Numerical Evaluation of Image Homogeneity, Signal-to-Noise Ratio, and Specific Absorption Rate for Human Brain Imaging at 1.5, 3, 7, 10.5, and 14T in an 8-Channel Transmit/Receive Array

PurposeTo predict signal-to-noise ratio (SNR) trends and absorbed energy in magnetic resonance imaging (MRI) of the brain up to 14T. Materials and MethodsA human head in an eight-channel transmit/receive coil was simulated with Maxwell and Bloch equations to determine excitation homogeneity with radiofrequency (RF) shimming, image homogeneity, SNR, and absorbed energy in MRI from 1.5 to 14T considering realistic field distributions and relaxation properties. ResultsRF shimming alone achieved a standard deviation in excitation flip angle less than 10 degrees in mid-brain up to 14T, but produced a small region with low excitation on a lower slice. Current reconstruction methods may produce shading artifacts at 14T. SNR increases with a greater-than-linear rate for gradient recalled echo (GRE) sequences having short (2 msec) echo time (TE) and long relaxation time (TR) (approximate to 2.3-fold increase from 7T to 14T), but a less-than-linear rate if TE is 10 msec (approximate to 1.6-fold increase from 7T to 14T). Depending on the sequence, SNR per square root of imaging time may produce a less-than-linear increase with B-0. Whole-head absorbed energy shows a less-than-quadratic increase with B-0 (1.7-fold increase from 7T to 14T). ConclusionNumerical simulations indicate that with proper preparation and precautions, imaging of the human brain at up to 14T could be performed safely, with advantages in SNR. J. Magn. Reson. Imaging 2015;41:1432-1439. (c) 2014 Wiley Periodicals, Inc.