A Deep Error Correction Network for Compressed Sensing MRI

TL;DR

This paper introduces a deep error correction network that enhances compressed sensing MRI reconstructions by learning to correct errors from existing algorithms, significantly improving image quality.

Contribution

The paper proposes a novel deep error correction network (DECN) that integrates with existing CS-MRI algorithms to improve reconstruction accuracy through learned error correction.

Findings

DECN significantly outperforms existing CS-MRI algorithms.

The error correction CNN effectively reduces reconstruction errors.

Experimental results demonstrate improved diagnostic image quality.

Abstract

Compressed sensing for magnetic resonance imaging (CS-MRI) exploits image sparsity properties to reconstruct MRI from very few Fourier k-space measurements. The goal is to minimize any structural errors in the reconstruction that could have a negative impact on its diagnostic quality. To this end, we propose a deep error correction network (DECN) for CS-MRI. The DECN model consists of three parts, which we refer to as modules: a guide, or template, module, an error correction module, and a data fidelity module. Existing CS-MRI algorithms can serve as the template module for guiding the reconstruction. Using this template as a guide, the error correction module learns a convolutional neural network (CNN) to map the k-space data in a way that adjusts for the reconstruction error of the template image. Our experimental results show the proposed DECN CS-MRI reconstruction framework can considerably improve upon existing inversion algorithms by supplementing with an error-correcting CNN.