Predict and Eliminate EMI Signals for RF Shielding-Free MRI via Simultaneous Sensing and Deep Learning

Abstract

All clinical magnetic resonance imaging (MRI) scanners require bulky and enclosed RF shielding rooms to prevent external electromagnetic interference (EMI) signals during data acquisition, and quality electronics inside shielding room (i.e., with minimal EMI emission). A novel strategy of simultaneous EMI sensing and deep learning is presented to model, predict and remove EMI signals from acquired MRI signals, completely eliminating the need for RF shielding. We demonstrated that this method worked robustly for various EMI sources from both external environments and internal scanner electronics, producing final image SNRs highly comparable to those obtained using a fully enclosed RF shielding cage in 0.055 Tesla and 1.5 Tesla MRI experiments.