DAM-Seg: Anatomically accurate cardiac segmentation using Dense Associative Networks

DAM-Seg: Anatomically accurate cardiac segmentation using Dense Associative Networks | 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 DAM-Seg: Anatomically accurate cardiac segmentation using Dense Associative Networks Zahid Ullah, Jihie Kim This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6028457/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 Deep learning-based cardiac segmentation has seen significant advancements over the years. Many studies have tackled the challenge of anatomically incorrect segmentation predictions by introducing auxiliary modules. These modules either post-process segmentation outputs or enforce consistency between specific points to ensure anatomical correctness. However, such approaches often increase network complexity, require separate training for these modules, and may lack robustness in scenarios with poor visibility. To address these limitations, we propose a novel transformer-based architecture that leverages dense associative networks to learn and retain specific patterns inherent to cardiac inputs. Unlike traditional methods, our approach restricts the network to memorize a limited set of patterns. During forward propagation, a weighted sum of these patterns is used to enforce anatomical correctness in the output. Since these patterns are input-independent, the model demonstrates enhanced robustness, even in cases with poor visibility. The proposed pipeline was evaluated on two publicly available datasets, CAMUS and CardiacNet. Experimental results indicate that our model consistently outperforms baseline approaches across all metrics, highlighting its effectiveness and reliability for cardiac segmentation tasks. Hopfield Networks Dense associative networks Cardiac segmentation Robust segmentation Full Text Additional Declarations No competing interests reported. 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-6028457","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":415726310,"identity":"32cca22e-dc58-433c-8a4e-a6b30b0be62e","order_by":0,"name":"Zahid Ullah","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAs0lEQVRIiWNgGAWjYPACGyBmbDxAipY0kJYGkrQcBpPEaZFvbz4m8THnvN3a9sNAW2psoglqYew5liY5c9vt5G1nEoFajqXlNhDSwiyRYybNC9RidgCohbHhMGEtbPLvvwG1nEs2O/+QSC08EjxsQC0H7MxuEGuLBE+aseXMbckJZjeAtiQQ4xf59sMPb3zcZmdvdj794YMPNTaEtcBAIlhlArHKQcCeFMWjYBSMglEwwgAA2wdEOuLgQ30AAAAASUVORK5CYII=","orcid":"","institution":"Dongguk University","correspondingAuthor":true,"prefix":"","firstName":"Zahid","middleName":"","lastName":"Ullah","suffix":""},{"id":415726311,"identity":"73feacb6-d6b8-4513-9759-e8cb292e2d44","order_by":1,"name":"Jihie Kim","email":"","orcid":"","institution":"Dongguk University","correspondingAuthor":false,"prefix":"","firstName":"Jihie","middleName":"","lastName":"Kim","suffix":""}],"badges":[],"createdAt":"2025-02-14 07:53:25","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6028457/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6028457/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":77382780,"identity":"9781cd9a-5ef5-4117-b016-81f4a14a80c6","added_by":"auto","created_at":"2025-02-28 04:23:48","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":2229172,"visible":true,"origin":"","legend":"","description":"","filename":"DAMSegArtificialIntelligenceReviewSubmitted.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6028457/v1_covered_92aff23c-d34d-41b1-bee3-0702f3b4f64b.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"DAM-Seg: Anatomically accurate cardiac segmentation using Dense Associative Networks","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"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":"Hopfield Networks, Dense associative networks, Cardiac segmentation, Robust segmentation","lastPublishedDoi":"10.21203/rs.3.rs-6028457/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6028457/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Deep learning-based cardiac segmentation has seen significant advancements over the years. Many studies have tackled the challenge of anatomically incorrect segmentation predictions by introducing auxiliary modules. These modules either post-process segmentation outputs or enforce consistency between specific points to ensure anatomical correctness. However, such approaches often increase network complexity, require separate training for these modules, and may lack robustness in scenarios with poor visibility. To address these limitations, we propose a novel transformer-based architecture that leverages dense associative networks to learn and retain specific patterns inherent to cardiac inputs. Unlike traditional methods, our approach restricts the network to memorize a limited set of patterns. During forward propagation, a weighted sum of these patterns is used to enforce anatomical correctness in the output. Since these patterns are input-independent, the model demonstrates enhanced robustness, even in cases with poor visibility. The proposed pipeline was evaluated on two publicly available datasets, CAMUS and CardiacNet. Experimental results indicate that our model consistently outperforms baseline approaches across all metrics, highlighting its effectiveness and reliability for cardiac segmentation tasks. ","manuscriptTitle":"DAM-Seg: Anatomically accurate cardiac segmentation using Dense Associative Networks","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-02-17 03:32:12","doi":"10.21203/rs.3.rs-6028457/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":"1133a353-5fa0-4a34-8764-2bbac244e1bc","owner":[],"postedDate":"February 17th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2025-02-28T04:23:16+00:00","versionOfRecord":[],"versionCreatedAt":"2025-02-17 03:32:12","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-6028457","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6028457","identity":"rs-6028457","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}