Please use this identifier to cite or link to this item: https://doi.org/10.1007/978-3-319-59448-4_8
DC FieldValue
dc.titleLearning-based heart coverage estimation for short-axis cine cardiac MR images
dc.contributor.authorTarroni G.
dc.contributor.authorOktay O.
dc.contributor.authorBai W.
dc.contributor.authorSchuh A.
dc.contributor.authorSuzuki H.
dc.contributor.authorPasserat-Palmbach J.
dc.contributor.authorGlocker B.
dc.contributor.authorde Marvao A.
dc.contributor.authorO�Regan D.
dc.contributor.authorCook S.
dc.contributor.authorRueckert D.
dc.date.accessioned2019-01-21T06:34:23Z
dc.date.available2019-01-21T06:34:23Z
dc.date.issued2017
dc.identifier.citationTarroni G., Oktay O., Bai W., Schuh A., Suzuki H., Passerat-Palmbach J., Glocker B., de Marvao A., O�Regan D., Cook S., Rueckert D. (2017). Learning-based heart coverage estimation for short-axis cine cardiac MR images 10263 LNCS : 73-82. ScholarBank@NUS Repository. https://doi.org/10.1007/978-3-319-59448-4_8
dc.identifier.issn3029743
dc.identifier.urihttp://scholarbank.nus.edu.sg/handle/10635/151043
dc.description.abstractThe correct acquisition of short axis (SA) cine cardiac MR image stacks requires the imaging of the full cardiac anatomy between the apex and the mitral valve plane via multiple 2D slices. While in the clinical practice the SA stacks are usually checked qualitatively to ensure full heart coverage, visual inspection can become infeasible for large amounts of imaging data that is routinely acquired, e.g. in population studies such as the UK Biobank (UKBB). Accordingly, we propose a learning-based technique for the fully-automated estimation of the heart coverage for SA image stacks. The technique relies on the identification of cardiac landmarks (i.e. the apex and the mitral valve sides) on two chamber view long axis images and on the comparison of the landmarks� positions to the volume covered by the SA stack. Landmark detection is performed using a hybrid random forest approach integrating both regression and structured classification models. The technique was applied on 3000 cases from the UKBB and compared to visual assessment. The obtained results (error rate = 2.3%, sens. = 73%, spec. = 90%) indicate that the proposed technique is able to correctly detect the vast majority of the cases with insufficient coverage, suggesting that it could be used as a fully-automated quality control step for CMR SA image stacks. � Springer International Publishing AG 2017.
dc.publisherSpringer Verlag
dc.sourceScopus
dc.subjectCardiac MR
dc.subjectHeart coverage
dc.subjectLandmark detection
dc.subjectQuality control
dc.typeConference Paper
dc.contributor.departmentDUKE-NUS MEDICAL SCHOOL
dc.description.doi10.1007/978-3-319-59448-4_8
dc.description.volume10263 LNCS
dc.description.page73-82
dc.published.statepublished
Appears in Collections:Staff Publications

Show simple item record
Files in This Item:
There are no files associated with this item.

SCOPUSTM   
Citations

2
checked on May 23, 2019

Page view(s)

12
checked on May 22, 2019

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.