EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

An Inline‐Integrable Image Restoration Model With ROI Fine‐Tuning and Slice‐to‐Volume Reconstruction for Accelerated Whole‐Brain Vessel Wall Imaging

Pengcheng Wang iD, Jingxiang Zhang, Jiayu Xiao, Junzhou Chen iD, Zhenjia Wang, Jin Li, Qingle Kong iD, Steven Y Cen, Sophia X Cui iD, Yifei Zhang, Wei Yu, Qi Yang und 3 weitere

Magnetic Resonance in Medicine · 2027-01 · 97 (1) · 169-181

DOI: 10.1002/mrm.70594 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Magnetic Resonance in Medicine, online erschienen am 08.10.2026. Verfasst von Pengcheng Wang und 14 weiteren Autor:innen. Beteiligte Einrichtung: Department of Radiology, University of Southern California, Los Angeles, California, USA. Hauptthemen laut MEDLINE: Brain, Image Processing, Computer-Assisted, Magnetic Resonance Imaging, Magnetic Resonance Angiography. Die Arbeit nennt 47 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Purpose

To develop a vessel wall imaging (VWI)‐dedicated image restoration model enabling high‐resolution whole‐brain VWI in under 6 min.

Methods

A transformer‐based 2.5D model was trained in a supervised manner to enhance the image quality of CAIPIRINHA 2 × 2‐accelerated VWI acquisitions to a level comparable to that of GRAPPA twofold‐accelerated scans. The majority of k ‐space data used for training and testing were acquired on a Siemens 3 T system equipped with a standard 20‐channel head–neck coil. Region‐of‐interest fine‐tuning and slice‐to‐volume reconstruction were devised to balance global structural fidelity with local vascular precision and 3D continuity. Model performance was evaluated both quantitatively and qualitatively through single‐center retrospective testing and prospective testing in multi‐center, generalized settings. Integration of the model into the vendor's inline image reconstruction pipeline was also investigated.

Results

Compared with the input images, model outputs improved peak SNR by more than 7 dB and structural similarity index measure by 0.19 in the retrospective test set. When applied to CAIPIRINHA fourfold‐accelerated data that otherwise underwent offline or inline GRAPPA reconstruction, the model significantly enhanced vessel wall SNR, wall‐to‐lumen CNR, wall‐to‐cerebrospinal fluid CNR, and image quality scores. These improvements were sustained in an independent cohort from different institutions and reproduced in a dataset acquired with smaller field of view and a 64‐channel coil, supporting the model's robustness and generalizability.

Conclusion

The proposed inline‐integrable image restoration model enables clinically viable whole‐brain VWI in under 6 min using standard 20‐channel coils, offering a practical approach to improve patient throughput without compromising diagnostic quality.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

BrainImage Processing, Computer-AssistedMagnetic Resonance ImagingMagnetic Resonance AngiographyHumansAlgorithmsRetrospective StudiesImaging, Three-DimensionalSignal-To-Noise Ratio

Stichwörter der Autor:innen

deep learningimage restorationintracranial vessel wallwhole‐brain vessel wall imaging

Autor:innen und Institutionen

  • Department of Radiology, University of Southern California, Los Angeles, California, USA.
  • Department of Biomedical Engineering, University of Southern California, Los Angeles, California, USA.
  • Department of Bioengineering, University of California Los Angeles, California, Los Angeles, California, USA.
  • Department of Radiology, Anzhen Hospital, Beijing, China.
  • Department of Radiology, Chaoyang Hospital, Beijing, China.
  • Siemens Medical Solutions, Los Angeles, California, USA.

ORCID-Profile: Pengcheng Wang, Junzhou Chen, Qingle Kong, Sophia X Cui, Zhaoyang Fan

Zitieren

APA

Wang, P., Zhang, J., Xiao, J., Chen, J., Wang, Z., Li, J., Kong, Q., Cen, S. Y., Cui, S. X., Zhang, Y., Yu, W., Yang, Q., Sheikh-Bahaei, N., Mack, W. J., & Fan, Z. (2027). An Inline‐Integrable Image Restoration Model With ROI Fine‐Tuning and Slice‐to‐Volume Reconstruction for Accelerated Whole‐Brain Vessel Wall Imaging. Magnetic Resonance in Medicine, 97(1), 169-181. https://doi.org/10.1002/mrm.70594

Vancouver

Wang P, Zhang J, Xiao J, Chen J, Wang Z, Li J, et al. An Inline‐Integrable Image Restoration Model With ROI Fine‐Tuning and Slice‐to‐Volume Reconstruction for Accelerated Whole‐Brain Vessel Wall Imaging. Magnetic Resonance in Medicine. 2027;97(1):169-181. doi:10.1002/mrm.70594

BibTeX
@article{Wang2027,
  author = {Wang, Pengcheng and Zhang, Jingxiang and Xiao, Jiayu and Chen, Junzhou and Wang, Zhenjia and Li, Jin and Kong, Qingle and Cen, Steven Y and Cui, Sophia X and Zhang, Yifei and Yu, Wei and Yang, Qi and Sheikh-Bahaei, Nasim and Mack, William J and Fan, Zhaoyang},
  title = {An Inline‐Integrable Image Restoration Model With ROI Fine‐Tuning and Slice‐to‐Volume Reconstruction for Accelerated Whole‐Brain Vessel Wall Imaging},
  journal = {Magnetic Resonance in Medicine},
  year = {2027},
  volume = {97},
  number = {1},
  pages = {169--181},
  doi = {10.1002/mrm.70594}
}
Kostenlos starten →