Enhancing compressed sensing and parallel imaging accelerated magnetic resonance angiography using a dual‐domain projection generative adversarial network
Medical Physics · 2026-07 · 53 (7)
DOI: 10.1002/mp.70567 ↗At a glance
Journal article in Medical Physics, published online on 2026-07-10. Written by Libo Xu and 7 co-authors. Institution: Shanghai Key Laboratory of Magnetic Resonance, School of Physics, East China Normal University, Shanghai, China. Major MEDLINE topics: Generative Adversarial Networks, Magnetic Resonance Angiography, Image Processing, Computer-Assisted, Deep Learning. 23 references. The full text is freely available in PubMed Central. Funded by: National Key Research and Development Program, National Natural Science Foundation of China, Beijing Municipal Natural Science Foundation.
Abstract (original language)
Background
As a key modality for cerebrovascular disease diagnosis, time‐of‐flight magnetic resonance angiography (TOF‐MRA) necessitates high spatial resolution and sensitivity. Although acceleration of MRA is critical for reducing scan time and increasing patient throughput, achieving diagnostic‐quality images at high undersampling rates remains a significant challenge.
Purpose
This study aims to develop a deep learning‐based post‐processing method that generates high‐quality MRA images from highly undersampled data, improving detection sensitivity for vascular abnormalities.
Methods
This prospective study employed a standard MRA scan as a baseline, followed by accelerated scans using compressed sensing (CS) with factors of 4, 6, 8, and 10, as well as sensitivity encoding (SENSE) with a factor of 4. A Dual‐Domain Projection Generative Adversarial Network (DDPGAN) was proposed, taking stacked 2D patches from accelerated MRA reconstructions as input and employing a dual‐headed discriminator to enhance image quality. The quantitative indicators included Peak Signal‐to‐Noise Ratio (PSNR), Structural Similarity Index Measure (SSIM), Normalized Mean Squared Error (NMSE), and Signal‐to‐Noise Ratio (SNR). Qualitative assessment was conducted using a 5‐point reader scale focusing on image clarity and diagnostic confidence.
Results
Sixty‐four patients (53 ± 16 years; 26 men) were included. DDPGAN outperformed other deep learning models across all qualitative and quantitative metrics, achieving PSNR = 31.98 dB, SSIM = 0.88, NMSE = 0.052, and SNR = 56.82 for CS×10. Qualitatively, CS×4 images improved from poor (reader1: 3.50 ± 0.50; reader2: 3.64 ± 0.48) to good/excellent (reader1: 4.64 ± 0.48; reader2: 4.93 ± 0.26), surpassing even standard scans (reader 1: 3.93 ± 0.707, reader 2: 4.71 ± 0.808). Comparative studies confirmed the robustness of DDPGAN across diverse acceleration scenarios, with significant improvements in the visualization of major cerebral vascular structures.
Conclusion
The DDPGAN framework significantly enhances accelerated MRA image quality, enabling high detail preservation and diagnostic confidence across various acceleration scenarios. Its dual‐domain design supports efficient, high‐quality MRA examinations, indicating strong clinical potential particularly in the evaluation of cerebrovascular disease.
Subjects
MeSH terms (MEDLINE)
Author keywords
Authors and institutions
- Shanghai Key Laboratory of Magnetic Resonance, School of Physics, East China Normal University, Shanghai, China.
- Institute of Magnetic Resonance and Molecular Imaging in Medicine, East China Normal University, Shanghai, China.
- Department of Radiology, Beijing Chaoyang Hospital, Capital Medical University, Beijing, China.
- Key Lab of Medical Engineering for Cardiovascular Disease, Ministry of Education, Beijing, China.
- RadioDynamic Medical, Shanghai, China.
- Department of Radiology, Lucile Packard Children's Hospital, Stanford, California, USA.
Funding
- National Key Research and Development Program
- National Natural Science Foundation of China
- Beijing Municipal Natural Science Foundation
- Shanghai Special Fund for Promoting High-Quality Industrial Development
- Natural Science Foundation of Xiamen
- Grand NeoBay Development Fund
- National Key Research and Development Program of China
- Natural Science Foundation of Beijing Municipality
Cite
APA
Xu, L., Bian, Y., Gan, K., Pan, B., Yeom, K. W., Moseley, M., Yang, Q., & Gong, N. J. (2026). Enhancing compressed sensing and parallel imaging accelerated magnetic resonance angiography using a dual‐domain projection generative adversarial network. Medical Physics, 53(7). https://doi.org/10.1002/mp.70567
Vancouver
Xu L, Bian Y, Gan K, Pan B, Yeom KW, Moseley M, et al. Enhancing compressed sensing and parallel imaging accelerated magnetic resonance angiography using a dual‐domain projection generative adversarial network. Medical Physics. 2026;53(7). doi:10.1002/mp.70567
BibTeX
@article{Xu2026,
author = {Xu, Libo and Bian, Yueyan and Gan, Kexin and Pan, Boyang and Yeom, Kristen W and Moseley, Michael and Yang, Qi and Gong, Nan-Jie},
title = {Enhancing compressed sensing and parallel imaging accelerated magnetic resonance angiography using a dual‐domain projection generative adversarial network},
journal = {Medical Physics},
year = {2026},
volume = {53},
number = {7},
doi = {10.1002/mp.70567}
}
EUVIMED