Reconstruction of undersampled 3D non-Cartesian image-based navigators for coronary MRA using an unrolled deep learning model.

Mario O Malavé Corey Allan Baron Srivathsan P Koundinyan Christopher M SandinoFrank OngJoseph Y ChengDwight G Nishimura

Published in: Magnetic resonance in medicine (2020)

We have developed a deep neural network architecture to reconstruct undersampled 3D non-Cartesian VD cones iNAVs. Our approach decreases reconstruction time for 3D iNAVs, while preserving the accuracy of nonrigid motion information offered by them for correction.

Keyphrases

neural network
deep learning
coronary artery
coronary artery disease
artificial intelligence
convolutional neural network
machine learning
health information
healthcare
heart failure
high speed
computed tomography
mass spectrometry
magnetic resonance
high resolution