Artificial Intelligence to derive aligned strain in cine CMR to detect patients with myocardial fibrosis: an open and scrutinizable approach

Artificial Intelligence to derive aligned strain in cine CMR to detect patients with myocardial fibrosis: an open and scrutinizable approach | 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 Artificial Intelligence to derive aligned strain in cine CMR to detect patients with myocardial fibrosis: an open and scrutinizable approach Sven Koehler, Julian Kuhm, Tyler Huffaker, Daniel Young, Animesh Tandon, and 5 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-3785677/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 Cine Cardiac Magnetic Resonance (CMR) is the gold standard for cardiac function evaluation, incorporating ejection fraction (EF) and strain as vital indicators of abnormal deformation. Rare pathologies like Duchenne muscular dystrophies (DMD) are monitored with repeated late gadolinium-enhanced (LGE) CMR for identification of myocardial fibrosis. However, it is judicious to reduce repeated gadolinium exposure and rather employ strain analysis from cine CMR. This solution is limited so far since full strain curves are not comparable between individual cardiac cycles and current practice mainly neglects diastolic deformation patterns. Our novel Deep Learning-based approach derives strain values aligned by key frames throughout the cardiac cycle. In a reproducibility scenario (57+82 patients), our results reveal five times more significant differences (22 vs. 4) between patients with scar and without, enhancing scar detection by +30%, improving detection of patients with preserved EF by +61%, with an overall sensitivity/specificity of 82/81%. Health sciences/Cardiology Biological sciences/Computational biology and bioinformatics/Machine learning Biological sciences/Computational biology and bioinformatics/Image processing Full Text Additional Declarations Yes there is potential Competing Interest. AT is a consultant for Siemens Healthineers and Realize Medical. The other authors declares no competing interests. Supplementary Files 20231220supplinfoalignedstrain.pdf 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-3785677","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":264766236,"identity":"9261da77-35a8-4dfc-a458-21ad2c2ced1e","order_by":0,"name":"Sven Koehler","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABEElEQVRIiWNgGAWjYJCCAw9AJA8DAzNDAQMDP1FaEuBaDBgYJBsgohJ49aBoMThAQAu/2OGHBxL+HJYz5zl88HGBgU2+8fnVaRKMO2zqcGmRnJ1mcCCx7bCxZW9bsvEMgzTLbTfebjZgPJOG0xaD2wlALQ1piRvO85hJ8xgcNjC7cXbjA8a2wzi12N9O/wB0WFo9UIv5bx6D/wbGM85uOMDY9h+3LdI5BgcS2GwSDM72mDHzGBwwMODvBdlyAKcWids5BUC/2BhuOHMsGeiwZAOJG7ybDRLbkmGBjQH4Z6dv/vDhj4S8wZnkg595KuwM+PvPbpP42GZHVJTCLE6AxhTxgP8AaepHwSgYBaNg2AMAR3dbPJzaHGkAAAAASUVORK5CYII=","orcid":"https://orcid.org/0000-0003-4989-8766","institution":"University Clinic Heidelberg","correspondingAuthor":true,"prefix":"","firstName":"Sven","middleName":"","lastName":"Koehler","suffix":""},{"id":264766237,"identity":"d3a1dfff-d2ef-4fe8-8f5d-c897090d2f7b","order_by":1,"name":"Julian Kuhm","email":"","orcid":"https://orcid.org/0000-0003-1980-276X","institution":"University Clinic Heidelberg","correspondingAuthor":false,"prefix":"","firstName":"Julian","middleName":"","lastName":"Kuhm","suffix":""},{"id":264766238,"identity":"fe39902b-340a-4991-b21c-566c2bf94279","order_by":2,"name":"Tyler Huffaker","email":"","orcid":"","institution":"UT Southwestern /Children’s Health","correspondingAuthor":false,"prefix":"","firstName":"Tyler","middleName":"","lastName":"Huffaker","suffix":""},{"id":264766239,"identity":"cccf05f5-c892-4ab2-86ae-a1902b850e64","order_by":3,"name":"Daniel Young","email":"","orcid":"","institution":"UT Southwestern /Children’s Health","correspondingAuthor":false,"prefix":"","firstName":"Daniel","middleName":"","lastName":"Young","suffix":""},{"id":264766240,"identity":"b673b8a3-43dd-4a50-986e-254ec7c0b447","order_by":4,"name":"Animesh Tandon","email":"","orcid":"https://orcid.org/0000-0001-9769-8801","institution":"Cleveland Clinic Children's Center for Artificial Intelligence (C4AI)","correspondingAuthor":false,"prefix":"","firstName":"Animesh","middleName":"","lastName":"Tandon","suffix":""},{"id":264766241,"identity":"79f0bd08-af9c-49d9-829b-2a42c88d7172","order_by":5,"name":"Florian Andre","email":"","orcid":"","institution":"Heidelberg University Hospital","correspondingAuthor":false,"prefix":"","firstName":"Florian","middleName":"","lastName":"Andre","suffix":""},{"id":264766242,"identity":"1de861bb-a670-40ef-8802-a7c8a34b26d9","order_by":6,"name":"Norbert Frey","email":"","orcid":"","institution":"University Hospital