Data-Driven Learning of MRI Sampling Pattern

Data-Driven Learning of MRI Sampling Pattern

Author: 
Marcelo Wust Zibetti, PhD


MRI Poisson disk sampling pattern is shown on the left. MRI sampling pattern optimized for compressed sensing reconstructions with low-rank regularization (CS-LR) is shown on the right. Each sampling pattern has an acceleration factor (AF) of 18.

 

We are making available a MATLAB implementation of a machine learning algorithm to learn the optimal sampling pattern for MRI [2].

In a forthcoming publication, “Data-Driven Learning of MRI Sampling Pattern,” now in review at IEEE Transactions on Medical Imaging, we propose a data-driven approach for learning an efficacious sampling pattern in accelerated parallel MRI. The approach is applicable when two conditions are met:

  1. A set of fully sampled Cartesian k-space data of a specific anatomy is available for training;
  2. An image reconstruction for undersampled data or direct k-space recovery method for parallel MRI that allows a free choice of the sampling pattern is used.

The learned SP allows fast data collection by capturing the key learned data that result in minor deterioration of reconstruction quality. Our proposed approach has low computational cost and fast convergence, enabling the use of large datasets to optimize large sampling patterns—important features in high-resolution 3D-MRI, quantitative MRI, and dynamic MRI applications. In the related publication, we describe four parallel MRI reconstruction methods based on low rankness and sparsity, each used with two different datasets. Our findings indicate that the sampling pattern learned by our method results in scan time nearly twice as fast as that obtained with variable density and Poisson disk sampling pattern for the same level of error.


Related Publication

M. V. W. Zibetti, G. T. Herman, and R. R. Regatte, “Data-Driven Learning of MRI Sampling Pattern,” under review IEEE Transactions on Medical Imaging, 2020.

References

[1] M. V. W. Zibetti, E. S. Helou, R. R. Regatte, and G. T. Herman, “Monotone FISTA with variable acceleration for compressed sensing magnetic resonance imaging.” IEEE Trans. Comput. Imaging. vol. 5, no. 1, pp. 109–119, Mar. 2019.

[2] M. V. W. Zibetti, G. T. Herman, and R. R. Regatte, “Data-driven design of the sampling pattern for compressed sensing and low rank reconstructions on parallel MRI of human knee joint.” ISMRM Workshop on Data Sampling and Image Reconstruction, 2020.

 

PLEASE NOTE: The software available on this page is provided free of charge and comes without any warranty. CAI²R and the NYU School of Medicine do not take any liability for problems or damage of any kind resulting from the use of the files provided. Operation of the software is solely at the user's own risk. The software developments provided are not medical products and must not be used for making diagnostic decisions.

The software is provided for non-commercial, academic use only. Usage or distribution of the software for commercial purpose is prohibited. All rights belong to the author (Marcelo Wust Zibetti, PhD) and the NYU School of Medicine. If you use the software for academic work, please give credit to the author in publications and cite the related publications.

2 + 6 =
Solve this simple math problem and enter the result. E.g. for 1+3, enter 4.

Important: If you don't receive the download link within few minutes, please check the SPAM folder of your e-mail account.

 

Sponsors

Philanthropic Support

We gratefully acknowledge generous support for radiology research at NYU Langone Health from:
 
• The Big George Foundation
• Bernard and Irene Schwartz

Go to top