EUVIMEDEUVIMED entdecken
VergleichsstudieOpen Access · CC BY 4.0

Benchmarking Hybrid CNN ‐Transformer Versus Pure Transformer Architectures for Accelerated Hyperpolarized 129 Xe MRI Reconstruction

Ramtin Babaeipour iD, Matthew S Fox, Grace Parraga iD, Alexei Ouriadov iD

Journal of Magnetic Resonance Imaging · 2026-07 · 64 (1) · 266-280

DOI: 10.1002/jmri.70314 ↗

Kurz gefasst

Vergleichsstudie in der Zeitschrift Journal of Magnetic Resonance Imaging, online erschienen am 27.03.2026. Verfasst von Ramtin Babaeipour und 3 weiteren Autor:innen. Beteiligte Einrichtung: School of Biomedical Engineering, Faculty of Engineering, The University of Western Ontario, London, Ontario, Canada. Hauptthemen laut MEDLINE: Image Processing, Computer-Assisted, Magnetic Resonance Imaging, Xenon Isotopes. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 49 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Natural Sciences and Engineering Research Council of Canada.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Hyperpolarized 129 Xe MRI faces technical challenges including low signal‐to‐noise ratio and breath‐hold constraints. Current literature focuses on proprietary deep learning methods or image‐domain enhancements.

Purpose

To present a comprehensive evaluation of transformer and hybrid CNN‐transformer architectures integrating dual‐domain (k‐space and image) processing for HP 129 Xe MRI reconstruction. Study Type Retrospective. Population Two hundred five participants (22 healthy [male and female, 18–85 years], 26 COPD [male and female, 50–85 years], 90 asthma [male and female, 18–70 years], 67 long‐COVID [male and female, 18–70 years]) yielding 1640 2D slices. Dataset split: 80% training (1312 slices), 10% validation (164 slices), 10% test (164 slices). Field Strength/Sequence 3 T; 3D fast gradient‐recalled echo. Assessment Five architectures were compared: KTMR (hybrid transformer‐CNN), KIKI‐net (pure CNN), ReconFormer, SwinMR, and MR‐IPT (pure transformer) at acceleration factors of 3, 7, and 10. Performance was assessed using peak signal‐to‐noise ratio (PSNR), structural similarity index measure (SSIM), and normalized mean squared error (NMSE). Ventilation defect percentage (VDP) agreement with semi‐automated analysis was evaluated. Statistical Tests Friedman test with post hoc Dunn's test and Benjamini‐Hochberg correction for multiple comparisons. Significance level: p < 0.05.

Results

At 10‐fold acceleration, KTMR produced PSNR of 36.4 ± 2.8 dB and SSIM of 0.88 ± 0.12, significantly outperforming KIKI‐net (32.5 ± 3.4 dB, 0.81 ± 0.12), ReconFormer (29.7 ± 2.6 dB, 0.76 ± 0.12), SwinMR (30.5 ± 2.8 dB, 0.76 ± 0.09), and MR‐IPT (28.8 ± 2.4 dB, 0.74 ± 0.11). VDP measurements showed mean bias of 1.94% at 3‐fold, 2.12% at 7‐fold, and 2.69% at 10‐fold acceleration. Data Conclusion KTMR demonstrated superior performance for HP 129 Xe MRI reconstruction at high acceleration factors. Evidence Level 3. Technical Efficacy Stage 1.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Image Processing, Computer-AssistedMagnetic Resonance ImagingXenon IsotopesAdolescentAdultAgedAged, 80 and overFemaleHumansMaleMiddle AgedYoung AdultAsthmaBenchmarkingConvolutional Neural NetworksPulmonary Disease, Chronic ObstructiveRetrospective StudiesSignal-To-Noise RatioPost-Acute COVID-19 Syndrome

Stichwörter der Autor:innen

COPDMRI reconstructionVision Transformersasthmadeep learninghyperpolarized 129Xe MRIlong‐COVIDlung imagingmedical imagingpulmonary imaging

Substanzen

hyperpolarized Xe-129Xenon Isotopes

Autor:innen und Institutionen

  • School of Biomedical Engineering, Faculty of Engineering, The University of Western Ontario, London, Ontario, Canada.
  • Department of Physics and Astronomy, The University of Western Ontario, London, Ontario, Canada.
  • Lawson Research Institute, London, Ontario, Canada.
  • Department of Medical Biophysics, The University of Western Ontario, London, Ontario, Canada.
  • Robarts Research Institute, The University of Western Ontario, London, Ontario, Canada.

ORCID-Profile: Ramtin Babaeipour, Grace Parraga, Alexei Ouriadov

Förderung

  • Natural Sciences and Engineering Research Council of Canada

Zitieren

APA

Babaeipour, R., Fox, M. S., Parraga, G., & Ouriadov, A. (2026). Benchmarking Hybrid CNN ‐Transformer Versus Pure Transformer Architectures for Accelerated Hyperpolarized 129 Xe MRI Reconstruction. Journal of Magnetic Resonance Imaging, 64(1), 266-280. https://doi.org/10.1002/jmri.70314

Vancouver

Babaeipour R, Fox MS, Parraga G, Ouriadov A. Benchmarking Hybrid CNN ‐Transformer Versus Pure Transformer Architectures for Accelerated Hyperpolarized 129 Xe MRI Reconstruction. Journal of Magnetic Resonance Imaging. 2026;64(1):266-280. doi:10.1002/jmri.70314

BibTeX
@article{Babaeipour2026,
  author = {Babaeipour, Ramtin and Fox, Matthew S and Parraga, Grace and Ouriadov, Alexei},
  title = {Benchmarking Hybrid CNN ‐Transformer Versus Pure Transformer Architectures for Accelerated Hyperpolarized 129 Xe MRI Reconstruction},
  journal = {Journal of Magnetic Resonance Imaging},
  year = {2026},
  volume = {64},
  number = {1},
  pages = {266--280},
  doi = {10.1002/jmri.70314}
}
Kostenlos starten →