Directional Latent Space Representation For Medical Image Segmentation

Directional Latent Space Representation For Medical Image Segmentation | 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 Directional Latent Space Representation For Medical Image Segmentation Xintao Liu, Yan Gao, Changqing Zhan, Qiao Wang, Yu Zhang, Yi He, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4444261/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 12 Aug, 2024 Read the published version in The Visual Computer → Version 1 posted 11 You are reading this latest preprint version Abstract Efficient medical image segmentation plays an important role in computer-aided diagnosis (CAD). Deep mining of pixel semantics is crucial for medical image segmentation. However, previous works on medical semantic segmentation usually overlook the importance of embedding subspace, and lacked the mining of latent space direction information. In this work, we constructed global orthogonal basis and channel orthogonal basis in the latent space, which can significantly enhance the feature representation. We propose a novel distance-based segmentation method that decouples the embedding space into sub-embedding spaces of different classes, and then implements pixel level classification based on the distance between its embedding features and the origin of the subspace. Experiments on various public medical image segmentation benchmarks show the effectiveness of our model as compared to the state-of-the-art methods. The code will be published at https://github.com/lxt0525/LSDENet . Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 12 Aug, 2024 Read the published version in The Visual Computer → Version 1 posted Editorial decision: Revision requested 21 Jun, 2024 Reviews received at journal 21 Jun, 2024 Reviews received at journal 13 Jun, 2024 Reviewers agreed at journal 12 Jun, 2024 Reviews received at journal 12 Jun, 2024 Reviewers agreed at journal 09 Jun, 2024 Reviewers agreed at journal 07 Jun, 2024 Reviewers invited by journal 23 May, 2024 Editor assigned by journal 20 May, 2024 Submission checks completed at journal 20 May, 2024 First submitted to journal 19 May, 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-4444261","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":307765331,"identity":"aeeb9460-a8ee-41bc-b8d2-709b1df4cd6f","order_by":0,"name":"Xintao Liu","email":"","orcid":"","institution":"","correspondingAuthor":false,"prefix":"","firstName":"Xintao","middleName":"","lastName":"Liu","suffix":""},{"id":307765333,"identity":"7dbbf411-22ad-4f58-90ff-18cd2d6905f2","order_by":1,"name":"Yan Gao","email":"","orcid":"","institution":"","correspondingAuthor":false,"prefix":"","firstName":"Yan","middleName":"","lastName":"Gao","suffix":""},{"id":307765341,"identity":"dc995045-c9c3-4213-83af-e0dad38612fa","order_by":2,"name":"Changqing Zhan","email":"","orcid":"","institution":"","correspondingAuthor":false,"prefix":"","firstName":"Changqing","middleName":"","lastName":"Zhan","suffix":""},{"id":307765343,"identity":"9402c749-77ae-417e-b28d-1482985d1959","order_by":3,"name":"Qiao Wang","email":"","orcid":"","institution":"","correspondingAuthor":false,"prefix":"","firstName":"Qiao","middleName":"","lastName":"Wang","suffix":""},{"id":307765345,"identity":"12fc3ae9-32a8-44a0-aa61-d0a8055b85ee","order_by":4,"name":"Yu Zhang","email":"","orcid":"","institution":"","correspondingAuthor":false,"prefix":"","firstName":"Yu","middleName":"","lastName":"Zhang","suffix":""},{"id":307765347,"identity":"36c86623-216e-40e4-993f-f29e20af1404","order_by":5,"name":"Yi He","email":"","orcid":"","institution":"","correspondingAuthor":false,"prefix":"","firstName":"Yi","middleName":"","lastName":"He","suffix":""},{"id":307765354,"identity":"42c18e25-d080-436c-8d80-138d453633ca","order_by":6,"name":"Hongyan Quan","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA30lEQVRIiWNgGAWjYBACAwhlgyR0gDgtaaRrOUyCFnOJ5G0SP3ecl5dvYD74ubCNQY7vRgLj5wI8WixnpJVJ9p65bbjhAFuy9Mw2BmPJGwnM0jPwOexGjpkEb9vtBAMGHjNm3jaGxA03EtiYeQhokfzbdi5BvoH/G0hLPVFapHnbDiQwHOBhA2lJMCCo5cyzYmvZtmTDDYfZjKV5zkkYzjzzsFkar5bjyRtvvm2zk5dvb374mafMRp7vePLBz/i0MAgkQKOGGUxKADFjAz4NDAz8BwzwKxgFo2AUjIJRAAAJVEYhyhCWLwAAAABJRU5ErkJggg==","orcid":"","institution":"","correspondingAuthor":true,"prefix":"","firstName":"Hongyan","middleName":"","lastName":"Quan","suffix":""}],"badges":[],"createdAt":"2024-05-19 12:23:11","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4444261/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4444261/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1007/s00371-024-03589-8","type":"published","date":"2024-08-12T15:57:02+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":63070709,"identity":"da266830-aca5-4c45-921b-d70c811d8ec7","added_by":"auto","created_at":"2024-08-22 19:51:10","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":846258,"visible":true,"origin":"","legend":"","description":"","filename":"Latex.