Although the macroscopic equations of motion for nuclear magnetic resonance have been described and modeled for decades by the Bloch equations, limited human intuition of their nonlinear dynamics is an obstacle to fully exploiting the vast parameter space of MR pulse sequences. Here we recast the general problem of pulse sequence development as a game of perfect information, and propose an approach to optimize game play with a Bayesian derivative of reinforcement learning within a MRI physics simulation environment. We demonstrate an AI agent learning a canonical pulse sequence (gradient echo) and generating non-intuitive pulse sequences approximating Fourier spatial encoding.
This abstract and the presentation materials are available to members only; a login is required.