Learning a variational network for reconstruction of accelerated MRI data.

ABSTRACT:

Purpose

To allow fast and high-quality reconstruction of clinical accelerated multi-coil MR data by learning a variational network that combines the mathematical structure of variational models with deep learning.

Theory and methods

Generalized compressed sensing reconstruction formulated as a variational model is embedded in an unrolled gradient descent scheme. All parameters of this formulation, including the prior model defined by filter kernels and activation functions as well as the data term weights, are learned during an offline training procedure. The learned model can then be applied online to previously unseen data.

Results

The variational network approach is evaluated on a clinical knee imaging protocol for different acceleration factors and sampling patter

SUBMITTER: Hammernik K 

PROVIDER: S-EPMC5902683 | biostudies-literature | 2018 Jun

REPOSITORIES: biostudies-literature