Abstract
PurposeTailored parallel-transmit (pTx) pulses produce uniform excitation profiles at 7 T, but are sensitive to head motion. A potential solution is real-time pulse redesign. A deep learning framework is proposed to estimate pTx B1+ distributions following within-slice motion, which can then be used for tailored pTx pulse redesign.MethodsUsing simulated data, conditional generative adversarial networks were trained to predict B1+ distributions in the head following a displacement. Predictions were made for two virtual body models that were not included in training. Predicted maps were compared with groundtruth (simulated, following motion) B1+ maps. Tailored pTx pulses were designed using B1+ maps at the original position (simulated, no motion) and evaluated using simulated B1+ maps at displaced position (ground-truth maps) to quantify motion-related excitation error. A second pulse was designed using predicted maps (also evaluated on ground-truth maps) to investigate improvement offered by the proposed method.ResultsPredicted B1+ maps corresponded well with ground-truth maps. Error in predicted maps was lower than motion-related error in 99% and 67% of magnitude and phase evaluations, respectively. Worst-case flip-angle normalized RMS error due to motion (76% of target flip angle) was reduced by 59% when pulses were redesigned using predicted maps.ConclusionWe propose a framework for predicting B1+ maps online with deep neural networks. Predicted maps can then be used for real-time tailored pulse redesign, helping to overcome head motion–related error in pTx.
Highlights
Parallel transmission of RF pulses through independently controlled channels can help to overcome B1 nonuniformity seen in the head at 7 T,1,2 when tailored pulses are used.[3]
Geometrical and compositional differences between human subjects are partly addressed in alternative, nontailored approaches such as universal pulses (UPs),[7,8] SmartPulse,[9] and fast online-customized pTx pulses.[10]
An underlying assumption is that the range in head geometry and composition across human subjects is relatively constrained, implying that B+1 distributions are constrained
Summary
Parallel transmission (pTx) of RF pulses through independently controlled channels can help to overcome B1 nonuniformity seen in the head at 7 T,1,2 when tailored pulses are used.[3]. The database approach is problematic in cases in which an individual is an outlier with respect to anatomies represented in the database These methods do not address the dependence of B+1 on load position, leading to unpredictable pulse performance in cases of different initial subject positioning[11] and/or within-scan head motion.12–1 4 The former is often overlooked, whereas the latter is commonly reported.[15] Large head movements (exceeding 20 mm/degree) often occur among certain clinical populations,[16,17] elderly,[18] and pediatric[19,20] subjects. Specific absorption rate (SAR) distribution and associated tissue heating are sensitive to motion, and are especially so in pTx due to constructive interference between channels’ electric fields.28–30 Peak local SAR can exceed safety limits when head motion occurs in pTx simulations29—a critical issue that cannot be addressed retrospectively. We observe peak 10-g averaged local SAR for both pulses following motion
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
