| Title: | Fully Automated Myocardial Strain Estimation from Cardiovascular MRI-tagged Images Using a Deep Learning Framework in the UK Biobank |
| Journal: | Radiol Cardiothorac Imaging |
| Published: | 27 Feb 2020 |
| Pubmed: | https://pubmed.ncbi.nlm.nih.gov/32715298/ |
| DOI: | https://doi.org/10.1148/ryct.2020190032 |
Publication 1890
WARNING: the interactive features of this website use CSS3, which your browser does not support. To use the full features of this website, please update your browser.
Abstract
Contact for queries: Alistair.Young@kcl.ac.uk or s.e.petersen@qmul.ac.ukThis returned dataset contains CMR data on the first ~5000 participants who attended the imaging enhancement visit.
This category contains derived data from cardiovascular magnetic resonance (CMR) short-axis tagged images acquired in the basal, mid and apical levels of the left ventricle. Myocardial strain measurements were calculated via semi-automated analyses using CIMTag2D software (CIMTag2D v.8.1.5, Auckland MRI Research Group, New Zealand). Manual adjustments of the tagging grid were made in the end-diastolic (first frame), end-systolic (manually defined at the mid slice), early diastolic phase (rapid filling phase) and also in the last frame.
Returned data contains:
1) Image derived phenotypes:
- End-systolic circumferential strain (apex)
- End-systolic circumferential strain (base)
- End-systolic circumferential strain (mid)
- End-systolic torsion
- End-systolic torsion rate
2) Quality control scores of CMR tagging images and analysis
1 Author
- Ferdian E et al.
1 Application
| Application ID | Title |
|---|---|
| 2964 | Description of cardiovascular phenotype in the UK Biobank population based on cardiovascular magnetic resonance and carotid ultrasound |
Enabling scientific discoveries that improve human health