{"paper_id":"3dce4a67-0fb0-4a05-94e1-d09a7b366832","body_text":"A Robust and Data-Efficient Deep Learning Modelfor Cardiac Assessment without 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 A Robust and Data-Efficient Deep Learning Modelfor Cardiac Assessment without Segmentation Conor Artman, Ricardo Henao This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-5290766/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 22 Oct, 2025 Read the published version in BMC Medical Imaging → Version 1 posted 14 You are reading this latest preprint version Abstract Video-based deep learning (DL) algorithms often rely on segmentation models to detect clinically important features in transthoracic echocardiograms (TTEs). While effective, these algorithms can be too data hungry for practice and may be sensitive to common data quality issues. To overcome these concerns, we present a data-efficient DL algorithm, Scaled Gumbel Softmax (SGS) EchoNet, that is robust to these common data quality issues and, importantly, requires no ventricular segmentation model. In lieu of a segmentation model, we decompose and transform the output of an R(2+1)D convolutional encoder to estimate frame-level weights associated with the cardiac cycle, that are then used to obtain a video representation that can be used for estimation. We find that our transformation obviates the need for a segmentation model while improving the ability of the predictive model to handle noisy inputs. We show that our model achieves comparable performance to the state of the art, while demonstrating robustness to noise on an independent (external) validation set. Ultrasounds Computer Vision Clinical Decision Support Robust Deep Learning Cardiac Assessment Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 22 Oct, 2025 Read the published version in BMC Medical Imaging → Version 1 posted Editorial decision: Revision requested 06 May, 2025 Reviews received at journal 03 May, 2025 Reviewers agreed at journal 22 Apr, 2025 Reviewers agreed at journal 19 Mar, 2025 Reviewers agreed at journal 13 Mar, 2025 Reviewers agreed at journal 09 Feb, 2025 Reviewers agreed at journal 05 Jan, 2025 Reviews received at journal 28 Nov, 2024 Reviewers agreed at journal 18 Nov, 2024 Reviewers invited by journal 06 Nov, 2024 Editor invited by journal 30 Oct, 2024 Editor assigned by journal 24 Oct, 2024 Submission checks completed at journal 24 Oct, 2024 First submitted to journal 18 Oct, 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-5290766\",\"acceptedTermsAndConditions\":true,\"allowDirectSubmit\":false,\"archivedVersions\":[],\"articleType\":\"Research Article\",\"associatedPublications\":[],\"authors\":[{\"id\":370019067,\"identity\":\"18ef9809-4ecf-4894-a234-453424425a41\",\"order_by\":0,\"name\":\"Conor Artman\",\"email\":\"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAuklEQVRIiWNgGAWjYPACCTk+dgbGA0SqZgYRFsZsQJokLRWJbURr4Z99/uiGnzsk0tuYeQ8cYPhlk9hASIvEuWS2m71nJHLbmPkSDjD2pRHWwnCGme0GbxtIC4/BAcaew8YEdcgDtdz82yaRzka0FgOglttAWxLAWhh+HJYjqMXwDLPZbdk2CUOwwxIb0ghrkTvD+Ozm27Y6eX72HsMHH/7Y8BDUggoS20jUAAR/SNcyCkbBKBgFwx8AAMAON5+xi9SGAAAAAElFTkSuQmCC\",\"orcid\":\"\",\"institution\":\"Lawrence Livermore National Laboratory\",\"correspondingAuthor\":true,\"prefix\":\"\",\"firstName\":\"Conor\",\"middleName\":\"\",\"lastName\":\"Artman\",\"suffix\":\"\"},{\"id\":370019068,\"identity\":\"1e8e53b1-a075-4ebd-b7dc-880c3c60b12f\",\"order_by\":1,\"name\":\"Ricardo Henao\",\"email\":\"\",\"orcid\":\"\",\"institution\":\"Duke University\",\"correspondingAuthor\":false,\"prefix\":\"\",\"firstName\":\"Ricardo\",\"middleName\":\"\",\"lastName\":\"Henao\",\"suffix\":\"\"}],\"badges\":[],\"createdAt\":\"2024-10-18 