Self-Prior Guided Mamba-UNet Networks for Medical Image Super-Resolution

TL;DR

This paper introduces SMamba-UNet, a novel medical image super-resolution network that combines Mamba-based self-priors with a U-Net architecture, effectively capturing long-range dependencies with reduced computational cost.

Contribution

The paper proposes a self-prior guided Mamba-UNet that leverages Mamba models and an improved 2D-Selective-Scan module to enhance global feature extraction in medical image super-resolution.

Findings

Outperforms state-of-the-art methods on IXI and fastMRI datasets.

Effectively models long-range dependencies with linear complexity.

Enhances super-resolution quality with self-prior learning and directional feature fusion.

Abstract

In this paper, we propose a self-prior guided Mamba-UNet network (SMamba-UNet) for medical image super-resolution. Existing methods are primarily based on convolutional neural networks (CNNs) or Transformers. CNNs-based methods fail to capture long-range dependencies, while Transformer-based approaches face heavy calculation challenges due to their quadratic computational complexity. Recently, State Space Models (SSMs) especially Mamba have emerged, capable of modeling long-range dependencies with linear computational complexity. Inspired by Mamba, our approach aims to learn the self-prior multi-scale contextual features under Mamba-UNet networks, which may help to super-resolve low-resolution medical images in an efficient way. Specifically, we obtain self-priors by perturbing the brightness inpainting of the input image during network training, which can learn detailed texture and brightness information that is beneficial for super-resolution. Furthermore, we combine Mamba with Unet network to mine global features at different levels. We also design an improved 2D-Selective-Scan (ISS2D) module to divide image features into different directional sequences to learn long-range dependencies in multiple directions, and adaptively fuse sequence information to enhance super-resolved feature representation. Both qualitative and quantitative experimental results demonstrate that our approach outperforms current state-of-the-art methods on two public medical datasets: the IXI and fastMRI.