Accelerating MR Imaging via Deep Chambolle-Pock Network

TL;DR

This paper introduces CP-net, a deep learning model derived from the Chambolle-Pock algorithm, to improve MRI reconstruction from undersampled data, outperforming existing methods in accuracy.

Contribution

The paper presents a novel deep network based on Chambolle-Pock algorithm for MR image reconstruction, addressing limitations of traditional compressed sensing methods.

Findings

CP-net achieves higher reconstruction accuracy than state-of-the-art methods.

It effectively learns parameters and proximal operators within the Chambolle-Pock framework.

The method generalizes well across different MR scanners.

Abstract

Compressed sensing (CS) has been introduced to accelerate data acquisition in MR Imaging. However, CS-MRI methods suffer from detail loss with large acceleration and complicated parameter selection. To address the limitations of existing CS-MRI methods, a model-driven MR reconstruction is proposed that trains a deep network, named CP-net, which is derived from the Chambolle-Pock algorithm to reconstruct the in vivo MR images of human brains from highly undersampled complex k-space data acquired on different types of MR scanners. The proposed deep network can learn the proximal operator and parameters among the Chambolle-Pock algorithm. All of the experiments show that the proposed CP-net achieves more accurate MR reconstruction results, outperforming state-of-the-art methods across various quantitative metrics.