Flexible Alignment Super-Resolution Network for Multi-Contrast MRI

TL;DR

This paper introduces FASR-Net, a novel multi-contrast MRI super-resolution network that effectively aligns features across different scales and improves image quality, outperforming existing methods on benchmark datasets.

Contribution

The paper proposes a flexible alignment module with two components for handling scale differences in multi-contrast MRI super-resolution, and a fusion module for better feature integration.

Findings

FASR-Net outperforms state-of-the-art methods on FastMRI and IXI datasets.

The S-A and M-A modules effectively address scale mismatches in MRI images.

The CHPF module enhances feature fusion, improving image quality.

Abstract

Magnetic resonance imaging plays an essential role in clinical diagnosis by acquiring the structural information of biological tissue. Recently, many multi-contrast MRI super-resolution networks achieve good effects. However, most studies ignore the impact of the inappropriate foreground scale and patch size of multi-contrast MRI, which probably leads to inappropriate feature alignment. To tackle this problem, we propose the Flexible Alignment Super-Resolution Network (FASR-Net) for multi-contrast MRI Super-Resolution. The Flexible Alignment module of FASR-Net consists of two modules for feature alignment. (1) The Single-Multi Pyramid Alignment(S-A) module solves the situation where low-resolution (LR) images and reference (Ref) images have different scales. (2) The Multi-Multi Pyramid Alignment(M-A) module solves the situation where LR and Ref images have the same scale. Besides, we propose the Cross-Hierarchical Progressive Fusion (CHPF) module aiming at fusing the features effectively, further improving the image quality. Compared with other state-of-the-art methods, FASR-net achieves the most competitive results on FastMRI and IXI datasets. Our code will be available at \href{https://github.com/yimingliu123/FASR-Net}{https://github.com/yimingliu123/FASR-Net}.