Efficient approximation of Jacobian matrices involving a non-uniform fast Fourier transform (NUFFT)

Abstract

There is growing interest in learning Fourier domain sampling strategies (particularly for magnetic resonance imaging, MRI) using optimization approaches. For non-Cartesian sampling patterns, the system models typically involve non-uniform FFT (NUFFT) operations. Commonly used NUFFT algorithms contain frequency domain interpolation, which is not differentiable with respect to the sampling pattern, complicating the use of gradient methods. This paper describes an efficient and accurate approach for computing approximate gradients involving NUFFTs. Multiple numerical experiments validated the improved accuracy and efficiency of the proposed approximation. As an application to computational imaging, the NUFFT Jacobians were used to optimize non-Cartesian MRI sampling trajectories via data-driven stochastic optimization. Specifically, the sampling patterns were learned with respect to various model-based reconstruction algorithms, including quadratic regularized reconstruction and compressed sensing-based reconstruction. The proposed approach enables sampling optimization for image sizes that are infeasible with standard auto-differentiation methods due to memory limits. The synergistic acquisition and reconstruction lead to remarkably improved image quality. In fact, we show that model-based image reconstruction (MBIR) methods with suitably optimized imaging parameters can perform nearly as well as CNN-based methods.

arXiv comment12 pages, 5 figures

References in corpus (13)

• Adam: A Method for Stochastic Optimization
• MoDL: Model Based Deep Learning Architecture for Inverse Problems
• fastMRI: An Open Dataset and Benchmarks for Accelerated MRI
• The Complex Gradient Operator and the CR-Calculus
• J-MoDL: Joint Model-Based Deep Learning for Optimized Sampling and Reconstruction
• B-spline Parameterized Joint Optimization of Reconstruction and K-space Trajectories (BJORK) for Accelerated 2D MRI
• OEDIPUS: An Experiment Design Framework for Sparsity-Constrained MRI
• Automated Design of Pulse Sequences for Magnetic Resonance Fingerprinting using Physics-Inspired Optimization
• Adaptive Restart of the Optimized Gradient Method for Convex Optimization
• CG-SENSE revisited: Results from the first ISMRM reproducibility challenge
• Learning Sampling and Model-Based Signal Recovery for Compressed Sensing MRI
• Joint Angular Refinement and Reconstruction for Single-Particle Cryo-EM
• Stochastic Optimization of 3D Non-Cartesian Sampling Trajectory (SNOPY)

Cited by in corpus (5)

• B-spline Parameterized Joint Optimization of Reconstruction and K-space Trajectories (BJORK) for Accelerated 2D MRI
• Artificial Intelligence for Neuro MRI Acquisition: A Review
• AutoSamp: Autoencoding k-space Sampling via Variational Information Maximization for 3D MRI
• Bayesian Optimization of Sampling Densities in MRI
• On the complexity of nonsmooth automatic differentiation