SmartPulse, a machine learning approach for calibration-free dynamic RF shimming: preliminary study in a clinical environment

Abstract : Purpose: A calibration-free pulse design method is introduced to alleviate B$_1$$^+$ artifacts in clinical routine with parallel transmission at high field, dealing with significant inter-subject variability, found for instance in the abdomen. Theory and Methods: From a dual-transmit 3T scanner, a database of B$_1$$^+$ and off resonance abdominal maps from 50 subjects was first divided into three clusters based on mutual affinity between their respective tailored kT-points pulses. For each cluster, a kT-points pulse was computed, minimizing normalized root-mean-square flip angle (FA) deviations simultaneously for all subjects comprised in it. Using 30 additional subjects’ field distributions, a machine learning classifier was trained on this 80-labelled-subject database to recognize the best pulse from the three ones available, relying only on patient features accessible from the preliminary localizer sequence present in all protocols. This so-called SmartPulse process was experimentally tested on an additional 53-subject set and compared with other pulse types: vendor’s hard calibration-free dual excitation, tailored static RF shimming, universal and tailored kT-points pulses. Results: SmartPulse outperformed both calibration-free approaches. Tailored static RF shimming yielded similar FA homogeneity for most patients but broke down for some while SmartPulse remained robust. Although FA homogeneity was systematically better with tailored kT-points, the difference was barely noticeable on in-vivo images. Conclusion: The proposed method paves the way towards an efficient trade-off between tailored and universal pulse design approaches for large inter-subject variability. With no need for on-line field mapping or pulse design, it can fit seamlessly into a clinical protocol.