Deform-Mamba Network for MRI Super-Resolution

TL;DR

This paper introduces Deform-Mamba, a novel MRI super-resolution architecture that effectively captures local and global image features while reducing computational costs, leading to high-quality image reconstruction.

Contribution

The paper presents a new Deform-Mamba network with a dual-branch encoder and multi-view context module, enhancing feature extraction for MRI super-resolution.

Findings

Achieves competitive performance on IXI and fastMRI datasets.

Effectively explores local and global image information.

Reduces computational cost compared to traditional methods.

Abstract

In this paper, we propose a new architecture, called Deform-Mamba, for MR image super-resolution. Unlike conventional CNN or Transformer-based super-resolution approaches which encounter challenges related to the local respective field or heavy computational cost, our approach aims to effectively explore the local and global information of images. Specifically, we develop a Deform-Mamba encoder which is composed of two branches, modulated deform block and vision Mamba block. We also design a multi-view context module in the bottleneck layer to explore the multi-view contextual content. Thanks to the extracted features of the encoder, which include content-adaptive local and efficient global information, the vision Mamba decoder finally generates high-quality MR images. Moreover, we introduce a contrastive edge loss to promote the reconstruction of edge and contrast related content. Quantitative and qualitative experimental results indicate that our approach on IXI and fastMRI datasets achieves competitive performance.