Spinal Segmentation Based on Heatmap Regression Positioning and Improved UNet

Spinal Segmentation Based on Heatmap Regression Positioning and Improved UNet | 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 Spinal Segmentation Based on Heatmap Regression Positioning and Improved UNet Yuyao Huang, Yuhang Wang, Li He, Zhiqin He, Lin Xiao This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4673743/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 11 You are reading this latest preprint version Abstract The spine is essential for supporting the human body and maintaining its functions. In primary healthcare settings, radiologist shortages and medical resource scarcity often result in spinal fracture misdiagnoses and oversights. This paper introduces a spinal segmentation method utilizing heat map regression and an enhanced UNet, aiding radiologists in swiftly diagnosing spinal fractures and enhancing diagnostic efficiency. During landmark positioning, this paper presents an M-SCN network structure designed for multi-feature fusion. The LA stage of SCN incorporates multi-level feature outputs, while the SC stage introduces cyclic feature fusion, enhancing the feature extraction method and the selection of the maximum feature values, thereby improving the SCN's capability to capture local and global image features. To enhance positioning accuracy, we propose a graph-structured multi-coordinate point optimization method. A weighted directed graph is constructed, employing the predicted heat map's peak value and the Euclidean distances between points to define unary terms and pairwise weights for graph edges. Finally, the Bellman-Ford algorithm optimizes the coordinate points, significantly enhancing positioning accuracy. Compared to the original SCN network, the M-SCN network reduces the prediction error rate by 4.43%. Addressing the issue of UNet's inability to capture global feature information, which results in incomplete vertebrae segmentation, we introduce a UNet-CB network structure featuring global context attention. ContextBlocks and residual connections are integrated into the UNet BasicBlock to bolster global information capture. Additionally, a central heatmap is introduced to improve individual vertebrae recognition. In the vertebral segmentation experiment, the Dice Similarity Coefficient (DSC) achieved 95.64%, the Maximum Symmetry Surface Distance (MSSD) was 4.862 mm, and accuracy and recall rates were 95.86% and 92.46%, respectively. Spinal fracture Landmark positioning Deep learning Image segmentation Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Editorial decision: Revision requested 29 Sep, 2024 Reviews received at journal 20 Jul, 2024 Reviews received at journal 20 Jul, 2024 Reviews received at journal 18 Jul, 2024 Reviewers agreed at journal 14 Jul, 2024 Reviewers agreed at journal 10 Jul, 2024 Reviewers agreed at journal 10 Jul, 2024 Reviewers invited by journal 10 Jul, 2024 Editor assigned by journal 09 Jul, 2024 Submission checks completed at journal 08 Jul, 2024 First submitted to journal 02 Jul, 2024 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-4673743","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":329553201,"identity":"6d6c7c55-4739-445a-b665-6caa722fdb05","order_by":0,"name":"Yuyao Huang","email":"","orcid":"","institution":"Guizhou University","correspondingAuthor":false,"prefix":"","firstName":"Yuyao","middleName":"","lastName":"Huang","suffix":""},{"id":329553202,"identity":"dec97618-d8a8-40e5-8b2d-36c9affc6610","order_by":1,"name":"Yuhang Wang","email":"","orcid":"","institution":"Guizhou University","correspondingAuthor":false,"prefix":"","firstName":"Yuhang","middleName":"","lastName":"Wang","suffix":""},{"id":329553203,"identity":"8214dd2e-9404-4d2f-82e3-bebfaa07b8e3","order_by":2,"name":"Li He","email":"","orcid":"","institution":"Shenzhen Traditional Chinese Medicine Hospital","correspondingAuthor":false,"prefix":"","firstName":"Li","middleName":"","lastName":"He","suffix":""},{"id":329553204,"identity":"8dc8caf6-a1ef-47da-9996-1df88b30cada","order_by":3,"name":"Zhiqin He","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAtklEQVRIiWNgGAWjYFACHgaGDxCWAfFaGGeQrIWZhyQt8u25Bx/b/KpLbGBv3ibBUHOHsBbGnnfJxrl9bIkNPMfKJBiOPSOshVkix0w6t4cnsQHIkGBsOExYC5tEjvlvyx6JxAb5N0Rq4QEazszwwwBoCw+RWiR43hhL9jYkGLfxpBVbJBwjQot8e47hhx9/6mT72Q9vvPGhhggtDAwJwGBrA3oKyiZSC8Mf4pSOglEwCkbBCAUAxGUzvxfr4/EAAAAASUVORK5CYII=","orcid":"","institution":"Guizhou University","correspondingAuthor":true,"prefix":"","firstName":"Zhiqin","middleName":"","lastName":"He","suffix":""},{"id":329553205,"identity":"9e05635f-5ab1-4c75-b935-243e1f6745e2","order_by":4,"name":"Lin Xiao","email":"","orcid":"","institution":"Guizhou University","correspondingAuthor":false,"prefix":"","firstName":"Lin","middleName":"","lastName":"Xiao","suffix":""}],"badges":[],"createdAt":"2024-07-02 11:09:37","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4673743/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4673743/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":61468714,"identity":"36b15510-dcc4-452d-8863-d9543c131c1a","added_by":"auto","created_at":"2024-07-31 06:16:37","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1034656,"visible":true,"origin":"","legend":"","description":"","filename":"SpinalSegmentationBasedonHeatmapRegressionPositioningandImprovedUNet.