MRI zero: fully automated invention of MRI sequences using supervised learning

摘要

We present a supervised learning approach to automatically generate MR sequences and corresponding reconstruction from scratch without providing sequence programming rules. New framework is tested in human brain measurement at 3T. Subjects and Methods: The entire scanning and reconstruction process is simulated end-to-end as a fully differentiable concatenated sequence of tensor operations. Each tensor operation from the stack implements: RF events (RFE) (i.e. flip angles and phases), gradient moment events (GME) in x and y, delay times, and a weighting for an ADC, acting on the input model spin system (given in terms of PD, T_1 and T_2, and DB0). At the sequence learning step, we use Adam[1] optimizer to find the sequence parameters given the loss function specified with respect to data fidelity and SAR cost terms.