Premium
Machine learning RF shimming: Prediction by iteratively projected ridge regression
Author(s) -
Ianni Julianna D.,
Cao Zhipeng,
Grissom William A.
Publication year - 2018
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.27192
Subject(s) - shim (computing) , homogeneity (statistics) , electromagnetic coil , radio frequency , computer science , physics , artificial intelligence , nuclear magnetic resonance , algorithm , machine learning , medicine , telecommunications , quantum mechanics , erectile dysfunction
Purpose To obviate online slice‐by‐slice RF shim optimization and reduceB 1 +mapping requirements for patient‐specific RF shimming in high‐field magnetic resonance imaging. Theory and Methods RF Shim Prediction by Iteratively Projected Ridge Regression (PIPRR) predicts patient‐specific, SAR‐efficient RF shims with a machine learning approach that merges learning with training shim design. To evaluate it, a set ofB 1 +maps was simulated for 100 human heads for a 24‐element coil at 7T. Features were derived from tissue masks and the DC Fourier coefficients of the coils’B 1 +maps in each slice, which were used for kernelized ridge regression prediction of SAR‐efficient RF shim weights. Predicted shims were compared to directly designed shims, circularly polarized mode, and nearest‐neighbor shims predicted using the same features. Results PIPRR predictions had 87% and 13% lowerB 1 +coefficients of variation compared to circularly polarized mode and nearest‐neighbor shims, respectively, and achieved homogeneity and SAR similar to that of directly designed shims. Predictions were calculated in 4.92 ms on average. Conclusion PIPRR predicted uniform, SAR‐efficient RF shims, and could save a large amount ofB 1 +mapping and computation time in RF‐shimmed ultra‐high field magnetic resonance imaging.