Heidelberg","correspondingAuthor":false,"prefix":"","firstName":"Norbert","middleName":"","lastName":"Frey","suffix":""},{"id":264766243,"identity":"14ca3d15-7ed7-43d2-960f-87fac6d0daa8","order_by":7,"name":"Gerald Greil","email":"","orcid":"","institution":"UT Southwestern /Children’s Health","correspondingAuthor":false,"prefix":"","firstName":"Gerald","middleName":"","lastName":"Greil","suffix":""},{"id":264766244,"identity":"8eca39f7-9a40-4de2-9952-db5a8d813ce1","order_by":8,"name":"Tarique Hussain","email":"","orcid":"","institution":"UT Southwestern /Children’s Health","correspondingAuthor":false,"prefix":"","firstName":"Tarique","middleName":"","lastName":"Hussain","suffix":""},{"id":264766245,"identity":"7902ee41-778c-4a95-bc8a-462ffa743763","order_by":9,"name":"Sandy Engelhardt","email":"","orcid":"","institution":"University Hospital Heidelberg","correspondingAuthor":false,"prefix":"","firstName":"Sandy","middleName":"","lastName":"Engelhardt","suffix":""}],"badges":[],"createdAt":"2023-12-21 08:25:27","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-3785677/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-3785677/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":49212695,"identity":"9ba543d4-05af-4f47-8287-6be11748026c","added_by":"auto","created_at":"2024-01-05 09:20:09","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":5114660,"visible":true,"origin":"","legend":"","description":"","filename":"20231220manuscriptalignedstrain.pdf","url":"https://assets-eu.researchsquare.com/files/rs-3785677/v1_covered_c451a370-029b-40c2-95c0-aff2132cf669.pdf"},{"id":49199789,"identity":"214fa035-3d9a-4451-b07a-a6f10f54eb69","added_by":"auto","created_at":"2024-01-05 04:14:41","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":6182289,"visible":true,"origin":"","legend":"","description":"","filename":"20231220supplinfoalignedstrain.pdf","url":"https://assets-eu.researchsquare.com/files/rs-3785677/v1/b0f164cb15eadef9c47e6f21.pdf"}],"financialInterests":"\u003cb\u003eYes\u003c/b\u003e there is potential Competing Interest.\nAT is a consultant for Siemens Healthineers and Realize Medical.\r\nThe other authors declares no competing interests.","formattedTitle":"Artificial Intelligence to derive aligned strain in cine CMR to detect patients with myocardial fibrosis: an open and scrutinizable approach","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"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":"","lastPublishedDoi":"10.21203/rs.3.rs-3785677/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-3785677/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Cine Cardiac Magnetic Resonance (CMR) is the gold standard for cardiac function evaluation, incorporating ejection fraction (EF) and strain as vital indicators of abnormal deformation. Rare pathologies like Duchenne muscular dystrophies (DMD) are monitored with repeated late gadolinium-enhanced (LGE) CMR for identification of myocardial fibrosis. However, it is judicious to reduce repeated gadolinium exposure and rather employ strain analysis from cine CMR. This solution is limited so far since full strain curves are not comparable between individual cardiac cycles and current practice mainly neglects diastolic deformation patterns. Our novel Deep Learning-based approach derives strain values aligned by key frames throughout the cardiac cycle. In a reproducibility scenario (57+82 patients), our results reveal five times more significant differences (22 vs. 4) between patients with scar and without, enhancing scar detection by +30%, improving detection of patients with preserved EF by +61%, with an overall sensitivity/specificity of 82/81%.","manuscriptTitle":"Artificial Intelligence to derive aligned strain in cine CMR to detect patients with myocardial fibrosis: an open and scrutinizable approach","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-01-05 04:14:36","doi":"10.21203/rs.3.rs-3785677/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":"05760a07-61f4-40a8-9a16-139d9c4b3620","owner":[],"postedDate":"January 5th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":27899067,"name":"Health sciences/Cardiology"},{"id":27899068,"name":"Biological sciences/Computational biology and bioinformatics/Machine learning"},{"id":27899069,"name":"Biological sciences/Computational biology and bioinformatics/Image processing"}],"tags":[],"updatedAt":"2024-01-05T19:50:34+00:00","versionOfRecord":[],"versionCreatedAt":"2024-01-05 04:14:36","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-3785677","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-3785677","identity":"rs-3785677","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}