# Compressed Sensing MRI via a Multi-scale Dilated Residual Convolution Network

## TL;DR

This paper introduces a multi-scale dilated residual convolutional network for MRI reconstruction that achieves faster processing and higher accuracy by effectively expanding receptive fields and preserving features, outperforming existing methods.

## Contribution

The paper proposes a novel multi-scale dilated residual network that balances high performance and efficiency for MRI reconstruction, extending its application to super-resolution tasks.

## Key findings

- Outperforms several existing algorithms in accuracy and visual quality
- Maintains stability under noisy conditions
- Effective in MRI super-resolution tasks

## Abstract

Magnetic resonance imaging (MRI) reconstruction is an active inverse problem which can be addressed by conventional compressed sensing (CS) MRI algorithms that exploit the sparse nature of MRI in an iterative optimization-based manner. However, two main drawbacks of iterative optimization-based CSMRI methods are time-consuming and are limited in model capacity. Meanwhile, one main challenge for recent deep learning-based CSMRI is the trade-off between model performance and network size. To address the above issues, we develop a new multi-scale dilated network for MRI reconstruction with high speed and outstanding performance. Comparing to convolutional kernels with same receptive fields, dilated convolutions reduce network parameters with smaller kernels and expand receptive fields of kernels to obtain almost same information. To maintain the abundance of features, we present global and local residual learnings to extract more image edges and details. Then we utilize concatenation layers to fuse multi-scale features and residual learnings for better reconstruction. Compared with several non-deep and deep learning CSMRI algorithms, the proposed method yields better reconstruction accuracy and noticeable visual improvements. In addition, we perform the noisy setting to verify the model stability, and then extend the proposed model on a MRI super-resolution task.