dc.contributor.author | Tasken, Anders Austlid | |
dc.contributor.author | Berg, Erik Andreas Rye | |
dc.contributor.author | Grenne, Bjørnar Leangen | |
dc.contributor.author | Holte, Espen | |
dc.contributor.author | Dalen, Håvard | |
dc.contributor.author | Stølen, Stian Bergseng | |
dc.contributor.author | Lindseth, Frank | |
dc.contributor.author | Aakhus, Svend | |
dc.contributor.author | Kiss, Gabriel Hanssen | |
dc.date.accessioned | 2024-01-11T13:29:43Z | |
dc.date.available | 2024-01-11T13:29:43Z | |
dc.date.created | 2023-08-31T12:02:06Z | |
dc.date.issued | 2023 | |
dc.identifier.issn | 0933-3657 | |
dc.identifier.uri | https://hdl.handle.net/11250/3111142 | |
dc.description.abstract | Perioperative monitoring of cardiac function is beneficial for early detection of cardiovascular complications. The standard of care for cardiac monitoring performed by trained cardiologists and anesthesiologists involves a manual and qualitative evaluation of ultrasound imaging, which is a time-demanding and resource-intensive process with intraobserver- and interobserver variability. In practice, such measures can only be performed a limited number of times during the intervention. To overcome these difficulties, this study presents a robust method for automatic and quantitative monitoring of cardiac function based on 3D transesophageal echocardiography (TEE) B-mode ultrasound recordings of the left ventricle (LV). Such an assessment obtains consistent measurements and can produce a near real-time evaluation of ultrasound imagery. Hence, the presented method is time-saving and results in increased accessibility. The mitral annular plane systolic excursion (MAPSE), characterizing global LV function, is estimated by landmark detection and cardiac view classification of two-dimensional images extracted along the long-axis of the ultrasound volume. MAPSE estimation directly from 3D TEE recordings is beneficial since it removes the need for manual acquisition of cardiac views, hence decreasing the need for interference by physicians. Two convolutional neural networks (CNNs) were trained and tested on acquired ultrasound data of 107 patients, and MAPSE estimates were compared to clinically obtained references in a blinded study including 31 patients. The proposed method for automatic MAPSE estimation had low bias and low variability in comparison to clinical reference measures. The method accomplished a mean difference for MAPSE estimates of (-0.16 +- 1.06) mm. Thus, the results did not show significant systematic errors. The obtained bias and variance of the method were comparable to inter-observer variability of clinically obtained MAPSE measures on 2D TTE echocardiography. The novel pipeline proposed in this study has the potential to enhance cardiac monitoring in perioperative- and intensive care settings. | en_US |
dc.description.abstract | Automated estimation of mitral annular plane systolic excursion by artificial intelligence from 3D ultrasound recordings | en_US |
dc.language.iso | eng | en_US |
dc.publisher | Elsevier | en_US |
dc.rights | Navngivelse 4.0 Internasjonal | * |
dc.rights.uri | http://creativecommons.org/licenses/by/4.0/deed.no | * |
dc.subject | Hjertefunksjon | en_US |
dc.subject | Cardiac function | en_US |
dc.subject | Medisinsk ultralyd | en_US |
dc.subject | Medical ultrasound | en_US |
dc.subject | Artificial intelligence in health and ethics | en_US |
dc.subject | Artificial intelligence in health and ethics | en_US |
dc.subject | Hjerteklaffekirurgi | en_US |
dc.subject | aortic valve replacement | en_US |
dc.subject | Artificial Neural Networks | en_US |
dc.subject | Artificial Neural Networks | en_US |
dc.subject | kunstig innteligens | en_US |
dc.subject | Artificial inteligence | en_US |
dc.subject | Hjerteinfarkt | en_US |
dc.subject | Myocardial infarction | en_US |
dc.subject | Hjertesykdommer | en_US |
dc.subject | Heart diseases | en_US |
dc.subject | Artificial Intelligence | en_US |
dc.subject | Artificial Intelligence | en_US |
dc.subject | Hjerte og karsykdom | en_US |
dc.subject | Cardiovascular disease | en_US |
dc.subject | Bildebehandling | en_US |
dc.subject | Image processing | en_US |
dc.subject | Ultralyd 3D-avbildning | en_US |
dc.subject | Ultrasound 3D imaging | en_US |
dc.subject | Medisinsk bildebehandling | en_US |
dc.subject | Medical image processing | en_US |
dc.subject | Applied Artificial Intelligence | en_US |
dc.subject | Applied Artificial Intelligence | en_US |
dc.subject | Kunstig intelligens | en_US |
dc.subject | Artificial intelligence | en_US |
dc.subject | Invasiv kardiologi | en_US |
dc.subject | Interventional cardiology | en_US |
dc.subject | Bildeanalyse | en_US |
dc.subject | Image analysis | en_US |
dc.title | Automated estimation of mitral annular plane systolic excursion by artificial intelligence from 3D ultrasound recordings | en_US |
dc.title.alternative | Automated estimation of mitral annular plane systolic excursion by artificial intelligence from 3D ultrasound recordings | en_US |
dc.type | Peer reviewed | en_US |
dc.type | Journal article | en_US |
dc.description.version | publishedVersion | en_US |
dc.subject.nsi | VDP::Datateknologi: 551 | en_US |
dc.subject.nsi | VDP::Computer technology: 551 | en_US |
dc.subject.nsi | VDP::Datateknologi: 551 | en_US |
dc.subject.nsi | VDP::Computer technology: 551 | en_US |
dc.subject.nsi | VDP::Datateknologi: 551 | en_US |
dc.subject.nsi | VDP::Computer technology: 551 | en_US |
dc.subject.nsi | VDP::Datateknologi: 551 | en_US |
dc.subject.nsi | VDP::Computer technology: 551 | en_US |
dc.subject.nsi | VDP::Datateknologi: 551 | en_US |
dc.subject.nsi | VDP::Computer technology: 551 | en_US |
dc.subject.nsi | VDP::Datateknologi: 551 | en_US |
dc.subject.nsi | VDP::Computer technology: 551 | en_US |
dc.source.volume | 144 | en_US |
dc.source.journal | Artificial Intelligence in Medicine | en_US |
dc.identifier.doi | 10.1016/j.artmed.2023.102646 | |
dc.identifier.cristin | 2171353 | |
dc.relation.project | Norges forskningsråd: 237887 | en_US |
cristin.ispublished | true | |
cristin.fulltext | preprint | |
cristin.fulltext | original | |
cristin.qualitycode | 2 | |