16:23:20\",\"currentVersionCode\":1,\"declarations\":\"\",\"doi\":\"10.21203/rs.3.rs-5290766/v1\",\"doiUrl\":\"https://doi.org/10.21203/rs.3.rs-5290766/v1\",\"draftVersion\":[],\"editorialEvents\":[{\"content\":\"https://doi.org/10.1186/s12880-025-01903-x\",\"type\":\"published\",\"date\":\"2025-10-22T16:16:40+00:00\"}],\"editorialNote\":\"\",\"failedWorkflow\":false,\"files\":[{\"id\":94505614,\"identity\":\"d340e205-37fc-4d25-a8a8-6419ca34a267\",\"added_by\":\"auto\",\"created_at\":\"2025-10-28 16:17:14\",\"extension\":\"pdf\",\"order_by\":1,\"title\":\"\",\"display\":\"\",\"copyAsset\":false,\"role\":\"manuscript-pdf\",\"size\":3565940,\"visible\":true,\"origin\":\"\",\"legend\":\"\",\"description\":\"\",\"filename\":\"BMC.pdf\",\"url\":\"https://assets-eu.researchsquare.com/files/rs-5290766/v1_covered_af559500-37d0-460e-b06d-ff4cef48ac66.pdf\"}],\"financialInterests\":\"No competing interests reported.\",\"formattedTitle\":\"A Robust and Data-Efficient Deep Learning Modelfor Cardiac Assessment without 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\":\"info@researchsquare.com\",\"identity\":\"bmc-medical-imaging\",\"isNatureJournal\":false,\"hasQc\":true,\"allowDirectSubmit\":false,\"externalIdentity\":\"bmim\",\"sideBox\":\"Learn more about [BMC Medical Imaging](http://bmcmedimaging.biomedcentral.com/)\",\"snPcode\":\"\",\"submissionUrl\":\"https://www.editorialmanager.com/bmim/default.aspx\",\"title\":\"BMC Medical Imaging\",\"twitterHandle\":\"BMC_series\",\"acdcEnabled\":true,\"dfaEnabled\":false,\"editorialSystem\":\"em\",\"reportingPortfolio\":\"BMC Series\",\"inReviewEnabled\":true,\"inReviewRevisionsEnabled\":true},\"keywords\":\"Ultrasounds, Computer Vision, Clinical Decision Support, Robust Deep Learning, Cardiac Assessment\",\"lastPublishedDoi\":\"10.21203/rs.3.rs-5290766/v1\",\"lastPublishedDoiUrl\":\"https://doi.org/10.21203/rs.3.rs-5290766/v1\",\"license\":{\"name\":\"CC BY 4.0\",\"url\":\"https://creativecommons.org/licenses/by/4.0/\"},\"manuscriptAbstract\":\"Video-based deep learning (DL) algorithms often rely on segmentation models to detect clinically important features in transthoracic echocardiograms (TTEs). While effective, these algorithms can be too data hungry for practice and may be sensitive to common data quality issues. To overcome these concerns, we present a data-efficient DL algorithm, Scaled Gumbel Softmax (SGS) EchoNet, that is robust to these common data quality issues and, importantly, requires no ventricular segmentation model. In lieu of a segmentation model, we decompose and transform the output of an R(2+1)D convolutional encoder to estimate frame-level weights associated with the cardiac cycle, that are then used to obtain a video representation that can be used for estimation. We find that our transformation obviates the need for a segmentation model while improving the ability of the predictive model to handle noisy inputs. We show that our model achieves comparable performance to the state of the art, while demonstrating robustness to noise on an independent (external) validation set.\",\"manuscriptTitle\":\"A Robust and Data-Efficient Deep Learning Modelfor Cardiac Assessment without Segmentation\",\"msid\":\"\",\"msnumber\":\"\",\"nonDraftVersions\":[{\"code\":1,\"date\":\"2024-10-28 04:44:30\",\"doi\":\"10.21203/rs.3.rs-5290766/v1\",\"editorialEvents\":[{\"type\":\"communityComments\",\"content\":0},{\"type\":\"decision\",\"content\":\"Revision