Vis enkel innførsel

dc.contributor.authorØstvik, Andreas
dc.contributor.authorSmistad, Erik
dc.contributor.authorAase, Svein Arne
dc.contributor.authorHaugen, Bjørn Olav
dc.contributor.authorLøvstakken, Lasse
dc.date.accessioned2018-12-14T12:13:42Z
dc.date.available2018-12-14T12:13:42Z
dc.date.created2018-11-01T08:41:52Z
dc.date.issued2018
dc.identifier.citationUltrasound in Medicine and Biology. 2018, 1-11.nb_NO
dc.identifier.issn0301-5629
dc.identifier.urihttp://hdl.handle.net/11250/2577742
dc.description.abstractTransthoracic echocardiography examinations are usually performed according to a protocol comprising different probe postures providing standard views of the heart. These are used as a basis when assessing cardiac function, and it is essential that the morphophysiological representations are correct. Clinical analysis is often initialized with the current view, and automatic classification can thus be useful in improving today's workflow. In this article, convolutional neural networks (CNNs) are used to create classification models predicting up to seven different cardiac views. Data sets of 2-D ultrasound acquired from studies totaling more than 500 patients and 7000 videos were included. State-of-the-art accuracies of 98.3% ± 0.6% and 98.9% ± 0.6% on single frames and sequences, respectively, and real-time performance with 4.4 ± 0.3 ms per frame were achieved. Further, it was found that CNNs have the potential for use in automatic multiplanar reformatting and orientation guidance. Using 3-D data to train models applicable for 2-D classification, we achieved a median deviation of 4° ± 3° from the optimal orientations.nb_NO
dc.language.isoengnb_NO
dc.titleReal-time Standard View Classification in Transthoracic Echocardiography using Convolutional Neural Networksnb_NO
dc.typeJournal articlenb_NO
dc.typePeer reviewednb_NO
dc.description.versionacceptedVersionnb_NO
dc.source.pagenumber1-11nb_NO
dc.source.journalUltrasound in Medicine and Biologynb_NO
dc.identifier.doi10.1016/j.ultrasmedbio.2018.07.024
dc.identifier.cristin1625771
dc.relation.projectNorges forskningsråd: 237887nb_NO
cristin.unitcode7401,90,25,0
cristin.unitnameHelse
cristin.ispublishedtrue
cristin.fulltextpostprint
cristin.qualitycode2


Tilhørende fil(er)

Thumbnail

Denne innførselen finnes i følgende samling(er)

Vis enkel innførsel