A motion-corrected deep-learning reconstruction framework for accelerating whole-heart magnetic resonance imaging in patients with congenital heart disease.

Andrew PhairAnastasia FotakiLina FelsnerThomas J FletcherHaikun QiRené M BotnarClaudia Prieto

Published in: Journal of cardiovascular magnetic resonance : official journal of the Society for Cardiovascular Magnetic Resonance (2024)

The MoCo-MoDL framework was applied to an adult CHD patient cohort, achieving good quality 3D whole-heart images from ∼2-minute scans with reconstruction times of ∼30 seconds.

Keyphrases

congenital heart disease
deep learning
convolutional neural network
heart failure
artificial intelligence
atrial fibrillation
computed tomography
case report
machine learning
optical coherence tomography
quality improvement
high speed
magnetic resonance
mass spectrometry