MRSaiFE: towards the real-time prediction of SAR in 3T and 7T MR RF coils - a feasibility study with 10 body models

Abstract

Significant RF power deposition in the body causing local specific absorption rate (SAR) in the form of hotspots is an important safety concern at 3T (128 MHz) and, even more so, at 7T (298 MHz). In this work, we expand the proof-of-concept of artificial intelligence based real-time MRI safety prediction software (MRSaiFE) to 10 body models. We show that SAR patterns can be predicted with a mean squared error (MSE) of less than 1% and a structural similarity index of above 90% for 7T brain and above 85% for 3T body MRI.

Deep learning‐based local SAR prediction using B1 maps and structural MRI of the head for parallel transmission at 7 T

“…Thus, a total of four encoding and decoding stages were assumed to be enough in addition to empirical findings reported earlier. 45 Adaptive moment estimation 46 optimizer with an initial learning rate of 10 −4 , a staircase exponential decay rate of 98% for every 10 epochs, and default momentum values (i.e., β1 = 0.85, β2 = 0.999, and 𝜀 = 10 −3 ) were implemented by using the built-in classes in TensorFlow.…”