Benchmarking learned non-Cartesian k-space trajectories and reconstruction networks

01/27/2022
by   Chaithya G R, et al.
0

We benchmark the current existing methods to jointly learn non-Cartesian k-space trajectory and reconstruction: PILOT, BJORK, and compare them with those obtained from the recently developed generalized hybrid learning (HybLearn) framework. We present the advantages of using projected gradient descent to enforce MR scanner hardware constraints as compared to using added penalties in the cost function. Further, we use the novel HybLearn scheme to jointly learn and compare our results through a retrospective study on fastMRI validation dataset.

READ FULL TEXT

page 5

page 6

research
06/04/2016

Provable Burer-Monteiro factorization for a class of norm-constrained matrix problems

We study the projected gradient descent method on low-rank matrix proble...
research
09/06/2017

CNN-Based Projected Gradient Descent for Consistent Image Reconstruction

We present a new method for image reconstruction which replaces the proj...
research
11/30/2022

Generalized Deep Learning-based Proximal Gradient Descent for MR Reconstruction

The data consistency for the physical forward model is crucial in invers...
research
08/23/2023

Non-ergodic linear convergence property of the delayed gradient descent under the strongly convexity and the Polyak-Łojasiewicz condition

In this work, we establish the linear convergence estimate for the gradi...
research
09/07/2012

Learning Model-Based Sparsity via Projected Gradient Descent

Several convex formulation methods have been proposed previously for sta...
research
03/16/2023

Stochastic gradient descent for linear inverse problems in variable exponent Lebesgue spaces

We consider a stochastic gradient descent (SGD) algorithm for solving li...

Please sign up or login with your details

Forgot password? Click here to reset