Learning Sampling and Model-Based Signal Recovery for Compressed Sensing MRI

Abstract

Compressed sensing (CS) MRI relies on adequate undersampling of the k-space to accelerate the acquisition without compromising image quality. Consequently, the design of optimal sampling patterns for these k-space coefficients has received significant attention, with many CS MRI methods exploiting variable-density probability distributions. Realizing that an optimal sampling pattern may depend on the downstream task (e.g. image reconstruction, segmentation, or classification), we here propose joint learning of both task-adaptive k-space sampling and a subsequent model-based proximal-gradient recovery network. The former is enabled through a probabilistic generative model that leverages the Gumbel-softmax relaxation to sample across trainable beliefs while maintaining differentiability. The proposed combination of a highly flexible sampling model and a model-based (sampling-adaptive) image reconstruction network facilitates exploration and efficient training, yielding improved MR image quality compared to other sampling baselines.

References in corpus (5)

• Adam: A Method for Stochastic Optimization
• The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables
• fastMRI: An Open Dataset and Benchmarks for Accelerated MRI
• Neural Proximal Gradient Descent for Compressive Imaging
• Self-Supervised Deep Active Accelerated MRI

Cited by in corpus (9)

• B-spline Parameterized Joint Optimization of Reconstruction and K-space Trajectories (BJORK) for Accelerated 2D MRI
• PUERT: Probabilistic Under-sampling and Explicable Reconstruction Network for CS-MRI
• Efficient approximation of Jacobian matrices involving a non-uniform fast Fourier transform (NUFFT)
• Artificial Intelligence for Neuro MRI Acquisition: A Review
• Single-pass Object-adaptive Data Undersampling and Reconstruction for MRI
• Data and Physics driven Deep Learning Models for Fast MRI Reconstruction: Fundamentals and Methodologies
• AutoSamp: Autoencoding k-space Sampling via Variational Information Maximization for 3D MRI
• Experimental design for MRI by greedy policy search
• Gradient-Based Learning of Discrete Structured Measurement Operators for Signal Recovery