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4444261/v1_covered_206b92e1-16de-4d5f-8c55-9bf59c0282db.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Directional Latent Space Representation For Medical Image Segmentation","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":"the-visual-computer","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"tvcj","sideBox":"Learn more about [The Visual Computer](http://link.springer.com/journal/371)","snPcode":"371","submissionUrl":"https://submission.nature.com/new-submission/371/3","title":"The Visual Computer","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"","lastPublishedDoi":"10.21203/rs.3.rs-4444261/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4444261/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Efficient medical image segmentation plays an important role in computer-aided diagnosis (CAD). Deep mining of pixel semantics is crucial for medical image segmentation. However, previous works on medical semantic segmentation usually overlook the importance of embedding subspace, and lacked the mining of latent space direction information. In this work, we constructed global orthogonal basis and channel orthogonal basis in the latent space, which can significantly enhance the feature representation. We propose a novel distance-based segmentation method that decouples the embedding space into sub-embedding spaces of different classes, and then implements pixel level classification based on the distance between its embedding features and the origin of the subspace. Experiments on various public medical image segmentation benchmarks show the effectiveness of our model as compared to the state-of-the-art methods. The code will be published at https://github.com/lxt0525/LSDENet.","manuscriptTitle":"Directional Latent Space Representation For Medical Image Segmentation","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-05-31 13:25:13","doi":"10.21203/rs.3.rs-4444261/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2024-06-21T19:12:10+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-06-21T09:14:36+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-06-13T11:15:16+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"42495382312075953112421050503016947443","date":"2024-06-12T09:48:03+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-06-12T09:03:03+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"34170902982002312659883351895850885365","date":"2024-06-10T02:16:37+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"154952114344780445853549686571472744225","date":"2024-06-08T01:23:37+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2024-05-23T13:52:42+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2024-05-20T09:48:54+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2024-05-20T07:37:46+00:00","index":"","fulltext":""},{"type":"submitted","content":"The Visual Computer","date":"2024-05-19T12:21:46+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"the-visual-computer","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"tvcj","sideBox":"Learn more about [The Visual Computer](http://link.springer.com/journal/371)","snPcode":"371","submissionUrl":"https://submission.nature.com/new-submission/371/3","title":"The Visual Computer","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"ad4772b1-6ac1-41b8-a120-de303dccdd63","owner":[],"postedDate":"May 31st, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2024-08-22T19:23:29+00:00","versionOfRecord":{"articleIdentity":"rs-4444261","link":"https://doi.org/10.1007/s00371-024-03589-8","journal":{"identity":"the-visual-computer","isVorOnly":false,"title":"The Visual Computer"},"publishedOn":"2024-08-12 15:57:02","publishedOnDateReadable":"August 12th, 2024"},"versionCreatedAt":"2024-05-31 13:25:13","video":"","vorDoi":"10.1007/s00371-024-03589-8","vorDoiUrl":"https://doi.org/10.1007/s00371-024-03589-8","workflowStages":[]},"version":"v1","identity":"rs-4444261","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4444261","identity":"rs-4444261","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}