Data-Driven Regularization Parameter Selection in Dynamic MRI

  title={Data-Driven Regularization Parameter Selection in Dynamic MRI},
  author={Matti Hanhela and Olli H. J. Gr{\"o}hn and Mikko I. Kettunen and Kati Niinim{\"a}ki and Marko Vauhkonen and Ville Kolehmainen},
  journal={Journal of Imaging},
In dynamic MRI, sufficient temporal resolution can often only be obtained using imaging protocols which produce undersampled data for each image in the time series. This has led to the popularity of compressed sensing (CS) based reconstructions. One problem in CS approaches is determining the regularization parameters, which control the balance between data fidelity and regularization. We propose a data-driven approach for the total variation regularization parameter selection, where… 

Figures from this paper



Parameter selection in dynamic contrast-enhanced magnetic resonance tomography

This work considers the image reconstruction problem of sparsely sampled dynamic contrast-enhanced (DCE) magnetic resonance imaging (MRI) and selects the spatial regularization parameter using the S-curve, leaving the temporal regularizationparameter as the only free parameter in the reconstruction problem.

Non-Cartesian MRI Reconstruction With Automatic Regularization Via Monte-Carlo SURE

This work develops a data-driven regularization parameter adjustment scheme that minimizes an estimate [based on the principle of Stein's unbiased risk estimate (SURE)] of a suitable weighted squared-error measure in k-space.

Dynamic MRI reconstruction from undersampled data with an anatomical prescan

A new variational approach is proposed for the reconstruction of subsampled dynamic MR data, which combines smooth, temporal regularization with spatial total variation regularization and furthermore uses the infimal convolution of two total variation Bregman distances to incorporate structural a-priori information from an anatomical MRI prescan into the reconstructed of the dynamic image sequence.

Multiresolution Parameter Choice Method for Total Variation Regularized Tomography

It is rigorously proven that the TV norms of the reconstructions converge with any choice of regularization parameter, and it seems to automatically adapt to the desired resolution and noise level.

Sparse MRI: The application of compressed sensing for rapid MR imaging

Practical incoherent undersampling schemes are developed and analyzed by means of their aliasing interference and demonstrate improved spatial resolution and accelerated acquisition for multislice fast spin‐echo brain imaging and 3D contrast enhanced angiography.

An Optimal Radial Profile Order Based on the Golden Ratio for Time-Resolved MRI

A constant azimuthal profile spacing, based on the Golden Ratio, is investigated as optimal for image reconstruction from an arbitrary number of profiles in radial MRI.

Pseudo-Polar Fourier Transform-Based Compressed Sensing MRI

The proposed PP trajectory-based CS MRI methods achieves a more accurate reconstruction with respect to image detail/edge preservation and artifact suppression and provides a practical and accurate CS-based rapid imaging method for clinical applications.

An in vivo MRI Template Set for Morphometry, Tissue Segmentation, and fMRI Localization in Rats

A new in vivo rat T2 MRI template set, comprising average images of both intensity and shape, obtained via non-linear registration and confirmed that, like with previous templates, forepaw and hindpaw fMRI activations can be correctly localized in the expected atlas structure.

Compressed sensing MRI: a review of the clinical literature.

Compressed sensing (CS) is a method for accelerating MRI acquisition by acquiring less data through undersampling of k-space, which has the potential to mitigate the time-intensiveness of MRI.

Computational optimization methods for large-scale inverse problems

A novel method for selecting the Bayesian prior parameter is proposed, based on a priori information about the sparsity of the unknown function, which seems promising and adaptable for several practical applications.