Deep Learning Phase Error Correction for Cerebrovascular 4D Flow MRI

Deep Learning Phase Error Correction for Cerebrovascular 4D Flow MRI | 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 Article Deep Learning Phase Error Correction for Cerebrovascular 4D Flow MRI Shanmukha Srinivas, Evan Masutani, Alexander Norbash, Albert Hsiao This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-2399531/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 05 Jun, 2023 Read the published version in Scientific Reports → Version 1 posted 8 You are reading this latest preprint version Abstract Background and Purpose Background phase errors in 4D Flow MRI may negatively impact blood flow quantification. In this study, we assessed their impact on cerebrovascular flow volume measurements, evaluated the benefit of manual image-based correction, and assessed the potential of a convolutional neural network (CNN), a form of deep learning, to directly infer the correction vector field. Methods With IRB waiver of informed consent, we retrospectively identified 96 MRI exams from 48 patients who underwent cerebrovascular 4D Flow MRI from October 2015 to 2020. Flow measurements of the anterior, posterior, and venous circulation were performed to assess inflow-outflow error and the benefit of manual image-based phase error correction. A CNN was then trained to directly infer the phase-error correction field, without segmentation, from 4D Flow volumes to automate correction, reserving from 23 exams for testing. Statistical analyses included Spearman correlation, Bland-Altman, Wilcoxon-signed rank (WSR) and F-tests. Results Prior to correction, there was strong correlation between inflow and outflow ( ρ = 0.833–0.947) measurements with the largest discrepancy in the venous circulation. Manual phase error correction improved inflow-outflow correlation ( ρ = 0.945–0.981) and decreased variance ( p < 0.001, F-test ). Fully automated CNN correction was non-inferior to manual correction with no significant differences in correlation ( ρ = 0.971 vs ρ = 0.982) or bias ( p = 0.82, Wilcoxon-Signed Rank test ) of inflow and outflow measurements. Conclusions Residual background phase error can impair inflow-outflow consistency of cerebrovascular flow volume measurements. A CNN can be used to directly infer the phase-error vector field to fully automate phase error correction. CNN = convolutional neural network SRS = stereotactic radiosurgery SM = Spetzler-Martin VENC = velocity encoding BA = basilar artery PCA = posterior cerebral artery SSS = superior sagittal sinus SS = straight sinus TS = transverse sinus WSR = Wilcoxon-signed rank Full Text Additional Declarations Competing interest reported. AH receives research grant support from GE Healthcare and Bayer AG. AH is a founder and shareholder of Arterys. EM and AH are listed as co-inventors on patent application US20220261991A1 (status: pending) assigned to The Regents of the University of California, which includes in its claims the CNN-based method to perform phase error correction on 4D Flow MRI. SS and AN declare no potential conflict of interest. Cite Share Download PDF Status: Published Journal Publication published 05 Jun, 2023 Read the published version in Scientific Reports → Version 1 posted Editorial decision: Major revision 13 Mar, 2023 Reviews received at journal 09 Mar, 2023 Reviewers agreed at journal 27 Feb, 2023 Reviewers invited by journal 16 Feb, 2023 Editor assigned by journal 16 Feb, 2023 Editor invited by journal 23 Dec, 2022 Submission checks completed at journal 23 Dec, 2022 First submitted to journal 20 Dec, 2022 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-2399531","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":162484622,"identity":"92d94505-4b8e-4cc2-9d0b-66621d0193a0","order_by":0,"name":"Shanmukha Srinivas","email":"","orcid":"","institution":"UC San Diego Health System","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Shanmukha","middleName":"","lastName":"Srinivas","suffix":""},{"id":162484627,"identity":"13d7a1de-c43f-4899-9f10-33f995134bc8","order_by":1,"name":"Evan Masutani","email":"","orcid":"","institution":"UC San Diego Health System","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Evan","middleName":"","lastName":"Masutani","suffix":""},{"id":162484630,"identity":"ddb02496-add8-48fd-881a-0703ee7d5d22","order_by":2,"name":"Alexander Norbash","email":"","orcid":"","institution":"UC San Diego Health System","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Alexander","middleName":"","lastName":"Norbash","suffix":""},{"id":162484633,"identity":"61ccb098-65fc-4550-82d3-1eaa42f7c68e","order_by":3,"name":"Albert Hsiao","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABAUlEQVRIie2QP2vCQBTAXwjYxZL1lupXeBJwaT7M3ZIsJzgJhQ5C4aZgVj9GnNTtwoEup12zNVvXuBQXpdfoVHohY4f7DY/H4/14fwAcjv9IkAJQgAECeNKbNzWT91oUohslNG0gi04K8CayvLMSzA+qrl6jZP3wVqnTBliWqRzqmbLvpRYxobt4sk13KAsNbFnGU295tCsg9RhoT03ykhpFmA1JH/1HYVeGkoc1vaoEPz7rmxJo9C8tCkqOhAlFsezfpwBH32tRRqUeE7aIR7nmU3kQJPy5pUiPiVUZvKfh6fwVDXG/X1UvInoyH1tV59mz/fxfkCbKzv0Oh8Ph+JNv5G5lWqJhSdsAAAAASUVORK5CYII=","orcid":"","institution":"UC San Diego Health System","correspondingAuthor":true,"submittingAuthor":false,"prefix":"","firstName":"Albert","middleName":"","lastName":"Hsiao","suffix":""}],"badges":[],"createdAt":"2022-12-21 03:29:05","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-2399531/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-2399531/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1038/s41598-023-36061-z","type":"published","date":"2023-06-05T21:08:37+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":44730725,"identity":"c20b706b-8430-478b-97e8-f3d5e322521f","added_by":"auto","created_at":"2023-10-16 