Towards Ultra-low Framerate Ultrasound Localization Microscopy on Human Brain with Artificial Intelligence

Towards Ultra-low Framerate Ultrasound Localization Microscopy on Human Brain with Artificial Intelligence | 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 Biological Sciences - Article Towards Ultra-low Framerate Ultrasound Localization Microscopy on Human Brain with Artificial Intelligence Xinyang Jiang, Chuanyu Zhong, Weixun Wan, Zefan Qu, Zilong Wang, and 11 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6936682/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted You are reading this latest preprint version Abstract Ultrasound Localization Microscopy (ULM) has emerged as a promising technique for in-vivo imaging of microvasculature. Conventional ULM relies on ultrasound acquisitions with high (typically>500 Hz) or ultra-high (~ 20,000Hz) frame rates, which are technically challenging in routine clinical settings due to hardware limitations and restricted fields of view. This study aims to enable broader clinical use by developing a ULM framework that operates effectively on low (∼ 40 Hz) and ultra-low (∼ 10 Hz) frame rate CEUS videos. By systematically evaluating the effects of low and ultra-low frame rate clinical ultrasound videos on existing open-source ULM algorithms, we developed Low Framerate Ultrasound Localization Microscopy (LFRULM), which is an AI-enhanced ULM framework tailored for real-world clinical applications. LFRULM incorporates deep neural network modules to improve all three core components of conventional ULM pipelines: microbubble localization, microbubble linking, and trajectory accumulation. Our results demonstrate that conventional ULM algorithms perform suboptimally under low frame rate conditions, with notable artifacts, incomplete vascular reconstructions, and reduced spatial fidelity. In contrast, LFRULM exhibits superior robustness to temporal undersampling and background noise, producing clearer and more comprehensive vascular images with improved spatial resolution, reduced artifacts, and reliable quantitative measurements of cerebral microvascular dynamics. Biological sciences/Biological techniques/Imaging/Ultrasound Health sciences/Medical research/Translational research Full Text Additional Declarations There is NO Competing Interest. Cite Share Download PDF Status: Under Review 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-6936682","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Biological Sciences - Article","associatedPublications":[],"authors":[{"id":497353317,"identity":"80dc1d37-211f-4d4a-964e-1ca5fef67f49","order_by":0,"name":"Xinyang Jiang","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA40lEQVRIiWNgGAWjYDACZijFLwGmJWSI1yI5g4GxAaiFh3jbDG6AtTAQ1mJwnPeYxM8dtezGt5uPP7pRY8HDwH746AZ8WiSb+dIke88cZza7cyyxOecY0GE8aWk38GnhZ+Yxk+BtO8ZsdiPHsDmHDahFgscMrxY2oBbJv0AtxjNAWv4RoQVkizRvWw2zgQRQS24bEVokm3mMrWXbDjBL3EhLnJ3bJ8HDRsgvBufPGN5821aXzD8j+cDnnG91cvzsh4/h1QIELMB4P5yM8B0B5SDA/IGBoc6OCIWjYBSMglEwUgEAMYlAya1RqZIAAAAASUVORK5CYII=","orcid":"","institution":"Microsoft","correspondingAuthor":true,"prefix":"","firstName":"Xinyang","middleName":"","lastName":"Jiang","suffix":""},{"id":497353318,"identity":"c678ad84-aaf7-4b06-bd3d-e4af195b850b","order_by":1,"name":"Chuanyu Zhong","email":"","orcid":"","institution":"Shanghai Sixth People’s Hospital, Shanghai Jiao Tong University of Medicine","correspondingAuthor":false,"prefix":"","firstName":"Chuanyu","middleName":"","lastName":"Zhong","suffix":""},{"id":497353319,"identity":"310d6276-1095-4061-9ce8-d5287dc3a3b7","order_by":2,"name":"Weixun Wan","email":"","orcid":"","institution":"Tongji University","correspondingAuthor":false,"prefix":"","firstName":"Weixun","middleName":"","lastName":"Wan","suffix":""},{"id":497353320,"identity":"ad42b347-46f1-41be-b5ad-123d7501958a","order_by":3,"name":"Zefan Qu","email":"","orcid":"","institution":"Tongji