Experimental design for MRI by greedy policy search

Code

• github.com/Timsey/pg_mri
  OfficialIn paperpytorch★ 23
• github.com/yangpuPKU/L2SR-Learning-to-Sample-and-Reconstruct
  pytorch★ 9

Abstract

In today's clinical practice, magnetic resonance imaging (MRI) is routinely accelerated through subsampling of the associated Fourier domain. Currently, the construction of these subsampling strategies - known as experimental design - relies primarily on heuristics. We propose to learn experimental design strategies for accelerated MRI with policy gradient methods. Unexpectedly, our experiments show that a simple greedy approximation of the objective leads to solutions nearly on-par with the more general non-greedy approach. We offer a partial explanation for this phenomenon rooted in greater variance in the non-greedy objective's gradient estimates, and experimentally verify that this variance hampers non-greedy models in adapting their policies to individual MR images. We empirically show that this adaptivity is key to improving subsampling designs.

Tasks

Reproductions