cs.CVFeb 28, 2026

Direct low-field MRI super-resolution using undersampled k-space

Authors: Daniel Tweneboah Anyimadu, Mohammed M. Abdelsamea, Ahmed Karam Eldaly

Organizations: Department of Computer Science, University of Exeter, Exeter, United Kingdom · UCL Hawkes Institute, University College London, London, United Kingdom

Read PDF
Ask AI
Cite

Copy citation

DOINot available for this paper

Abstract

Low-field magnetic resonance imaging (MRI) provides affordable access to diagnostic imaging but suffers from prolonged acquisition and limited image quality. Accelerated imaging can be achieved with k-space undersampling, while super-resolution (SR) and image quality transfer (IQT) methods typically rely on spatial-domain post-processing. In this work, we propose a novel framework for reconstructing high-field MR like images directly from undersampled low-field k-space. Our approach employs a k-space dual channel U-Net that processes the real and imaginary components of undersampled k-space to restore missing frequency content. Experiments on low-field brain MRI demonstrate that our k-space-driven image enhancement consistently outperforms the counterpart spatial-domain method. Furthermore, reconstructions from undersampled k-space achieve image quality comparable to full k-space acquisitions. To the best of our knowledge, this is the first work that investigates low-field MRI SR/IQT directly from undersampled k-space.

Figures & tables

Figure 1: K-space dual channel U-Net for LF-MRI SR/IQT using undersampled k -space.
Figure 2: HF-MR test images, and pseudo-radial and cartesian undersampling binary masks at 50% and 30% sampling rates.
DomainMetric100%50%30%
Pseudo-radial Sampling
InterpolationSSIM0.8473 ±\pm 0.01970.4946 ±\pm 0.03030.3859 ±\pm 0.0153
 PSNR25.41 ±\pm 1.679221.64 ±\pm 0.868321.42 ±\pm 0.6350
IQT SpatialSSIM0.9499 ±\pm 0.01160.9422 ±\pm 0.01160.9330 ±\pm 0.0137
 PSNR33.85 ±\pm 2.147031.45 ±\pm 1.827830.54 ±\pm 1.9291
IQT K-SpaceSSIM0.9505 ±\pm 0.01180.9480 ±\pm 0.01220.9406 ±\pm 0.0141
Table 1: Average and standard deviation PSNR and SSIM measures for k -space and spatial domain IQT at different sampling rates. Bold indicates best results.
Figure 3: Reconstruction results of the LF images, and IQT in the spatial and k -space domains, at different pseudo-radial under-sampling rates using two test images.
Figure 4: Absolute error maps between HF images in Fig. 2 , and the reconstructions in Fig. 3 at different pseudo-radial under-sampling rates: ∣HF−LF∣|\text{HF}-\text{LF}| in row 1, ∣HF−IQT-spatial∣|\text{HF}-\text{IQT-spatial}| in rows 2 and ∣HF−IQT-k-space∣|\text{HF}-\text{IQT-\emph{k}-space}| in row 3.

Explore similar work

CardsList

  1. Low-Field Magnetic Resonance Image Enhancement using Undersampled k-Space

    Mar 14, 2026Daniel Tweneboah Anyimadu, Mohammed Abdalla, Mohammed M. Abdelsamea +1Magnetic Resonance ImagingMedical Image Super-Resolution

    Department of Computer Science, University of Exeter, United Kingdom · Neurology Department, Royal Devon and Exeter Hospital, Exeter, United Kingdom · UCL Hawkes Institute, Department of Computer Science, University College London, London, United Kingdom

  2. Low-Field Magnetic Resonance Image Quality Enhancement using Undersampled k-Space and Out-of-Distribution Generalisation

    Mar 14, 2026Daniel Tweneboah Anyimadu, Mohammed M. Abdelsamea, Ahmed Karam EldalyMagnetic Resonance ImagingAccelerated MRI Reconstruction

    Department of Computer Science, University of Exeter, Exeter, United Kingdom · UCL Hawkes Institute, Department of Computer Science, University College London, London, United Kingdom

  3. Variational Network with Wavelet-based UNET in Accelerated MRI Reconstruction from Under Sampled K-space Data

    Jun 13, 2026Yasir Arafat Prodhan, Shaikh Anowarul FattahU-NetWavelet Methods

    Department of Electrical and Electronic Engineering, Bangladesh University of Engineering and Technology, Dhaka, Bangladesh · This paper was produced by the IEEE Publication Technology Group. They are in Piscataway, NJ.