21:33:45","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":448964,"visible":true,"origin":"","legend":"","description":"","filename":"NeuroECCManuscriptSciReports.pdf","url":"https://assets-eu.researchsquare.com/files/rs-2399531/v1_covered_f8d1bd58-df0c-453d-bd1a-efb9d64871a2.pdf"}],"financialInterests":"Competing interest reported. AH receives research grant support from GE Healthcare and Bayer AG. AH is a founder and shareholder of Arterys. EM and AH are listed as co-inventors on patent application US20220261991A1 (status: pending) assigned to The Regents of the University of California, which includes in its claims the CNN-based method to perform phase error correction on 4D Flow MRI. SS and AN declare no potential conflict of interest.","formattedTitle":"Deep Learning Phase Error Correction for Cerebrovascular 4D Flow MRI","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":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"CNN = convolutional neural network, SRS = stereotactic radiosurgery, SM = Spetzler-Martin, VENC = velocity encoding, BA = basilar artery, PCA = posterior cerebral artery, SSS = superior sagittal sinus, SS = straight sinus, TS = transverse sinus, WSR = Wilcoxon-signed rank","lastPublishedDoi":"10.21203/rs.3.rs-2399531/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-2399531/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003ch2\u003eBackground and Purpose\u003c/h2\u003e \u003cp\u003eBackground phase errors in 4D Flow MRI may negatively impact blood flow quantification. In this study, we assessed their impact on cerebrovascular flow volume measurements, evaluated the benefit of manual image-based correction, and assessed the potential of a convolutional neural network (CNN), a form of deep learning, to directly infer the correction vector field.\u003c/p\u003e\u003ch2\u003eMethods\u003c/h2\u003e \u003cp\u003eWith IRB waiver of informed consent, we retrospectively identified 96 MRI exams from 48 patients who underwent cerebrovascular 4D Flow MRI from October 2015 to 2020. Flow measurements of the anterior, posterior, and venous circulation were performed to assess inflow-outflow error and the benefit of manual image-based phase error correction. A CNN was then trained to directly infer the phase-error correction field, without segmentation, from 4D Flow volumes to automate correction, reserving from 23 exams for testing. Statistical analyses included Spearman correlation, Bland-Altman, Wilcoxon-signed rank (WSR) and F-tests.\u003c/p\u003e\u003ch2\u003eResults\u003c/h2\u003e \u003cp\u003ePrior to correction, there was strong correlation between inflow and outflow (\u003cem\u003eρ\u0026thinsp;=\u003c/em\u003e\u0026thinsp;0.833\u0026ndash;0.947) measurements with the largest discrepancy in the venous circulation. Manual phase error correction improved inflow-outflow correlation (\u003cem\u003eρ\u0026thinsp;=\u003c/em\u003e\u0026thinsp;0.945\u0026ndash;0.981) and decreased variance (\u003cem\u003ep\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.001, \u003cem\u003eF-test\u003c/em\u003e). Fully automated CNN correction was non-inferior to manual correction with no significant differences in correlation (\u003cem\u003eρ\u003c/em\u003e\u0026thinsp;=\u0026thinsp;0.971 vs \u003cem\u003eρ\u003c/em\u003e\u0026thinsp;=\u0026thinsp;0.982) or bias (\u003cem\u003ep\u003c/em\u003e\u0026thinsp;=\u0026thinsp;0.82, \u003cem\u003eWilcoxon-Signed Rank test\u003c/em\u003e) of inflow and outflow measurements.\u003c/p\u003e\u003ch2\u003eConclusions\u003c/h2\u003e \u003cp\u003eResidual background phase error can impair inflow-outflow consistency of cerebrovascular flow volume measurements. A CNN can be used to directly infer the phase-error vector field to fully automate phase error correction.\u003c/p\u003e","manuscriptTitle":"Deep Learning Phase Error Correction for Cerebrovascular 4D Flow MRI","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2022-12-29 06:20:47","doi":"10.21203/rs.3.rs-2399531/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Major revision","date":"2023-03-13T07:21:49+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2023-03-09T16:31:30+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"87810879-a090-4322-811f-ab7c9392f356","date":"2023-02-27T15:47:17+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2023-02-16T22:10:03+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2023-02-16T22:01:43+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2022-12-23T13:03:33+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2022-12-23T12:57:29+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2022-12-21T03:16:07+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"ccf741a7-ed30-4c34-9058-6a8f82978ca9","owner":[],"postedDate":"December 29th, 2022","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2023-10-16T21:17:42+00:00","versionOfRecord":{"articleIdentity":"rs-2399531","link":"https://doi.org/10.1038/s41598-023-36061-z","journal":{"identity":"scientific-reports","isVorOnly":false,"title":"Scientific Reports"},"publishedOn":"2023-06-05 21:08:37","publishedOnDateReadable":"June 5th, 2023"},"versionCreatedAt":"2022-12-29 06:20:47","video":"","vorDoi":"10.1038/s41598-023-36061-z","vorDoiUrl":"https://doi.org/10.1038/s41598-023-36061-z","workflowStages":[]},"version":"v1","identity":"rs-2399531","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-2399531","identity":"rs-2399531","version":["v1"]},"buildId":"7rjqhiLT3MXkJMwkYKINL","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}