Keywords: AI/ML Software, Safety, Machine learning, MR safety, SAR, UHF
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.
How to access this content:
For one year after publication, abstracts and videos are only open to registrants of this annual meeting. Registrants should use their existing login information. Non-registrant access can be purchased via the ISMRM E-Library.
After one year, current ISMRM & ISMRT members get free access to both the abstracts and videos. Non-members and non-registrants must purchase access via the ISMRM E-Library.
After two years, the meeting proceedings (abstracts) are opened to the public and require no login information. Videos remain behind password for access by members, registrants and E-Library customers.
Keywords