requested\",\"date\":\"2025-05-06T09:36:48+00:00\",\"index\":\"\",\"fulltext\":\"\"},{\"type\":\"editorInvitedReview\",\"content\":\"\",\"date\":\"2025-05-03T12:04:12+00:00\",\"index\":\"hide\",\"fulltext\":\"\"},{\"type\":\"reviewerAgreed\",\"content\":\"104550022218768097879119784750332506932\",\"date\":\"2025-04-22T23:12:22+00:00\",\"index\":\"hide\",\"fulltext\":\"\"},{\"type\":\"reviewerAgreed\",\"content\":\"292641101496583473682018927293751985282\",\"date\":\"2025-03-19T06:18:46+00:00\",\"index\":\"hide\",\"fulltext\":\"\"},{\"type\":\"reviewerAgreed\",\"content\":\"329942766906437829936805849042398908751\",\"date\":\"2025-03-14T01:13:43+00:00\",\"index\":\"hide\",\"fulltext\":\"\"},{\"type\":\"reviewerAgreed\",\"content\":\"186545848403798781306637443960161164242\",\"date\":\"2025-02-10T04:09:58+00:00\",\"index\":\"hide\",\"fulltext\":\"\"},{\"type\":\"reviewerAgreed\",\"content\":\"235665405825783027006570677411082998517\",\"date\":\"2025-01-06T00:37:30+00:00\",\"index\":\"hide\",\"fulltext\":\"\"},{\"type\":\"editorInvitedReview\",\"content\":\"\",\"date\":\"2024-11-28T13:56:35+00:00\",\"index\":\"hide\",\"fulltext\":\"\"},{\"type\":\"reviewerAgreed\",\"content\":\"125276900926988048008663723045284609972\",\"date\":\"2024-11-18T12:27:13+00:00\",\"index\":\"hide\",\"fulltext\":\"\"},{\"type\":\"reviewersInvited\",\"content\":\"\",\"date\":\"2024-11-07T00:15:15+00:00\",\"index\":\"\",\"fulltext\":\"\"},{\"type\":\"editorInvited\",\"content\":\"\",\"date\":\"2024-10-30T07:05:48+00:00\",\"index\":\"\",\"fulltext\":\"\"},{\"type\":\"editorAssigned\",\"content\":\"\",\"date\":\"2024-10-24T13:58:11+00:00\",\"index\":\"\",\"fulltext\":\"\"},{\"type\":\"checksComplete\",\"content\":\"\",\"date\":\"2024-10-24T13:57:21+00:00\",\"index\":\"\",\"fulltext\":\"\"},{\"type\":\"submitted\",\"content\":\"BMC Medical Imaging\",\"date\":\"2024-10-18T16:16:42+00:00\",\"index\":\"\",\"fulltext\":\"\"}],\"status\":\"published\",\"journal\":{\"display\":true,\"email\":\"info@researchsquare.com\",\"identity\":\"bmc-medical-imaging\",\"isNatureJournal\":false,\"hasQc\":true,\"allowDirectSubmit\":false,\"externalIdentity\":\"bmim\",\"sideBox\":\"Learn more about [BMC Medical Imaging](http://bmcmedimaging.biomedcentral.com/)\",\"snPcode\":\"\",\"submissionUrl\":\"https://www.editorialmanager.com/bmim/default.aspx\",\"title\":\"BMC Medical Imaging\",\"twitterHandle\":\"BMC_series\",\"acdcEnabled\":true,\"dfaEnabled\":false,\"editorialSystem\":\"em\",\"reportingPortfolio\":\"BMC Series\",\"inReviewEnabled\":true,\"inReviewRevisionsEnabled\":true}}],\"origin\":\"\",\"ownerIdentity\":\"859f01e9-80f1-42e1-b309-ff54be945256\",\"owner\":[],\"postedDate\":\"October 28th, 2024\",\"published\":true,\"recentEditorialEvents\":[],\"rejectedJournal\":[],\"revision\":\"\",\"amendment\":\"\",\"status\":\"published-in-journal\",\"subjectAreas\":[],\"tags\":[],\"updatedAt\":\"2025-10-27T16:40:24+00:00\",\"versionOfRecord\":{\"articleIdentity\":\"rs-5290766\",\"link\":\"https://doi.org/10.1186/s12880-025-01903-x\",\"journal\":{\"identity\":\"bmc-medical-imaging\",\"isVorOnly\":false,\"title\":\"BMC Medical Imaging\"},\"publishedOn\":\"2025-10-22 16:16:40\",\"publishedOnDateReadable\":\"October 22nd, 2025\"},\"versionCreatedAt\":\"2024-10-28 04:44:30\",\"video\":\"\",\"vorDoi\":\"10.1186/s12880-025-01903-x\",\"vorDoiUrl\":\"https://doi.org/10.1186/s12880-025-01903-x\",\"workflowStages\":[]},\"version\":\"v1\",\"identity\":\"rs-5290766\",\"journalConfig\":\"researchsquare\"},\"__N_SSP\":true},\"page\":\"/article/[identity]/[[...version]]\",\"query\":{\"redirect\":\"/article/rs-5290766\",\"identity\":\"rs-5290766\",\"version\":[\"v1\"]},\"buildId\":\"qtupq5eGEP_6zYnWcrvyt\",\"isFallback\":false,\"isExperimentalCompile\":false,\"dynamicIds\":[84888],\"gssp\":true,\"scriptLoader\":[]}","source_license":"CC-BY-4.0","license_restricted":false}