Video Compressive Sensing for Dynamic MRI

TL;DR

This paper introduces kt-CSLDS, a novel video compressive sensing framework that accelerates dynamic MRI acquisition by modeling motion with a linear dynamical system and reconstructing images through structured sparsity, achieving high accuracy and efficiency.

Contribution

The paper proposes a new framework combining LDS modeling and structured sparsity for dynamic MRI, with an efficient convex optimization algorithm and theoretical convergence guarantees.

Findings

Achieves superior reconstruction accuracy in dynamic MRI

Reduces computational time compared to existing methods

Effectively models motion using linear dynamical systems

Abstract

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 linear dynamical system (LDS) to model the motion manifold. Given compressive measurements, the state sequence of an LDS can be first estimated using system identification techniques. 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 performance 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.