EUVIMEDObjevte EUVIMED
Open access · CC BY 4.0

Image space formalism of convolutional neural networks for k‐space interpolation

P Dawood iD, F Breuer, M Gram iD, I Homolya iD, P M Jakob iD, M Zaiss iD, M Blaimer iD

Magnetic Resonance in Medicine · 2025-12 · 94 (6) · 2680-2701

DOI: 10.1002/mrm.70002 ↗

At a glance

Journal article in Magnetic Resonance in Medicine, published online on 2025-08-05. Written by P Dawood and 6 co-authors. Institution: Experimental Physics 5, University of Würzburg, Würzburg, Germany. Major MEDLINE topics: Neural Networks, Computer, Image Processing, Computer-Assisted, Brain, Magnetic Resonance Imaging. Cited 2 times so far (Crossref); 51 references. The full text is freely available (open access, CC BY 4.0).

AbstraktSubjectsBibliografické údajeCiteRelated studies

Abstract (original language)

Purpose

Noise resilience in image reconstructions by scan‐specific robust artificial neural networks for k‐space interpolation (RAKI) is linked to nonlinear activations in k‐space. To gain a deeper understanding of this relationship, an image space formalism of RAKI is introduced for analyzing noise propagation analytically, identifying and characterizing image reconstruction features and to describe the role of nonlinear activations in a human‐readable manner. Theory and Methods The image space formalism for RAKI inference is employed by expressing nonlinear activations in k‐space as element‐wise multiplications with activation masks, which transform into convolutions in image space. Jacobians of the de‐aliased, coil‐combined image relative to the aliased coil images can be expressed algebraically; thus, the noise amplification is quantified analytically (g‐factor maps). We analyze the role of nonlinearity for noise resilience by controlling the degree of nonlinearity in the reconstruction model via the negative slope parameter in leaky ReLU.

Results

The analytical g‐factor maps correspond with those obtained from Monte Carlo simulations and from an auto differentiation approach for in vivo brain images. Apparent blurring and contrast loss artifacts are identified as implications of enhanced noise resilience. These residual artifacts can be traded against noise resilience by adjusting the degree of nonlinearity in the model (Tikhonov‐like regularization) in case of limited training data. The inspection of image space activations reveals an autocorrelation pattern leading to a potential center artifact.

Conclusion

The image space formalism of RAKI provides the means for analytical quantitative noise‐propagation analysis and human‐readable visualization of the effects of the nonlinear activation functions in k‐space.

Subjects

MeSH terms (MEDLINE)

Neural Networks, ComputerImage Processing, Computer-AssistedBrainMagnetic Resonance ImagingHumansAlgorithmsMonte Carlo MethodComputer SimulationPhantoms, ImagingSignal-To-Noise RatioConvolutional Neural Networks

Author keywords

GRAPPARAKIconvolutional neural networkexplainable AIg‐factornoise propagationparallel imaging

Authors and institutions

  • Experimental Physics 5, University of Würzburg, Würzburg, Germany.
  • Institute of Neuroradiology, University Hospital Erlangen, Erlangen, Germany.
  • Magnetic Resonance and X-ray Imaging Department, Fraunhofer Institute for Integrated Circuits IIS, Division Development Center X-Ray Technology, Würzburg, Germany.
  • Department of Internal Medicine I, University Hospital Würzburg, Würzburg, Germany.
  • Molecular and Cellular Imaging, Comprehensive Heart Failure Center, University Hospital Würzburg, Würzburg, Germany.

ORCID profiles: P Dawood, M Gram, I Homolya, P M Jakob, M Zaiss, M Blaimer

Cite

APA

Dawood, P., Breuer, F., Gram, M., Homolya, I., Jakob, P. M., Zaiss, M., & Blaimer, M. (2025). Image space formalism of convolutional neural networks for k‐space interpolation. Magnetic Resonance in Medicine, 94(6), 2680-2701. https://doi.org/10.1002/mrm.70002

Vancouver

Dawood P, Breuer F, Gram M, Homolya I, Jakob PM, Zaiss M, et al. Image space formalism of convolutional neural networks for k‐space interpolation. Magnetic Resonance in Medicine. 2025;94(6):2680-2701. doi:10.1002/mrm.70002

BibTeX
@article{Dawood2025,
  author = {Dawood, P and Breuer, F and Gram, M and Homolya, I and Jakob, P M and Zaiss, M and Blaimer, M},
  title = {Image space formalism of convolutional neural networks for k‐space interpolation},
  journal = {Magnetic Resonance in Medicine},
  year = {2025},
  volume = {94},
  number = {6},
  pages = {2680--2701},
  doi = {10.1002/mrm.70002}
}
Start for free →