University","correspondingAuthor":false,"prefix":"","firstName":"Zefan","middleName":"","lastName":"Qu","suffix":""},{"id":497353321,"identity":"bf4184aa-ec1b-4473-9da5-75527f874efc","order_by":4,"name":"Zilong Wang","email":"","orcid":"https://orcid.org/0000-0002-6760-1471","institution":"Microsoft","correspondingAuthor":false,"prefix":"","firstName":"Zilong","middleName":"","lastName":"Wang","suffix":""},{"id":497353322,"identity":"ca7f5068-fa21-48a7-9824-8866b9680963","order_by":5,"name":"Xingxuan Zhang","email":"","orcid":"","institution":"Shanghai Sixth People’s Hospital, Shanghai Jiao Tong University of Medicine","correspondingAuthor":false,"prefix":"","firstName":"Xingxuan","middleName":"","lastName":"Zhang","suffix":""},{"id":497353323,"identity":"46e5e250-a009-43a3-8687-bae18f739cb9","order_by":6,"name":"Xiang Xu","email":"","orcid":"","institution":"The First Affiliated Hospital, Fujian Medical University","correspondingAuthor":false,"prefix":"","firstName":"Xiang","middleName":"","lastName":"Xu","suffix":""},{"id":497353324,"identity":"b0604850-1d1d-4fcc-9756-2508306d868c","order_by":7,"name":"Linglin Wei","email":"","orcid":"","institution":"The First Affiliated Hospital, Fujian Medical University","correspondingAuthor":false,"prefix":"","firstName":"Linglin","middleName":"","lastName":"Wei","suffix":""},{"id":497353325,"identity":"23d2d22f-a96c-4a30-96fa-791fa36ad4dc","order_by":8,"name":"Dailin Sun","email":"","orcid":"","institution":"The First Affiliated Hospital, Fujian Medical University","correspondingAuthor":false,"prefix":"","firstName":"Dailin","middleName":"","lastName":"Sun","suffix":""},{"id":497353326,"identity":"2936b315-a9ca-4827-8314-d525016695f5","order_by":9,"name":"Yu Wang","email":"","orcid":"","institution":"Fujian Medical University","correspondingAuthor":false,"prefix":"","firstName":"Yu","middleName":"","lastName":"Wang","suffix":""},{"id":497353327,"identity":"2600822f-c9ab-4bd3-8235-27e5af4496a9","order_by":10,"name":"Yuanxiang Lin","email":"","orcid":"","institution":"The First Affiliated Hospital of Fujian Medical University","correspondingAuthor":false,"prefix":"","firstName":"Yuanxiang","middleName":"","lastName":"Lin","suffix":""},{"id":497353328,"identity":"f7718080-c973-4115-9450-ccb6fced42b0","order_by":11,"name":"Xinxiu Liu","email":"","orcid":"","institution":"The First Affiliated Hospital, Fujian Medical University","correspondingAuthor":false,"prefix":"","firstName":"Xinxiu","middleName":"","lastName":"Liu","suffix":""},{"id":497353329,"identity":"716a6914-2a32-42aa-84e5-f336a3f84cfc","order_by":12,"name":"Cairong Zhao","email":"","orcid":"","institution":"Tongji University","correspondingAuthor":false,"prefix":"","firstName":"Cairong","middleName":"","lastName":"Zhao","suffix":""},{"id":497353330,"identity":"7af0d26f-6817-4238-b6ef-f2a8a60da346","order_by":13,"name":"Dongsheng Li","email":"","orcid":"","institution":"Microsoft","correspondingAuthor":false,"prefix":"","firstName":"Dongsheng","middleName":"","lastName":"Li","suffix":""},{"id":497353331,"identity":"423db5d7-cd83-420b-932e-49f949e2df24","order_by":14,"name":"Lili Qiu","email":"","orcid":"","institution":"Microsoft","correspondingAuthor":false,"prefix":"","firstName":"Lili","middleName":"","lastName":"Qiu","suffix":""},{"id":497353332,"identity":"66376d09-5c24-42e8-b3fe-117ac9a6db9c","order_by":15,"name":"Yuanyi Zheng","email":"","orcid":"https://orcid.org/0000-0002-1328-0641","institution":"Sixth People's Hospital Affiliated to Shanghai Jiao Tong University School of Medicine","correspondingAuthor":false,"prefix":"","firstName":"Yuanyi","middleName":"","lastName":"Zheng","suffix":""}],"badges":[],"createdAt":"2025-06-20 08:07:21","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6936682/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6936682/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":93399712,"identity":"5df132fe-820c-4dee-af74-a2852480e413","added_by":"auto","created_at":"2025-10-13 