EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Regularized Joint Reconstruction and Slab Combination for Accelerated Three‐Dimensional Multi‐Slab Diffusion‐Weighted Imaging Using Multi‐Scale Energy Models

Reza Ghorbani iD, Jyothi Rikhab Chand iD, Chu-Yu Lee iD, Mathews Jacob iD, Merry Mani iD

Magnetic Resonance in Medicine · 2026

DOI: 10.1002/mrm.70512 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Magnetic Resonance in Medicine, 2026. Verfasst von Reza Ghorbani und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Electrical and Computer Engineering, University of Virginia, Charlottesville, Virginia, USA. Hauptthemen laut MEDLINE: Diffusion Magnetic Resonance Imaging, Imaging, Three-Dimensional, Brain, Image Processing, Computer-Assisted. Die Arbeit nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NIH HHS, NCRR NIH HHS, NIBIB NIH HHS.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Purpose

To jointly reconstruct high‐resolution diffusion‐weighted volumes and eliminate slab‐boundary artifacts while preserving fine anatomical detail from undersampled 3D multi‐slab k‐space acquisitions.

Methods

A bilinear forward model was formulated to describe the 3D multi‐slab acquisition, treating the image volume and slab excitation profiles as joint variables. A maximum a posteriori framework optimized a cost function with a Gaussian data‐fidelity term, a CNN‐based deep energy prior guiding accelerated recovery, and a quadratic regularization term anchoring the slab profiles to an initial estimate. The energy‐based prior models the negative log distribution of clean diffusion‐weighted images, while its gradient guides the accelerated reconstruction toward the artifact‐free distribution. The resulting non‐convex problem was solved via alternating minimization, where the image volume was updated through a majorize–minimize scheme with conjugate gradient optimization, and slab profiles were estimated through regularized least‐squares optimization.

Results

The proposed Energy‐based Profile Encoding (EPEN) framework substantially reduced slab‐boundary artifacts compared with conventional slab‐boundary correction approaches. Improved structural consistency and contrast preservation were achieved across multiple acceleration factors and slab configurations.

Conclusion

EPEN enables robust joint 3D multi‐slab diffusion MRI reconstruction with slab profile correction within an alternating optimization framework using deep energy‐based image priors.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Diffusion Magnetic Resonance ImagingImaging, Three-DimensionalBrainImage Processing, Computer-AssistedHumansAlgorithmsArtifactsPhantoms, ImagingConvolutional Neural Networks

Stichwörter der Autor:innen

3D multi‐slab diffusion MRIboundary artifact correctionmulti‐scale energy model

Autor:innen und Institutionen

  • Department of Electrical and Computer Engineering, University of Virginia, Charlottesville, Virginia, USA.
  • Department of Radiology, University of Iowa, Iowa City, Iowa, USA.
  • Department of Radiology and Medical Imaging, and Department of Biomedical Engineering, University of Virginia, Charlottesville, Virginia, USA.

ORCID-Profile: Reza Ghorbani, Jyothi Rikhab Chand, Chu-Yu Lee, Mathews Jacob, Merry Mani

Förderung

  • NIH HHS
  • NCRR NIH HHS
  • NIBIB NIH HHS
  • National Institute of Biomedical Imaging and Bioengineering
  • National Institutes of Health

Zitieren

APA

Ghorbani, R., Rikhab Chand, J., Lee, C. Y., Jacob, M., & Mani, M. (2026). Regularized Joint Reconstruction and Slab Combination for Accelerated Three‐Dimensional Multi‐Slab Diffusion‐Weighted Imaging Using Multi‐Scale Energy Models. Magnetic Resonance in Medicine. https://doi.org/10.1002/mrm.70512

Vancouver

Ghorbani R, Rikhab Chand J, Lee CY, Jacob M, Mani M. Regularized Joint Reconstruction and Slab Combination for Accelerated Three‐Dimensional Multi‐Slab Diffusion‐Weighted Imaging Using Multi‐Scale Energy Models. Magnetic Resonance in Medicine. 2026. doi:10.1002/mrm.70512

BibTeX
@article{Ghorbani2026,
  author = {Ghorbani, Reza and Rikhab Chand, Jyothi and Lee, Chu-Yu and Jacob, Mathews and Mani, Merry},
  title = {Regularized Joint Reconstruction and Slab Combination for Accelerated Three‐Dimensional Multi‐Slab Diffusion‐Weighted Imaging Using Multi‐Scale Energy Models},
  journal = {Magnetic Resonance in Medicine},
  year = {2026},
  doi = {10.1002/mrm.70512}
}
Kostenlos starten →