EUVIMEDEUVIMED entdecken
Crossref

A K‐space guided invertible diffusion model for accelerating MRI reconstruction

Jiayu Yang, Feng Zhu, Zhipeng Yu, Yuhang Chen, Jie Ding

Medical Physics · 2026-11 · 53 (11)

DOI: 10.1002/mp.70765 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Medical Physics, online erschienen am 14.11.2026. Verfasst von Jiayu Yang und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer, Jiangsu University of Science and Technology, Zhenjiang, China. Hauptthemen laut MEDLINE: Image Processing, Computer-Assisted, Magnetic Resonance Imaging. Die Arbeit nennt 36 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Magnetic resonance imaging (MRI), a core technology in clinical medical diagnosis, has long aimed to balance imaging quality and acquisition efficiency. Traditional MRI techniques, limited by the Nyquist‐Shannon sampling theorem, are faced with significant challenges in high‐acceleration‐factor imaging, including artifacts and detail loss due to sparse sampling. While existing parallel imaging, compressed sensing, and deep learning methods have improved reconstruction efficiency, they have limitations such as insufficient integration of electromagnetic physics models with biological tissue prior information, inadequate high‐frequency information recovery, and high computational complexity.

Purpose

To address these persistent limitations in high‐acceleration MRI reconstruction, this study proposes a K‐space guided invertible diffusion model (KG‐IDM) designed to improve reconstruction fidelity.

Methods

KG‐IDM enables high‐quality MRI reconstruction through Cross‐domain Feature Injection (CFI) with Adaptive Channel‐Spatial Interaction Attention (ACSIA) for multi‐source feature alignment, and a K‐space Guided Bimodal Spectral Enhancement Network (KG‐BSEN) for dual‐path frequency–spatial enhancement. This framework jointly exploits spatial and spectral representations, enhancing cross‐domain feature consistency and reducing reconstruction artifacts.

Results

Experiments on the fastMRI single‐coil knee dataset using retrospectively undersampled complex‐valued k‐space at , , , and acceleration show that KG‐IDM achieves the highest mean PSNR and SSIM and the lowest mean NMSE relative to all nine baseline methods. At acceleration, KG‐IDM achieves dB PSNR, SSIM, and NMSE. At , it achieves dB, , and , respectively. Paired volume‐level Wilcoxon tests over 199 evaluation volumes showed statistically significant favorable differences in all 108 comparisons, with all Holm‐adjusted .

Conclusions

By integrating measurement‐guided cross‐domain feature fusion with frequency–spatial refinement, KG‐IDM consistently improves reconstruction fidelity across the evaluated acceleration factors and provides a promising framework for accelerated MRI reconstruction.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Image Processing, Computer-AssistedMagnetic Resonance ImagingDiffusionHumans

Stichwörter der Autor:innen

MRI accelerationimage reconstructioninvertible diffusion model

Autor:innen und Institutionen

  • School of Computer, Jiangsu University of Science and Technology, Zhenjiang, China.

Zitieren

APA

Yang, J., Zhu, F., Yu, Z., Chen, Y., & Ding, J. (2026). A K‐space guided invertible diffusion model for accelerating MRI reconstruction. Medical Physics, 53(11). https://doi.org/10.1002/mp.70765

Vancouver

Yang J, Zhu F, Yu Z, Chen Y, Ding J. A K‐space guided invertible diffusion model for accelerating MRI reconstruction. Medical Physics. 2026;53(11). doi:10.1002/mp.70765

BibTeX
@article{Yang2026,
  author = {Yang, Jiayu and Zhu, Feng and Yu, Zhipeng and Chen, Yuhang and Ding, Jie},
  title = {A K‐space guided invertible diffusion model for accelerating MRI reconstruction},
  journal = {Medical Physics},
  year = {2026},
  volume = {53},
  number = {11},
  doi = {10.1002/mp.70765}
}
Kostenlos starten →