Automatic determination of the regularization weighting for wavelet-based compressed sensing MRI reconstructions.

Gabriel Varela-Mattatall Corey Allan BaronRavi S Menon

Published in: Magnetic resonance in medicine (2021)

Our main finding is an automatic, fast, noniterative, and robust procedure to determine the regularization weighting. The impact of this method is to enable prospective and tuning-free wavelet-based compressed sensing reconstructions.

Keyphrases

deep learning
convolutional neural network
machine learning
neural network
image quality
magnetic resonance imaging
contrast enhanced
minimally invasive
molecularly imprinted
mass spectrometry