Fully Automated Myocardial Strain Estimation from Cardiovascular MRI-tagged Images Using a Deep Learning Framework in the UK Biobank.
Edward FerdianAvan SuinesiaputraKenneth FungNay AungElena LukaschukAhmet BarutcuEdd MacleanJose PaivaSteffen E PetersenStefan NeubauerSteffen Erhard PetersenAlistair A YoungPublished in: Radiology. Cardiothoracic imaging (2020)
The fully automated combined RNN and CNN framework for analysis of myocardial strain enabled unbiased strain evaluation in a high-throughput workflow, with similar ability to distinguish impairment due to diabetes, hypertension, and previous heart attack.Published under a CC BY 4.0 license. Supplemental material is available for this article.
Keyphrases
- deep learning
- high throughput
- convolutional neural network
- machine learning
- artificial intelligence
- left ventricular
- type diabetes
- blood pressure
- cardiovascular disease
- magnetic resonance imaging
- heart failure
- single cell
- contrast enhanced
- cross sectional
- atrial fibrillation
- skeletal muscle
- magnetic resonance
- insulin resistance
- metabolic syndrome
- clinical evaluation
- arterial hypertension