Video Compressive Sensing for Dynamic MRI

Jianing Shi, Wotao Yin, Aswin Sankaranarayanan, Richard Baraniuk

Technical report


We present a video compressive sensing framework, termed kt-CSLDS, to accelerate the image acquisition process of dynamic magnetic resonance imaging (MRI). We are inspired by a state-of-the-art model for video compressive sensing that utilizes a lin- ear dynamical system (LDS) to model the motion. Given compressive measurements, the state sequence of an LDS can be first estimated using system identification tech- niques. We then reconstruct the observation matrix using a joint structured sparsity assumption. In particular, we minimize an objective function with a mixture of wavelet sparsity and joint sparsity within the observation matrix. We derive an efficient convex optimization algorithm through alternating direction method of multipliers (ADMM), and provide a theoretical guarantee for global convergence. We demonstrate the per- formance of our approach for video compressive sensing, in terms of reconstruction accuracy. We also investigate the impact of various sampling strategies. We apply this framework to accelerate the acquisition process of dynamic MRI and show it achieves the best reconstruction accuracy with the least computational time compared with existing algorithms in the literature.

The image below depicts the architecture of the kt-CSLDS model.


Several numerical tests were done in the paper to compare the proposed algorithm to the existing ones. One set of results is



J. Shi, W. Yin, A. Sankaranarayanan, R. Baraniuk, Video Compressive Sensing for Dynamic MRI, arXiv:1401.7715, 2014.

« Back