Enhanced MRI Reconstruction Network using Neural Architecture Search

TL;DR

This paper introduces an improved MRI reconstruction network that employs neural architecture search to automatically optimize its structure, resulting in superior performance over existing methods on public datasets.

Contribution

The paper proposes a novel heterogeneous neural network architecture for MRI reconstruction that uses differentiable NAS to select optimal operations, enhancing performance and addressing vanishing gradient issues.

Findings

Outperforms state-of-the-art MRI reconstruction methods

Evaluated on two public datasets with superior results

Uses NAS to automatically optimize network architecture

Abstract

The accurate reconstruction of under-sampled magnetic resonance imaging (MRI) data using modern deep learning technology, requires significant effort to design the necessary complex neural network architectures. The cascaded network architecture for MRI reconstruction has been widely used, while it suffers from the "vanishing gradient" problem when the network becomes deep. In addition, homogeneous architecture degrades the representation capacity of the network. In this work, we present an enhanced MRI reconstruction network using a residual in residual basic block. For each cell in the basic block, we use the differentiable neural architecture search (NAS) technique to automatically choose the optimal operation among eight variants of the dense block. This new heterogeneous network is evaluated on two publicly available datasets and outperforms all current state-of-the-art methods, which demonstrates the effectiveness of our proposed method.