12:22:24","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":7519749,"visible":true,"origin":"","legend":"Article File","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6936682/v1_covered_322409f2-8cbf-4454-b3a9-68f8d080e314.pdf"}],"financialInterests":"There is \u003cb\u003eNO\u003c/b\u003e Competing Interest.","formattedTitle":"Towards Ultra-low Framerate Ultrasound Localization Microscopy on Human Brain with Artificial Intelligence","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":false,"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":"nature-portfolio","isNatureJournal":true,"hasQc":false,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"","title":"Nature Portfolio","twitterHandle":"","acdcEnabled":false,"dfaEnabled":false,"editorialSystem":"ejp","reportingPortfolio":"","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"","lastPublishedDoi":"10.21203/rs.3.rs-6936682/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6936682/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Ultrasound Localization Microscopy (ULM) has emerged as a promising technique for in-vivo imaging of microvasculature. Conventional ULM relies on ultrasound acquisitions with high (typically\u003e500 Hz) or ultra-high (~ 20,000Hz) frame rates, which are technically challenging in routine clinical settings due to hardware limitations and restricted fields of view. This study aims to enable broader clinical use by developing a ULM framework that operates effectively on low (∼ 40 Hz) and ultra-low (∼ 10 Hz) frame rate CEUS videos. By systematically evaluating the effects of low and ultra-low frame rate clinical ultrasound videos on existing open-source ULM algorithms, we developed Low Framerate Ultrasound Localization Microscopy (LFRULM), which is an AI-enhanced ULM framework tailored for real-world clinical applications. LFRULM incorporates deep neural network modules to improve all three core components of conventional ULM pipelines: microbubble localization, microbubble linking, and trajectory accumulation. Our results demonstrate that conventional ULM algorithms perform suboptimally under low frame rate conditions, with notable artifacts, incomplete vascular reconstructions, and reduced spatial fidelity. In contrast, LFRULM exhibits superior robustness to temporal undersampling and background noise, producing clearer and more comprehensive vascular images with improved spatial resolution, reduced artifacts, and reliable quantitative measurements of cerebral microvascular dynamics.","manuscriptTitle":"Towards Ultra-low Framerate Ultrasound Localization Microscopy on Human Brain with Artificial Intelligence","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-10-13 12:14:09","doi":"10.21203/rs.3.rs-6936682/v1","editorialEvents":[],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"nature-communications","isNatureJournal":true,"hasQc":false,"allowDirectSubmit":false,"externalIdentity":"NCOMMS","sideBox":"Learn more about [Nature Communications](http://www.nature.com/ncomms/)","snPcode":"","submissionUrl":"https://mts-ncomms.nature.com/","title":"Nature Communications","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"ejp","reportingPortfolio":"Nature Communications","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"eccd8b7d-0355-42fd-b219-435210ac52a6","owner":[],"postedDate":"October 13th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[{"id":52834439,"name":"Biological sciences/Biological techniques/Imaging/Ultrasound"},{"id":52834440,"name":"Health sciences/Medical research/Translational research"}],"tags":[],"updatedAt":"2025-10-13T12:14:10+00:00","versionOfRecord":[],"versionCreatedAt":"2025-10-13 12:14:09","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-6936682","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6936682","identity":"rs-6936682","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}