k-Space Deep Learning for Accelerated MRI

Abstract

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.

Accepted to IEEE Transactions on Medical Imaging

References in corpus (2)

• Compressed Sensing MRI Reconstruction using a Generative Adversarial Network with a Cyclic Loss
• Understanding Geometry of Encoder-Decoder CNNs

Cited by in corpus (8)

• Non-Learning based Deep Parallel MRI Reconstruction (NLDpMRI)
• Reducing Uncertainty in Undersampled MRI Reconstruction with Active Acquisition
• k-t NEXT: Dynamic MR Image Reconstruction Exploiting Spatio-temporal Correlations
• Efficient B-mode Ultrasound Image Reconstruction from Sub-sampled RF Data using Deep Learning
• k-Space Deep Learning for Parallel MRI: Application to Time-Resolved MR Angiography
• Detection and Correction of Cardiac MR Motion Artefacts during Reconstruction from K-space
• Highly Accelerated Multishot EPI through Synergistic Machine Learning and Joint Reconstruction
• Real-time interactive magnetic resonance (MR) temperature imaging in both aqueous and adipose tissues using cascaded deep neural networks for MR-guided focused ultrasound surgery (MRgFUS)