Efficient Complex-Valued Vision Transformers for MRI Classification Directly from k-Space

• URL: http://arxiv.org/abs/2601.18392v1
• Date: Mon, 26 Jan 2026 11:50:52 GMT
• Title: Efficient Complex-Valued Vision Transformers for MRI Classification Directly from k-Space
• Authors: Moritz Rempe, Lukas T. Rotkopf, Marco Schlimbach, Helmut Becker, Fabian Hörst, Johannes Haubold, Philipp Dammann, Kevin Kröninger, Jens Kleesiek,
• Abstract summary: Deep learning applications in Magnetic Resonance Imaging (MRI) predominantly operate on reconstructed magnitude images.<n>Standard neural network architectures rely on local operations (convolutions or grid-patches) that are ill-suited for the global, non-local nature of raw frequency-domain (k-Space) data.<n>We propose a novel complex-valued Vision Transformer (kViT) designed to perform classification directly on k-Space data.
• Score: 4.973425214325723
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Deep learning applications in Magnetic Resonance Imaging (MRI) predominantly operate on reconstructed magnitude images, a process that discards phase information and requires computationally expensive transforms. Standard neural network architectures rely on local operations (convolutions or grid-patches) that are ill-suited for the global, non-local nature of raw frequency-domain (k-Space) data. In this work, we propose a novel complex-valued Vision Transformer (kViT) designed to perform classification directly on k-Space data. To bridge the geometric disconnect between current architectures and MRI physics, we introduce a radial k-Space patching strategy that respects the spectral energy distribution of the frequency-domain. Extensive experiments on the fastMRI and in-house datasets demonstrate that our approach achieves classification performance competitive with state-of-the-art image-domain baselines (ResNet, EfficientNet, ViT). Crucially, kViT exhibits superior robustness to high acceleration factors and offers a paradigm shift in computational efficiency, reducing VRAM consumption during training by up to 68$\times$ compared to standard methods. This establishes a pathway for resource-efficient, direct-from-scanner AI analysis.

Related papers

• Knowledge-Informed Neural Network for Complex-Valued SAR Image Recognition [51.03674130115878]
  We introduce the Knowledge-Informed Neural Network (KINN), a lightweight framework built upon a novel "compression-aggregation-compression" architecture.<n>KINN establishes a state-of-the-art in parameter-efficient recognition, offering exceptional generalization in data-scarce and out-of-distribution scenarios.
  arXiv  Detail & Related papers  (2025-10-23T07:12:26Z)
• K-Syn: K-space Data Synthesis in Ultra Low-data Regimes [0.7817545394809559]
  This letter focuses on feature-level modeling in the frequency domain, enabling stable and rich generation even with ultra low-data regimes.<n>We integrate k-space data across time frames with multiple fusion strategies to steer and further optimize the generative trajectory.<n> Experimental results demonstrate that the proposed method possesses strong generative ability in low-data regimes.
  arXiv  Detail & Related papers  (2025-09-04T12:25:05Z)
• Efficient Visual State Space Model for Image Deblurring [99.54894198086852]
  Convolutional neural networks (CNNs) and Vision Transformers (ViTs) have achieved excellent performance in image restoration.<n>We propose a simple yet effective visual state space model (EVSSM) for image deblurring.<n>The proposed EVSSM performs favorably against state-of-the-art methods on benchmark datasets and real-world images.
  arXiv  Detail & Related papers  (2024-05-23T09:13:36Z)
• Frequency-Assisted Mamba for Remote Sensing Image Super-Resolution [49.902047563260496]
  We develop the first attempt to integrate the Vision State Space Model (Mamba) for remote sensing image (RSI) super-resolution. To achieve better SR reconstruction, building upon Mamba, we devise a Frequency-assisted Mamba framework, dubbed FMSR. Our FMSR features a multi-level fusion architecture equipped with the Frequency Selection Module (FSM), Vision State Space Module (VSSM), and Hybrid Gate Module (HGM)
  arXiv  Detail & Related papers  (2024-05-08T11:09:24Z)
• Deep Learning-based MRI Reconstruction with Artificial Fourier Transform Network (AFTNet) [14.146848823672677]
  We introduce a unified complex-valued deep learning framework-Artificial Fourier Transform Network (AFTNet)<n>AFTNet can be readily used to solve image inverse problems in domain transformation.<n>We show that AFTNet achieves superior accelerated MRI reconstruction compared to existing approaches.
  arXiv  Detail & Related papers  (2023-12-18T02:50:45Z)
• 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)
• Unsupervised Domain Transfer with Conditional Invertible Neural Networks [83.90291882730925]
  We propose a domain transfer approach based on conditional invertible neural networks (cINNs) Our method inherently guarantees cycle consistency through its invertible architecture, and network training can efficiently be conducted with maximum likelihood. Our method enables the generation of realistic spectral data and outperforms the state of the art on two downstream classification tasks.
  arXiv  Detail & Related papers  (2023-03-17T18:00:27Z)
• LWGNet: Learned Wirtinger Gradients for Fourier Ptychographic Phase Retrieval [14.588976801396576]
  We propose a hybrid model-driven residual network that combines the knowledge of the forward imaging system with a deep data-driven network. Unlike other conventional unrolling techniques, LWGNet uses fewer stages while performing at par or even better than existing traditional and deep learning techniques. This improvement in performance for low-bit depth and low-cost sensors has the potential to bring down the cost of FPM imaging setup significantly.
  arXiv  Detail & Related papers  (2022-08-08T17:22:54Z)
• K-Space Transformer for Fast MRIReconstruction with Implicit Representation [39.04792898427536]
  We propose a Transformer-based framework for processing sparsely sampled MRI signals in k-space. We adopt an implicit representation of spectrogram, treating spatial coordinates as inputs, and dynamically query the partially observed measurements. To strive a balance between computational cost and reconstruction quality, we build a hierarchical structure with low-resolution and high-resolution decoders respectively.
  arXiv  Detail & Related papers  (2022-06-14T16:06:15Z)
• Cross-Modality High-Frequency Transformer for MR Image Super-Resolution [100.50972513285598]
  We build an early effort to build a Transformer-based MR image super-resolution framework. We consider two-fold domain priors including the high-frequency structure prior and the inter-modality context prior. We establish a novel Transformer architecture, called Cross-modality high-frequency Transformer (Cohf-T), to introduce such priors into super-resolving the low-resolution images.
  arXiv  Detail & Related papers  (2022-03-29T07:56:55Z)
• Learning Frequency-aware Dynamic Network for Efficient Super-Resolution [56.98668484450857]
  This paper explores a novel frequency-aware dynamic network for dividing the input into multiple parts according to its coefficients in the discrete cosine transform (DCT) domain. In practice, the high-frequency part will be processed using expensive operations and the lower-frequency part is assigned with cheap operations to relieve the computation burden. Experiments conducted on benchmark SISR models and datasets show that the frequency-aware dynamic network can be employed for various SISR neural architectures.
  arXiv  Detail & Related papers  (2021-03-15T12:54:26Z)

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.