishedDoi":"10.21203/rs.3.rs-7117910/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7117910/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eDeep learning models have shown promising accuracy in brain tumor classification from medical images, but their black-box nature remains a barrier to clinical adoption. To address this, we propose a structured explanation framework based on the Owen value, which extends the Shapley value by incorporating spatial feature dependencies through a predefined segmentation hierarchy. Unlike traditional SHAP-based methods that treat pixels as independent features, our approach groups spatially coherent regions using superpixel segmentation and recursively distributes attribution scores through a multi-layer hierarchy. This design aligns more closely with clinical reasoning and improves both interpretability and computational efficiency. We evaluate our method using three metrics including Pointing Game Accuracy (PGA), Attribution Entropy (AE), and Area Over the Perturbation Curve (AOPC), and show that it consistently outperforms SHAP and axis-aligned Owen baselines in both explanation quality and runtime. The proposed framework offers a scalable and clinically meaningful path toward trustworthy AI-assisted diagnosis in medical imaging.\u003c/p\u003e","manuscriptTitle":"Hierarchical Owen Value Explanations for Interpretable Brain Tumor Classification in Medical Imaging","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-10-29 03:03:31","doi":"10.21203/rs.3.rs-7117910/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"editorInvitedReview","content":"","date":"2025-11-07T18:22:12+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"206493446627403470282600573273352171297","date":"2025-10-17T18:13:11+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-10-15T16:24:22+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2025-10-06T08:21:58+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-09-15T05:58:07+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-09-13T03:36:10+00:00","index":"","fulltext":""},{"type":"submitted","content":"BMC Medical Imaging","date":"2025-09-13T03:33:50+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"bmc-medical-imaging","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"bmim","sideBox":"Learn more about [BMC Medical Imaging](http://bmcmedimaging.biomedcentral.com/)","snPcode":"","submissionUrl":"https://www.editorialmanager.com/bmim/default.aspx","title":"BMC Medical Imaging","twitterHandle":"BMC_series","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"em","reportingPortfolio":"BMC Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"feeeefc6-3d14-4d7b-ae6d-ea3ee2f2dc4b","owner":[],"postedDate":"October 29th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2025-10-29T03:03:31+00:00","versionOfRecord":[],"versionCreatedAt":"2025-10-29 03:03:31","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7117910","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7117910","identity":"rs-7117910","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}