Joonsung Lee1, Matthias Gebhardt2,
1Electrical engineering and computer
science, Massachusetts Institute of Technology, Cambridge, MA, United States;
2Siemens Healthcare, Erlangen, Germany; 3Department of
Radiology, A. A. Martinos Center for Biomedical Imaging, Cambridge, MA,
United States; 4Harvard-MIT Division of Health Sciences and
Technology, Massachusetts Institute of Technology, Cambridge, MA, United
States
The
model compression method for local SAR esitmation dramatically decreases the
complexity of the prediction of the local SAR calculation and enables the
incorporation of local SAR constaints in pTX MLS RF design.