Jong Chul Ye

Compressed sensing have been extensively investigated as a means to accelerate the MR acquisition by exploiting the redundancy in spatial domain.  In this presentation, I will first review the basic principle of compressed sensing and recent development.  Then, I will provide a unified view of the compressed sensing, parallel imaging and recent structured low-rank matrix approaches for accelerated MRI. More specifically, inspired by k-space interpolation methods, an annihilating filter based low-rank Hankel matrix approach (ALOHA) is proposed as a general framework for sparsity-driven k-space interpolation method which unifies pMRI and CS-MRI. This converts pMRI and CS-MRI to a k-space interpolation problem using a structured matrix completion. In addition, it provides an important link to the recent deep learning approaches for accelerated MRI.

Akira Yamamoto

Through these clinical MR images, we try to explain three key elements essential for compressed sensing. The first is sparsity, the second is random sampling, and the third is nonlinear iterative image reconstruction. Since all of these keywords are unfamiliar to clinicians, we will try a simple and intuitive explanation that clinicians can understand necessity of these three elements by using MR image obtained with compressed sensing.