PAS-Mamba: Phase-Amplitude-Spatial State Space Model for MRI Reconstruction

• URL: http://arxiv.org/abs/2601.14530v1
• Date: Tue, 20 Jan 2026 22:53:35 GMT
• Title: PAS-Mamba: Phase-Amplitude-Spatial State Space Model for MRI Reconstruction
• Authors: Xiaoyan Kui, Zijie Fan, Zexin Ji, Qinsong Li, Hao Xu, Weixin Si, Haodong Xu, Beiji Zou,
• Abstract summary: We propose a framework that decouples phase and magnitude modeling in the frequency domain and combines it with image-domain features for better reconstruction.<n>Experiments on the IXI and fastMRI knee datasets show that PAS-Mamba consistently outperforms state of the art reconstruction methods.
• Score: 12.528008672425173
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Joint feature modeling in both the spatial and frequency domains has become a mainstream approach in MRI reconstruction. However, existing methods generally treat the frequency domain as a whole, neglecting the differences in the information carried by its internal components. According to Fourier transform theory, phase and amplitude represent different types of information in the image. Our spectrum swapping experiments show that magnitude mainly reflects pixel-level intensity, while phase predominantly governs image structure. To prevent interference between phase and magnitude feature learning caused by unified frequency-domain modeling, we propose the Phase-Amplitude-Spatial State Space Model (PAS-Mamba) for MRI Reconstruction, a framework that decouples phase and magnitude modeling in the frequency domain and combines it with image-domain features for better reconstruction. In the image domain, LocalMamba preserves spatial locality to sharpen fine anatomical details. In frequency domain, we disentangle amplitude and phase into two specialized branches to avoid representational coupling. To respect the concentric geometry of frequency information, we propose Circular Frequency Domain Scanning (CFDS) to serialize features from low to high frequencies. Finally, a Dual-Domain Complementary Fusion Module (DDCFM) adaptively fuses amplitude phase representations and enables bidirectional exchange between frequency and image domains, delivering superior reconstruction. Extensive experiments on the IXI and fastMRI knee datasets show that PAS-Mamba consistently outperforms state of the art reconstruction methods.

Related papers

• SpectralMamba-UNet: Frequency-Disentangled State Space Modeling for Texture-Structure Consistent Medical Image Segmentation [14.42559964239819]
  We propose SpectralMamba-UNet to decouple the learning of structural and textural information in the spectral domain.<n> Experiments on five public benchmarks demonstrate consistent improvements across diverse modalities and segmentation targets.
  arXiv  Detail & Related papers  (2026-02-26T15:17:42Z)
• Freqformer: Image-Demoiréing Transformer via Efficient Frequency Decomposition [83.40450475728792]
  We present Freqformer, a Transformer-based framework specifically designed for image demoir'eing through targeted frequency separation.<n>Our method performs an effective frequency decomposition that explicitly splits moir'e patterns into high-frequency spatially-localized textures and low-frequency scale-robust color distortions.<n>Experiments on various demoir'eing benchmarks demonstrate that Freqformer achieves state-of-the-art performance with a compact model size.
  arXiv  Detail & Related papers  (2025-05-25T12:23:10Z)
• PAD: Phase-Amplitude Decoupling Fusion for Multi-Modal Land Cover Classification [49.37555541088792]
  Phase-Amplitude Decoupling (PAD) is a frequency-aware framework that separates phase (modality-shared) and amplitude (modality-complementary) components.<n>This work establishes a new paradigm for physics-aware multi-modal fusion in remote sensing.
  arXiv  Detail & Related papers  (2025-04-27T07:21:42Z)
• Exploiting Frequency Correlation for Hyperspectral Image Reconstruction [21.71115793248267]
  Deep priors have emerged as potent methods in hyperspectral image (HSI) reconstruction. We propose a Hyperspectral Frequency Correlation (HFC) prior rooted in in-depth statistical frequency analyses of existent HSI datasets. We then establish the frequency domain learning composed of a Spectral-wise self-Attention of Frequency (SAF) and a Spectral-spatial Interaction of Frequency (SIF)
  arXiv  Detail & Related papers  (2024-06-02T09:36:37Z)
• A Dual Domain Multi-exposure Image Fusion Network based on the Spatial-Frequency Integration [57.14745782076976]
  Multi-exposure image fusion aims to generate a single high-dynamic image by integrating images with different exposures. We propose a novelty perspective on multi-exposure image fusion via the Spatial-Frequency Integration Framework, named MEF-SFI. Our method achieves visual-appealing fusion results against state-of-the-art multi-exposure image fusion approaches.
  arXiv  Detail & Related papers  (2023-12-17T04:45:15Z)
• Unified Frequency-Assisted Transformer Framework for Detecting and Grounding Multi-Modal Manipulation [109.1912721224697]
  We present the Unified Frequency-Assisted transFormer framework, named UFAFormer, to address the DGM4 problem. By leveraging the discrete wavelet transform, we decompose images into several frequency sub-bands, capturing rich face forgery artifacts. Our proposed frequency encoder, incorporating intra-band and inter-band self-attentions, explicitly aggregates forgery features within and across diverse sub-bands.
  arXiv  Detail & Related papers  (2023-09-18T11:06:42Z)
• Neural Spherical Harmonics for structurally coherent continuous representation of diffusion MRI signal [0.3277163122167433]
  We present a novel way to model diffusion magnetic resonance imaging (dMRI) datasets, that benefits from the structural coherence of the human brain. Current methods model the dMRI signal in individual voxels, disregarding the intervoxel coherence that is present. We use a neural network to parameterize a spherical harmonics series to represent the dMRI signal of a single subject from the Human Connectome Project dataset.
  arXiv  Detail & Related papers  (2023-08-16T08:28:01Z)
• Global k-Space Interpolation for Dynamic MRI Reconstruction using Masked Image Modeling [10.74920257710449]
  In dynamic Magnetic Imaging (MRI), k-space is typically undersampled due to limited scan time. We propose a novel Transformer-based k-space Global Interpolation Network, termed k-GIN. Our k-GIN learns global dependencies among low- and high-frequency components of 2D+t k-space and uses it to interpolate unsampled data.
  arXiv  Detail & Related papers  (2023-07-24T10:20:14Z)
• DONet: Dual-Octave Network for Fast MR Image Reconstruction [98.04121143761017]
  The Dual-Octave Network (DONet) is capable of learning multi-scale spatial-frequency features from both the real and imaginary components of MR data. Our framework provides three appealing benefits.
  arXiv  Detail & Related papers  (2021-05-12T21:41:02Z)
• Dual-Octave Convolution for Accelerated Parallel MR Image Reconstruction [75.35200719645283]
  We propose the Dual-Octave Convolution (Dual-OctConv), which is capable of learning multi-scale spatial-frequency features from both real and imaginary components. By reformulating the complex operations using octave convolutions, our model shows a strong ability to capture richer representations of MR images.
  arXiv  Detail & Related papers  (2021-04-12T10:51:05Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.