EUVIMEDEUVIMED entdecken
VergleichsstudieOpen Access · CC BY 4.0

Offline Reconstruction of Diffusion MRI Acquisitions for Comparison Between Complex PCA ‐Based and AI ‐Based Denoising

Francesco D'Antonio iD, Shaun Warrington iD, Jose-Pedro Manzano-Patron iD, Paul S Morgan iD, Stamatios N Sotiropoulos iD

Magnetic Resonance in Medicine · 2026-07 · 96 (1) · 435-447

DOI: 10.1002/mrm.70336 ↗

Kurz gefasst

Vergleichsstudie in der Zeitschrift Magnetic Resonance in Medicine, online erschienen am 07.03.2026. Verfasst von Francesco D'Antonio und 4 weiteren Autor:innen. Beteiligte Einrichtung: Sir Peter Mansfield Imaging Centre, School of Medicine, The University of Nottingham, Nottingham, UK. Hauptthemen laut MEDLINE: Diffusion Magnetic Resonance Imaging, Image Processing, Computer-Assisted, Brain. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 54 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: GE Healthcare, The University of Nottingham, European Research Council.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Purpose

Optimal diffusion MRI (dMRI) data for image denoising is often unavailable from scanner reconstruction. In this work, we make available an offline reconstruction pipeline for GE dMRI acquisitions, giving access to complex dMRI data. Furthermore, we compare the efficacy of GE HealthCare's AIR‐Recon DL (ARDL), a proprietary convolutional neural network‐based reconstruction and denoising approach, to patch‐based MPPCA SVS and NORDIC denoising methods on high‐resolution dMRI data.

Methods

We developed an end‐to‐end offline dMRI reconstruction pipeline for GE HealthCare acquisitions, augmenting the Orchestra software development kit, and validated its output against scanner reconstruction. We used it to compare MPPCA SVS , NORDIC, and ARDL denoising approaches, considering underlying metrics reflecting noise variance and bias, such as the signal profiles in highly anisotropic areas, and secondary downstream measurements, such as fiber orientation estimation and white matter tractography.

Results

Our validated offline reconstruction supports various in‐plane/out‐of‐plane accelerations and partial Fourier reconstruction methods. Unlike scanner reconstruction, it provides access to complex dMRI data, enabling denoising in the complex domain, which demonstrated superior noise floor suppression compared with magnitude‐constrained denoising. PCA‐based denoising methods had improved spatial resolution, contrast‐to‐noise and more robust fiber orientation estimation compared with ARDL.

Conclusion

We found significant gains in dMRI data quality when using the proposed offline reconstruction pipeline, allowing complex‐domain denoising to obtain high‐quality data at high spatial resolution and b‐value, using a wide‐bore scanner and a standard PGSE EPI sequence. MPPCA SVS and NORDIC (4D PCA‐based) outperformed ARDL (2D) in terms of spatial resolution and reduction of noise variance.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Diffusion Magnetic Resonance ImagingImage Processing, Computer-AssistedBrainHumansAlgorithmsSignal-To-Noise RatioPrincipal Component AnalysisSoftwareReproducibility of ResultsConvolutional Neural NetworksWhite MatterArtificial Intelligence

Stichwörter der Autor:innen

AIR‐recon DLMPPCANORDICdenoisingdiffusion MRIimage reconstruction

Autor:innen und Institutionen

  • Sir Peter Mansfield Imaging Centre, School of Medicine, The University of Nottingham, Nottingham, UK.
  • Mental Health and Clinical Neurosciences, School of Medicine, The University of Nottingham, Nottingham, UK.
  • National Institute of Health and Care Research Nottingham Biomedical Research Centre, Nottingham University Hospitals, Nottingham, UK.

ORCID-Profile: Francesco D'Antonio, Shaun Warrington, Jose-Pedro Manzano-Patron, Paul S Morgan, Stamatios N Sotiropoulos

Förderung

  • GE Healthcare
  • The University of Nottingham
  • European Research Council
  • University of Nottingham

Zitieren

APA

D'Antonio, F., Warrington, S., Manzano-Patron, J. P., Morgan, P. S., & Sotiropoulos, S. N. (2026). Offline Reconstruction of Diffusion MRI Acquisitions for Comparison Between Complex PCA ‐Based and AI ‐Based Denoising. Magnetic Resonance in Medicine, 96(1), 435-447. https://doi.org/10.1002/mrm.70336

Vancouver

D'Antonio F, Warrington S, Manzano-Patron JP, Morgan PS, Sotiropoulos SN. Offline Reconstruction of Diffusion MRI Acquisitions for Comparison Between Complex PCA ‐Based and AI ‐Based Denoising. Magnetic Resonance in Medicine. 2026;96(1):435-447. doi:10.1002/mrm.70336

BibTeX
@article{DAntonio2026,
  author = {D'Antonio, Francesco and Warrington, Shaun and Manzano-Patron, Jose-Pedro and Morgan, Paul S and Sotiropoulos, Stamatios N},
  title = {Offline Reconstruction of Diffusion MRI Acquisitions for Comparison Between Complex PCA ‐Based and AI ‐Based Denoising},
  journal = {Magnetic Resonance in Medicine},
  year = {2026},
  volume = {96},
  number = {1},
  pages = {435--447},
  doi = {10.1002/mrm.70336}
}
Kostenlos starten →