Control of a simulated MRI scanner with deep reinforcement learning

Magnetic resonance imaging (MRI) is a highly versatile and widely used clinical imaging tool. The content of MRI images is controlled by an acquisition sequence, which coordinates the timing and magnitude of the scanner hardware activations, which shape and coordinate the magnetisation within the body, allowing a coherent signal to be produced. The use of deep reinforcement learning (DRL) to control this process, and determine new and efficient acquisition strategies in MRI, has not been explored. Here, we take a first step into this area, by using DRL to control a virtual MRI scanner, and framing the problem as a game that aims to efficiently reconstruct the shape of an imaging phantom using partially reconstructed magnitude images. Our findings demonstrate that DRL successfully completed two key tasks: inducing the virtual MRI scanner to generate useful signals and interpreting those signals to determine the phantom's shape. This proof-of-concept study highlights the potential of DRL in autonomous MRI data acquisition, shedding light on the suitability of DRL for complex tasks, with limited supervision, and without the need to provide human-readable outputs.