Multi-Scale Intracranial Hemorrhage Detection in CT scans Using Cross-Stage Partial Fusion and Hierarchical Feature Learning

Multi-Scale Intracranial Hemorrhage Detection in CT scans Using Cross-Stage Partial Fusion and Hierarchical Feature 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 Research Article Multi-Scale Intracranial Hemorrhage Detection in CT scans Using Cross-Stage Partial Fusion and Hierarchical Feature Learning Burri Vijaya kumari, Satya Sai Ram This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6709416/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 Intracranial hemorrhage (ICH) detection from CT scans poses two major challenges: (1) Variability in hemorrhage size and location, which requires a model capable of detecting small, medium, and large-scale ICH instances, and (2) Efficient feature extraction, ensuring accurate detection while maintaining computational efficiency. To address these challenges, this study proposes a deep learning-based architecture for automated ICH detection using CT scan images from the CQ500 dataset. The model leverages Mosaic Data Augmentation to enhance training and a customized C2F (Cross-Stage Partial Fusion) module to improve feature extraction efficiency across different scales. The proposed model contains three main components: “the Backbone, Neck, and Head”. The C2F module, integrated into both the Backbone and Neck, enhances multi-scale feature learning by maintaining rich spatial information and improving gradient flow. The Neck incorporates Upsample layers to refine extracted features before passing them to the Head. The Detect module, embedded in the Head, performs hierarchical ICH predictions at small, medium, and large scales, ensuring comprehensive hemorrhage localization. The model was evaluated on the CQ500 dataset, achieving high performance metrics, with Precision: 0.945, Recall: 0.941, F1-score: 0.94, [email protected] : 0.974, and [email protected] :0.95: 0.822. These results demonstrate the model’s efficacy in accurately detecting ICH at multiple scales. Intracranial Hemorrhage detection CQ500 dataset Cross-Stage Partial Fusion Detect module 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-6709416","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":467818484,"identity":"ec2b67f8-8d0a-4b95-b90e-c15114a1772b","order_by":0,"name":"Burri Vijaya kumari","email":"data:image/png;base64,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","orcid":"","institution":"Acharya Nagarjuna University college of Engineering and Technology, Acharya Nagarjuna University","correspondingAuthor":true,"prefix":"","firstName":"Burri","middleName":"Vijaya","lastName":"kumari","suffix":""},{"id":467818489,"identity":"10c1b5ee-2f00-4258-8dd3-7dc3382255e0","order_by":1,"name":"Satya Sai Ram","email":"","orcid":"","institution":"RVR \u0026 JC College of Engineering","correspondingAuthor":false,"prefix":"","firstName":"Satya","middleName":"Sai","lastName":"Ram","suffix":""}],"badges":[],"createdAt":"2025-05-20 15:53:07","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6709416/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6709416/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":85593477,"identity":"dc5d8e4f-58ee-4ed3-9b69-0e6247d15ca5","added_by":"auto","created_at":"2025-06-28 13:16:40","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1764447,"visible":true,"origin":"","legend":"","description":"","filename":"ICHYolov8neuro.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6709416/v1_covered_f260ee96-e7c5-4338-8400-28195f4f796f.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Multi-Scale Intracranial Hemorrhage Detection in CT scans Using Cross-Stage Partial Fusion and Hierarchical Feature Learning","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":"Intracranial Hemorrhage detection, CQ500 dataset, Cross-Stage Partial Fusion, Detect module","lastPublishedDoi":"10.21203/rs.3.rs-6709416/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6709416/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eIntracranial hemorrhage (ICH) detection from CT scans poses two major challenges: (1) Variability in hemorrhage size and location, which requires a model capable of detecting small, medium, and large-scale ICH instances, and (2) Efficient feature extraction, ensuring accurate detection while maintaining computational efficiency. To address these challenges, this study proposes a deep learning-based architecture for automated ICH detection using CT scan images from the CQ500 dataset. The model leverages Mosaic Data Augmentation to enhance training and a customized C2F (Cross-Stage Partial Fusion) module to improve feature extraction efficiency across different scales. The proposed model contains three main components: \u0026ldquo;the Backbone, Neck, and Head\u0026rdquo;. The C2F module, integrated into both the Backbone and Neck, enhances multi-scale feature learning by maintaining rich spatial information and improving gradient flow. The Neck incorporates Upsample layers to refine extracted features before passing them to the Head. The Detect module, embedded in the Head, performs hierarchical ICH predictions at small, medium, and large scales, ensuring comprehensive hemorrhage localization. The model was evaluated on the CQ500 dataset, achieving high performance metrics, with Precision: 0.945, Recall: 0.941, F1-score: 0.94, [email protected]: 0.974, and [email protected]:0.95: 0.822. These results demonstrate the model\u0026rsquo;s efficacy in accurately detecting ICH at multiple scales.\u003c/p\u003e","manuscriptTitle":"Multi-Scale Intracranial Hemorrhage Detection in CT scans Using Cross-Stage Partial Fusion and Hierarchical Feature Learning","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-06-09 03:23:01","doi":"10.21203/rs.3.rs-6709416/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":"ca91782a-4c0e-4fac-978e-3871ff8a76d0","owner":[],"postedDate":"June 9th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2025-06-28T13:08:30+00:00","versionOfRecord":[],"versionCreatedAt":"2025-06-09 03:23:01","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-6709416","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6709416","identity":"rs-6709416","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}