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4673743/v1_covered_3fd38393-c2c9-4585-a8a9-cb8a37b41282.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Spinal Segmentation Based on Heatmap Regression Positioning and Improved UNet","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":true,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"cluster-computing","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"Learn more about [Cluster Computing](https://www.springer.com/journal/10586)","snPcode":"10586","submissionUrl":"https://submission.nature.com/new-submission/10586/3","title":"Cluster Computing","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Spinal fracture, Landmark positioning, Deep learning, Image segmentation ","lastPublishedDoi":"10.21203/rs.3.rs-4673743/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4673743/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eThe spine is essential for supporting the human body and maintaining its functions. In primary healthcare settings, radiologist shortages and medical resource scarcity often result in spinal fracture misdiagnoses and oversights. This paper introduces a spinal segmentation method utilizing heat map regression and an enhanced UNet, aiding radiologists in swiftly diagnosing spinal fractures and enhancing diagnostic efficiency. During landmark positioning, this paper presents an M-SCN network structure designed for multi-feature fusion. The LA stage of SCN incorporates multi-level feature outputs, while the SC stage introduces cyclic feature fusion, enhancing the feature extraction method and the selection of the maximum feature values, thereby improving the SCN's capability to capture local and global image features. To enhance positioning accuracy, we propose a graph-structured multi-coordinate point optimization method. A weighted directed graph is constructed, employing the predicted heat map's peak value and the Euclidean distances between points to define unary terms and pairwise weights for graph edges. Finally, the Bellman-Ford algorithm optimizes the coordinate points, significantly enhancing positioning accuracy. Compared to the original SCN network, the M-SCN network reduces the prediction error rate by 4.43%. Addressing the issue of UNet's inability to capture global feature information, which results in incomplete vertebrae segmentation, we introduce a UNet-CB network structure featuring global context attention. ContextBlocks and residual connections are integrated into the UNet BasicBlock to bolster global information capture. Additionally, a central heatmap is introduced to improve individual vertebrae recognition. In the vertebral segmentation experiment, the Dice Similarity Coefficient (DSC) achieved 95.64%, the Maximum Symmetry Surface Distance (MSSD) was 4.862 mm, and accuracy and recall rates were 95.86% and 92.46%, respectively.\u003c/p\u003e","manuscriptTitle":"Spinal Segmentation Based on Heatmap Regression Positioning and Improved UNet","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-07-31 06:08:28","doi":"10.21203/rs.3.rs-4673743/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2024-09-29T23:21:49+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-07-20T16:09:27+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-07-20T08:49:51+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-07-18T21:06:41+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"308802992536462148266784024149391640756","date":"2024-07-14T08:39:48+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"128712400766106220161697702690630516799","date":"2024-07-10T06:25:53+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"289312154074763761407329515785636607576","date":"2024-07-10T05:54:48+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2024-07-10T05:44:36+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2024-07-09T08:25:17+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2024-07-08T09:53:51+00:00","index":"","fulltext":""},{"type":"submitted","content":"Cluster Computing","date":"2024-07-02T11:08:17+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"cluster-computing","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"Learn more about [Cluster Computing](https://www.springer.com/journal/10586)","snPcode":"10586","submissionUrl":"https://submission.nature.com/new-submission/10586/3","title":"Cluster Computing","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"95b1f7d1-a12e-47f1-ad72-d2447cd262b8","owner":[],"postedDate":"July 31st, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2025-01-12T14:23:28+00:00","versionOfRecord":[],"versionCreatedAt":"2024-07-31 06:08:28","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-4673743","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4673743","identity":"rs-4673743","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}