EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

DEEP‐DISORDER: Motion Correction in 3D MRI via Segment Reconstruction and Registration

Laurens Beljaards iD, Martijn Nagtegaal iD, Chinmay Rao, Yiming Dong, Matthias J P van Osch iD, Nicola Pezzotti, Mariya Doneva, Marius Staring

NMR in Biomedicine · 2026-05 · 39 (5)

DOI: 10.1002/nbm.70286 ↗

Kurz gefasst

Fachartikel in der Zeitschrift NMR in Biomedicine, online erschienen am 09.04.2026. Verfasst von Laurens Beljaards und 7 weiteren Autor:innen. Beteiligte Einrichtung: Department of Radiology, Leiden University Medical Center, Leiden, the Netherlands. Hauptthemen laut MEDLINE: Imaging, Three-Dimensional, Magnetic Resonance Imaging, Motion. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 38 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: ROBUST: Trustworthy AI-based Systems for Sustainable Growth, Dutch Research Council (NWO), Philips.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

3D MR image acquisition is inherently time intensive, rendering it susceptible to patient motion during scanning. This may introduce significant blurring and artifacts, potentially necessitating reacquisition. We propose a modular framework to retrospectively correct for intrascan motion in 3D brain MRI, without active motion tracking. Serving as the backbone of our approach is an existing distributed and incoherent sampling scheme (DISORDER), combined with a fast network trained for highly undersampled reconstruction. This enables approximate reconstructions of anatomy after every few seconds, using only a tiny fraction of k‐space data (< 2%). While these reconstructions are only approximate, we postulate they are sufficient to estimate motion patterns at said temporal resolution. Groupwise registration, notable for its elimination of registration bias, is utilized for estimating rigid motion parameters, which are leveraged to reconstruct the measured data with reduced motion artifacts. The approach was evaluated on 94 retrospectively and 3 prospectively motion‐corrupted in vivo 3D T1‐weighted brain MRI acquisitions. The estimated motion parameters matched the known retrospective motion with 0.06 mm and 0.13° accuracy, resulting in an improvement in reconstruction quality from to SSIM for the retrospective scans. The prospective scans improved from to SSIM after correction in the case of gradual motion and from to SSIM for extreme motion. In conclusion, the proposed approach, that is free of external tracking devices or navigators, successfully estimated and corrected 3D motion between small subportions of a scan. This resulted in vastly improved image quality, making volumetric MRI substantially more tolerant to motion.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Imaging, Three-DimensionalMagnetic Resonance ImagingMotionHumansArtifactsAlgorithmsBrain

Stichwörter der Autor:innen

DISORDERdeep learninggroupwise registrationimage reconstructionretrospective motion correction

Autor:innen und Institutionen

  • Department of Radiology, Leiden University Medical Center, Leiden, the Netherlands.
  • Department of Mathematics and Computer Science, Eindhoven University of Technology, Eindhoven, the Netherlands.
  • Cardiologs, Paris, France.
  • Philips Innovative Technologies, Hamburg, Germany.

ORCID-Profile: Laurens Beljaards, Martijn Nagtegaal, Matthias J P van Osch

Förderung

  • ROBUST: Trustworthy AI-based Systems for Sustainable Growth
  • Dutch Research Council (NWO)
  • Philips
  • Dutch Ministry of Economic Affairs and Climate Policy (EZK)
  • Health ∼Holland Top Sector Life Sciences & Health
  • Nederlandse Organisatie voor Wetenschappelijk Onderzoek
  • Ministerie van Economische Zaken en Klimaat

Zitieren

APA

Beljaards, L., Nagtegaal, M., Rao, C., Dong, Y., P van Osch, M. J., Pezzotti, N., Doneva, M., & Staring, M. (2026). DEEP‐DISORDER: Motion Correction in 3D MRI via Segment Reconstruction and Registration. NMR in Biomedicine, 39(5). https://doi.org/10.1002/nbm.70286

Vancouver

Beljaards L, Nagtegaal M, Rao C, Dong Y, P van Osch MJ, Pezzotti N, et al. DEEP‐DISORDER: Motion Correction in 3D MRI via Segment Reconstruction and Registration. NMR in Biomedicine. 2026;39(5). doi:10.1002/nbm.70286

BibTeX
@article{Beljaards2026,
  author = {Beljaards, Laurens and Nagtegaal, Martijn and Rao, Chinmay and Dong, Yiming and P van Osch, Matthias J and Pezzotti, Nicola and Doneva, Mariya and Staring, Marius},
  title = {DEEP‐DISORDER: Motion Correction in 3D MRI via Segment Reconstruction and Registration},
  journal = {NMR in Biomedicine},
  year = {2026},
  volume = {39},
  number = {5},
  doi = {10.1002/nbm.70286}
}
Kostenlos starten →