Scipediacontent: Scipediacontent moved page Draft Content 943040862 to Tarroni et al 2019a

2021-02-15T11:34:09Z

Scipediacontent moved page Draft Content 943040862 to Tarroni et al 2019a

Scipediacontent: Created page with " == Abstract == The effectiveness of a cardiovascular magnetic resonance (CMR) scan depends on the ability of the operator to correctly tune the acquisition parameters to the..."

2021-02-15T11:34:06Z

Created page with " == Abstract == The effectiveness of a cardiovascular magnetic resonance (CMR) scan depends on the ability of the operator to correctly tune the acquisition parameters to the..."

New page

== Abstract ==

The effectiveness of a cardiovascular magnetic resonance (CMR) scan depends on the ability of the operator to correctly tune the acquisition parameters to the subject being scanned and on the potential occurrence of imaging artefacts such as cardiac and respiratory motion. In the clinical practice, a quality control step is performed by visual assessment of the acquired images: however, this procedure is strongly operator-dependent, cumbersome and sometimes incompatible with the time constraints in clinical settings and large-scale studies. We propose a fast, fully-automated, learning-based quality control pipeline for CMR images, specifically for short-axis image stacks. Our pipeline performs three important quality checks: 1) heart coverage estimation, 2) inter-slice motion detection, 3) image contrast estimation in the cardiac region. The pipeline uses a hybrid decision forest method - integrating both regression and structured classification models - to extract landmarks as well as probabilistic segmentation maps from both long- and short-axis images as a basis to perform the quality checks. The technique was tested on up to 3000 cases from the UK Biobank as well as on 100 cases from the UK Digital Heart Project, and validated against manual annotations and visual inspections performed by expert interpreters. The results show the capability of the proposed pipeline to correctly detect incomplete or corrupted scans (e.g. on UK Biobank, sensitivity and specificity respectively 88% and 99% for heart coverage estimation, 85% and 95% for motion detection), allowing their exclusion from the analysed dataset or the triggering of a new acquisition.

Document type: Article

== Full document ==
<pdf>Media:Draft_Content_943040862-beopen997-9587-document.pdf</pdf>

== Original document ==

The different versions of the original document can be found in:

* [http://arxiv.org/abs/1803.09354 http://arxiv.org/abs/1803.09354] under the license https://creativecommons.org/licenses/by

* [http://dx.doi.org/10.1109/tmi.2018.2878509 http://dx.doi.org/10.1109/tmi.2018.2878509]

* [http://hdl.handle.net/10044/1/65595 http://hdl.handle.net/10044/1/65595]

* [http://openaccess.city.ac.uk/id/eprint/22768/1/2018-Learning-Based_Quality_Control_for_Cardiac_MR_Images.pdf http://openaccess.city.ac.uk/id/eprint/22768/1/2018-Learning-Based_Quality_Control_for_Cardiac_MR_Images.pdf]

* [https://openaccess.city.ac.uk/id/eprint/22768/1/2018-Learning-Based_Quality_Control_for_Cardiac_MR_Images.pdf https://openaccess.city.ac.uk/id/eprint/22768/1/2018-Learning-Based_Quality_Control_for_Cardiac_MR_Images.pdf] under the license cc-by

* [http://xplorestaging.ieee.org/ielx7/42/8704227/08519790.pdf?arnumber=8519790 http://xplorestaging.ieee.org/ielx7/42/8704227/08519790.pdf?arnumber=8519790],
: [http://dx.doi.org/10.1109/tmi.2018.2878509 http://dx.doi.org/10.1109/tmi.2018.2878509] under the license http://creativecommons.org/licenses/by/4.0

* [https://dblp.uni-trier.de/db/journals/corr/corr1803.html#abs-1803-09354 https://dblp.uni-trier.de/db/journals/corr/corr1803.html#abs-1803-09354],
: [https://ieeexplore.ieee.org/abstract/document/8519790 https://ieeexplore.ieee.org/abstract/document/8519790],
: [https://arxiv.org/abs/1803.09354 https://arxiv.org/abs/1803.09354],
: [https://openaccess.city.ac.uk/id/eprint/22768 https://openaccess.city.ac.uk/id/eprint/22768],
: [https://arxiv.org/pdf/1803.09354 https://arxiv.org/pdf/1803.09354],
: [https://spiral.imperial.ac.uk/bitstream/10044/1/65595/2/qc_journal.pdf https://spiral.imperial.ac.uk/bitstream/10044/1/65595/2/qc_journal.pdf],
: [https://www.ncbi.nlm.nih.gov/pubmed/30403623 https://www.ncbi.nlm.nih.gov/pubmed/30403623],
: [https://spiral.imperial.ac.uk/handle/10044/1/65595 https://spiral.imperial.ac.uk/handle/10044/1/65595],
: [https://export.arxiv.org/pdf/1803.09354 https://export.arxiv.org/pdf/1803.09354],
: [https://doi.org/10.1109/TMI.2018.2878509 https://doi.org/10.1109/TMI.2018.2878509],
: [https://arxiv-vanity.com/papers/1803.09354 https://arxiv-vanity.com/papers/1803.09354],
: [http://ui.adsabs.harvard.edu/abs/2018arXiv180309354T/abstract http://ui.adsabs.harvard.edu/abs/2018arXiv180309354T/abstract],
: [http://export.arxiv.org/abs/1803.09354 http://export.arxiv.org/abs/1803.09354],
: [https://aps.arxiv.org/abs/1803.09354 https://aps.arxiv.org/abs/1803.09354],
: [https://uk.arxiv.org/abs/1803.09354 https://uk.arxiv.org/abs/1803.09354],
: [https://xplqa30.ieee.org/document/8519790 https://xplqa30.ieee.org/document/8519790],
: [https://ru.arxiv.org/abs/1803.09354 https://ru.arxiv.org/abs/1803.09354],
: [https://academic.microsoft.com/#/detail/2794958817 https://academic.microsoft.com/#/detail/2794958817]

← Older revision	Revision as of 11:34, 15 February 2021
(No difference)

Tarroni et al 2019a - Revision history

Scipediacontent: Scipediacontent moved page Draft Content 943040862 to Tarroni et al 2019a

Scipediacontent: Created page with " == Abstract == The effectiveness of a cardiovascular magnetic resonance (CMR) scan depends on the ability of the operator to correctly tune the acquisition parameters to the..."