Premium
Automatic determination of the regularization weighting for wavelet‐based compressed sensing MRI reconstructions
Author(s) -
VarelaMattatall Gabriel,
Baron Corey A.,
Me Ravi S.
Publication year - 2021
Publication title -
magnetic resonance in medicine
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.696
H-Index - 225
eISSN - 1522-2594
pISSN - 0740-3194
DOI - 10.1002/mrm.28812
Subject(s) - undersampling , weighting , wavelet , compressed sensing , regularization (linguistics) , computer science , artificial intelligence , iterative reconstruction , correlation coefficient , pattern recognition (psychology) , image quality , mathematics , algorithm , statistics , image (mathematics) , physics , acoustics
Purpose To present a method that automatically, rapidly, and in a noniterative manner determines the regularization weighting for wavelet‐based compressed sensing reconstructions. This method determines level‐specific regularization weighting factors from the wavelet transform of the image obtained from zero‐filling in k‐space. Methods We compare reconstruction results obtained by our method, λ auto , to the ones obtained by the L‐curve, λ Lcurve , and the minimum NMSE, λ NMSE . The comparisons are done using in vivo data; then, simulations are used to analyze the impact of undersampling and noise. We use NMSE, Pearson’s correlation coefficient, high‐frequency error norm, and structural similarity as reconstruction quality indices. Results Our method, λ auto , provides improved reconstructed image quality to that obtained by λ Lcurve regardless of undersampling or SNR and comparable quality to λ NMSE at high SNR. The method determines the regularization weighting prospectively with negligible computational time. Conclusion 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.