DARCS: Memory-Efficient Deep Compressed Sensing Reconstruction for Acceleration of 3D Whole-Heart Coronary MR Angiography

TL;DR

This paper introduces DARCS, a memory-efficient deep compressed sensing method for 3D coronary MR angiography that improves reconstruction quality while significantly reducing memory requirements compared to existing methods.

Contribution

The paper proposes a novel sparsifying transform based on a pre-trained artifact estimation network, enabling efficient 3D reconstruction with less memory usage.

Findings

DARCS outperforms traditional and deep learning methods in reconstruction quality.

The method generalizes well across different undersampling rates and noise levels.

Memory usage is reduced to 63% of MoDL.

Abstract

Three-dimensional coronary magnetic resonance angiography (CMRA) demands reconstruction algorithms that can significantly suppress the artifacts from a heavily undersampled acquisition. While unrolling-based deep reconstruction methods have achieved state-of-the-art performance on 2D image reconstruction, their application to 3D reconstruction is hindered by the large amount of memory needed to train an unrolled network. In this study, we propose a memory-efficient deep compressed sensing method by employing a sparsifying transform based on a pre-trained artifact estimation network. The motivation is that the artifact image estimated by a well-trained network is sparse when the input image is artifact-free, and less sparse when the input image is artifact-affected. Thus, the artifact-estimation network can be used as an inherent sparsifying transform. The proposed method, named De-Aliasing Regularization based Compressed Sensing (DARCS), was compared with a traditional compressed sensing method, de-aliasing generative adversarial network (DAGAN), model-based deep learning (MoDL), and plug-and-play for accelerations of 3D CMRA. The results demonstrate that the proposed method improved the reconstruction quality relative to the compared methods by a large margin. Furthermore, the proposed method well generalized for different undersampling rates and noise levels. The memory usage of the proposed method was only 63% of that needed by MoDL. In conclusion, the proposed method achieves improved reconstruction quality for 3D CMRA with reduced memory burden.