DH-Mamba：探索用于MRI重建的双域分层状态空间模型
DH-Mamba: Exploring Dual-domain Hierarchical State Space Models for MRI Reconstruction
AI总结：
本文提出一种用于MRI重建的双域分层Mamba模型，通过在k空间引入循环扫描、采用高效分层扫描策略及局部多样性增强模块，解决了长程遗忘与局部表示多样性受限问题，以更低计算成本显著优于现有方法。
摘要：
由于k空间中的显著欠采样，加速MRI重建提出了一个具有挑战性的病态逆问题。深度神经网络，如CNN和ViT，在该任务中显示出显著的性能提升，但同时也面临全局感受野与高效计算之间的困境。为此，本文探索了选择性状态空间模型（Mamba），这是一种具有线性复杂度的长程依赖建模新范式，旨在实现高效且有效的MRI重建。然而，将Mamba直接应用于MRI重建面临三个重大问题：(1) Mamba通常将2D图像沿行和列展平为不同的1D序列，破坏了k空间独特的频谱，使其在k空间学习中的潜力未得到探索。(2) 现有方法采用多方向长扫描在像素级展开图像，导致长程遗忘和高计算负担。(3) Mamba在处理空间变化内容时存在困难，导致局部表示的多样性有限。为了解决这些问题，我们从以下角度提出了一种用于MRI重建的双域分层Mamba：(1) 我们在k空间学习中开创性地引入了vision Mamba。为频谱展开定制了循环扫描，有利于k空间的全局建模。(2) 我们提出了一种在图像和k空间域均具有高效扫描策略的分层Mamba。它减轻了长程遗忘，并在效率和性能之间实现了更好的权衡。(3) 我们开发了一个局部多样性增强模块，以改善Mamba的空间变化表示。在三个公开数据集上进行了在各种欠采样模式下的MRI重建的大量实验。综合结果表明，我们的方法以更低的计算成本显著优于现有最先进的方法。
英文摘要：
The accelerated MRI reconstruction poses a challenging ill-posed inverse problem due to the significant undersampling in k-space. Deep neural networks, such as CNNs and ViTs, have shown substantial performance improvements for this task while encountering the dilemma between global receptive fields and efficient computation. To this end, this paper explores selective state space models (Mamba), a new paradigm for long-range dependency modeling with linear complexity, for efficient and effective MRI reconstruction. However, directly applying Mamba to MRI reconstruction faces three significant issues: (1) Mamba typically flattens 2D images into distinct 1D sequences along rows and columns, disrupting k-space's unique spectrum and leaving its potential in k-space learning unexplored. (2) Existing approaches adopt multi-directional lengthy scanning to unfold images at the pixel level, leading to long-range forgetting and high computational burden. (3) Mamba struggles with spatially-varying contents, resulting in limited diversity of local representations. To address these, we propose a dual-domain hierarchical Mamba for MRI reconstruction from the following perspectives: (1) We pioneer vision Mamba in k-space learning. A circular scanning is customized for spectrum unfolding, benefiting the global modeling of k-space. (2) We propose a hierarchical Mamba with an efficient scanning strategy in both image and k-space domains. It mitigates long-range forgetting and achieves a better trade-off between efficiency and performance. (3) We develop a local diversity enhancement module to improve the spatially-varying representation of Mamba. Extensive experiments are conducted on three public datasets for MRI reconstruction under various undersampling patterns. Comprehensive results demonstrate that our method significantly outperforms state-of-the-art methods with lower computational cost.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
