k-Space Deep Learning for Accelerated MRI
This addresses the need for faster MRI scans, which is crucial for medical imaging applications, and represents an incremental improvement by applying deep learning to a known compressed sensing framework.
The paper tackled the problem of accelerating MRI by interpolating missing k-space data, proposing a fully data-driven deep learning algorithm that consistently outperforms existing image-domain deep learning approaches in numerical experiments.
The annihilating filter-based low-rank Hankel matrix approach (ALOHA) is one of the state-of-the-art compressed sensing approaches that directly interpolates the missing k-space data using low-rank Hankel matrix completion. The success of ALOHA is due to the concise signal representation in the k-space domain thanks to the duality between structured low-rankness in the k-space domain and the image domain sparsity. Inspired by the recent mathematical discovery that links convolutional neural networks to Hankel matrix decomposition using data-driven framelet basis, here we propose a fully data-driven deep learning algorithm for k-space interpolation. Our network can be also easily applied to non-Cartesian k-space trajectories by simply adding an additional regridding layer. Extensive numerical experiments show that the proposed deep learning method consistently outperforms the existing image-domain deep learning approaches.