Motivation: In this study, the primary objective is to reduce the safety factor required for maintaining patient safety while improving SAR estimation accuracy. Goal(s): A machine-learning-based model will provide precise SAR predictions for various human models and body sizes, enabling safer and more efficient MRI scanning. Approach: A CycleGAN model was trained with simulated data generated from an 8-channel volume transmit array, including whole-body electromagnetic field data. Additionally, SAR values were analyzed statistically under 100 randomly transmitted conditions to determine an optimal safety factor by comparing true and predicted values Results: A safety factor of 1.0666 was demonstrated with successive accuracy improvements. Impact: This study offers more accurate SAR predictions that support safe, efficient MRI operations without excessive safety margins using machine learning methods. The model's precision increases patient safety and reduces scan times in high-field MRI procedures.
Hayat et al. (Tue,) studied this question.