Learning-based heart coverage estimation for short-axis cine cardiac MR images
File(s)
Accepted version
Author(s)
Type
Conference Paper
Abstract
The 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 en-
sure 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 re-
gression 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.
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 en-
sure 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 re-
gression 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.
Date Issued
2017-05-23
Date Acceptance
2017-03-27
Citation
Lecture Notes in Computer Science, 2017, 10263, pp.73-82
Publisher
Springer
Start Page
73
End Page
82
Journal / Book Title
Lecture Notes in Computer Science
Volume
10263
Copyright Statement
© 2017 Springer International Publishing AG. The final publication is available at Springer via https://doi.org/10.1007/978-3-319-59448-4_8
Sponsor
National Institute for Health Research
British Heart Foundation
Imperial College Healthcare NHS Trust- BRC Funding
Engineering & Physical Science Research Council (EPSRC)
Commission of the European Communities
Grant Number
RDB02 79560
PG/12/27/29489
RD410
EP/P001009/1
655033
Source
Functional Imaging and Modelling of the Heart (FIMH)
Subjects
Science & Technology
Life Sciences & Biomedicine
Cardiac & Cardiovascular Systems
Radiology, Nuclear Medicine & Medical Imaging
Cardiovascular System & Cardiology
Quality control
Cardiac MR
Landmark detection
Heart coverage
Artificial Intelligence & Image Processing
Publication Status
Published
Start Date
2017-06-11
Finish Date
2017-06-13
Coverage Spatial
Toronto, Canada
Date Publish Online
2017-05-23