Compressed sensing dynamic cardiac cine MRI using learned spatiotemporal dictionary

In dynamic cardiac cine magnetic resonance imaging, the spatiotemporal resolution is limited by the low imaging speed. Compressed sensing (CS) theory has been applied to improve the imaging speed and thus the spatiotemporal resolution. In this paper, we propose a novel technique that employs a patch-based 3-D spatiotemporal dictionary for sparse representations of dynamic image sequence in the CS framework. Specifically, the dynamic image sequence is divided into overlapping patches along both the spatial and temporal directions. The dictionary is used to provide flexible sparse expressions for these patches. The underlying optimization problem is solved by variable splitting and the alternating direction method with multiplier. Experimental results based on in vivo cardiac data demonstrate that the proposed method is able to accelerate cardiac cine imaging by a factor up to 8 and outperforms the existing state-of-the-art CS methods at high accelerations. The method is expected to be useful in dynamic imaging with a higher spatiotemporal resolution.