Towards multi-sequence MR image recovery from undersampled k-space data

Undersampled MR image recovery has been widely studied with Deep Learning methods as a post-processing step for accelerating MR acquisition. In this paper, we aim to optimize multi-sequence MR image recovery from undersampled k-space data under an overall time constraint. We first formulate it as a {\em constrained optimization} problem and show that finding the optimal sampling strategy for all sequences and the optimal recovery model for such sampling strategy is {\em combinatorial} and hence computationally prohibitive. To solve this problem, we propose a {\em blind recovery model} that simultaneously recovers multiple sequences, and an efficient approach to find proper combination of sampling strategy and recovery model. Our experiments demonstrate that the proposed method outperforms sequence-wise recovery, and sheds light on how to decide the undersampling strategy for sequences within an overall time budget.