EUVIMEDEUVIMED entdecken
Open Access

Deep Learning Reconstruction for 7T MP2RAGE and SPACE MRI: Improving Image Quality at High Acceleration Factors

Zeyu Liu, Vishal Patel iD, Xiangzhi Zhou iD, Shengzhen Tao iD, Thomas Yu, Jun Ma, Dominik Nickel iD, Patrick Liebig, Erin M Westerhold iD, Hamed Mojahed, Vivek Gupta iD, Erik H Middlebrooks iD

American Journal of Neuroradiology · 2025-11 · 46 (11) · 2446-2454

DOI: 10.3174/ajnr.a8841 ↗

Kurz gefasst

Fachartikel in der Zeitschrift American Journal of Neuroradiology, online erschienen am 20.05.2025. Verfasst von Zeyu Liu und 11 weiteren Autor:innen. Beteiligte Einrichtung: From the Department of Radiology (Z.L., V.P., X.Z., S.T., T.Y., E.M.W., V.G., E.H.M.), Mayo Clinic, Jacksonville, Florida. Hauptthemen laut MEDLINE: Deep Learning, Magnetic Resonance Imaging, Brain, Image Processing, Computer-Assisted. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 28 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: German Federal Ministry of Education and Research.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

BACKGROUND AND PURPOSE: Deep learning (DL) reconstruction has been successful in realizing otherwise impracticable acceleration factors and improving image quality in conventional MRI field strengths; however, there has been limited application to ultra-high-field MRI. The objective of this study was to evaluate the performance of a prototype DL-based image reconstruction technique in 7T MRI of the brain utilizing magnetization-prepared 2 rapid acquisition gradient echoes (MP2RAGE) and sampling perfection with application-optimized contrasts using different flip angle evolutions (SPACE) acquisitions, in comparison with reconstructions in conventional compressed sensing and controlled aliasing in parallel imaging techniques. MATERIALS AND METHODS: This retrospective study involved 60 patients who underwent 7T brain MRI between June 2024 and October 2024, comprising 30 patients with MP2RAGE data and 30 patients with SPACE FLAIR data. Each set of raw data was reconstructed with DL-based reconstruction and conventional reconstruction. Image quality was independently assessed by 2 neuroradiologists by using a 5-point Likert scale, which included overall image quality, artifacts, sharpness, structural conspicuity, and noise level. Interobserver agreement was determined by using top-box analysis. Contrast-to-noise ratio (CNR) and noise levels were quantitatively evaluated and compared by using the Wilcoxon signed-rank test. RESULTS: DL-based reconstruction resulted in a significant increase in overall image quality and a reduction in subjective noise level for both MP2RAGE and SPACE FLAIR data (all P .05). When compared with standard reconstruction, the implementation of DL-based reconstruction yielded an increase in CNR of 49.5% (95% CI, 33.0%-59.0%) for MP2RAGE data and 90.6% (95% CI, 73.2%-117.7%) for SPACE FLAIR data, along with a decrease in noise of 33.5% (95% CI, 23.0%-38.0%) for MP2RAGE data and 47.5% (95% CI, 41.9%-52.6%) for SPACE FLAIR data. CONCLUSIONS: DL-based reconstruction of 7T MRI significantly enhanced image quality compared with conventional reconstruction without introducing image artifacts. The achievable high acceleration factors have the potential to substantially improve image quality and resolution in 7T MRI.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningMagnetic Resonance ImagingBrainImage Processing, Computer-AssistedImage Interpretation, Computer-AssistedHumansMaleRetrospective StudiesFemaleMiddle AgedAdultAgedArtifactsSignal-To-Noise Ratio

Autor:innen und Institutionen

  • From the Department of Radiology (Z.L., V.P., X.Z., S.T., T.Y., E.M.W., V.G., E.H.M.), Mayo Clinic, Jacksonville, Florida.
  • Department of Radiology (Z.L.), Peking Union Medical College Hospital, Beijing, China.
  • Advanced Clinical Imaging Technology (T.Y.), Siemens Healthineers International AG, Lausanne, Switzerland.
  • Department of Radiology (T.Y.), Lausanne University Hospital and University of Lausanne, Lausanne, Switzerland.
  • LTS5, Ecole Polytechnique Fédérale de Lausanne (EPFL) (T.Y.), Lausanne, Switzerland.
  • Siemens Medical Solutions USA, Inc (J.M.), Jacksonville, Florida.

ORCID-Profile: Vishal Patel, Xiangzhi Zhou, Shengzhen Tao, Dominik Nickel, Erin M Westerhold, Vivek Gupta, Erik H Middlebrooks

Förderung

  • German Federal Ministry of Education and Research

Zitieren

APA

Liu, Z., Patel, V., Zhou, X., Tao, S., Yu, T., Ma, J., Nickel, D., Liebig, P., Westerhold, E. M., Mojahed, H., Gupta, V., & Middlebrooks, E. H. (2025). Deep Learning Reconstruction for 7T MP2RAGE and SPACE MRI: Improving Image Quality at High Acceleration Factors. American Journal of Neuroradiology, 46(11), 2446-2454. https://doi.org/10.3174/ajnr.a8841

Vancouver

Liu Z, Patel V, Zhou X, Tao S, Yu T, Ma J, et al. Deep Learning Reconstruction for 7T MP2RAGE and SPACE MRI: Improving Image Quality at High Acceleration Factors. American Journal of Neuroradiology. 2025;46(11):2446-2454. doi:10.3174/ajnr.a8841

BibTeX
@article{Liu2025,
  author = {Liu, Zeyu and Patel, Vishal and Zhou, Xiangzhi and Tao, Shengzhen and Yu, Thomas and Ma, Jun and Nickel, Dominik and Liebig, Patrick and Westerhold, Erin M and Mojahed, Hamed and Gupta, Vivek and Middlebrooks, Erik H},
  title = {Deep Learning Reconstruction for 7T MP2RAGE and SPACE MRI: Improving Image Quality at High Acceleration Factors},
  journal = {American Journal of Neuroradiology},
  year = {2025},
  volume = {46},
  number = {11},
  pages = {2446--2454},
  doi = {10.3174/ajnr.a8841}
}
Kostenlos starten →