Potential and challenges of generative adversarial networks for super-resolution in 4D flow MRI.
Authors
Affiliations (11)
Affiliations (11)
- Dept. Molecular Medicine and Surgery, Karolinska Institutet, Karolinska Universitetssjukhuset Solna (L1:00), Stockholm, 171 76, Sweden. Electronic address: [email protected].
- FLOW, Engineering Mechanics, KTH Royal Institute of Technology, Osquars Backe 18, Stockholm, 100 44, Sweden.
- Department of Radiology and Biomedical Imaging, University of California San Francisco, 505 Parnassus Avenue, San Francisco, CA 94143, USA.
- Faculty of Informatics, Telkom University, Jl.Telekomunikasi No. 1, Terusan Buahbatu, Bandung, 40257, West Java, Indonesia; Auckland Bioengineering Institute, University of Auckland, Bioengineering House, 70 Symonds St, Grafton, 1010, New Zealand.
- Auckland Bioengineering Institute, University of Auckland, Bioengineering House, 70 Symonds St, Grafton, 1010, New Zealand; School of Biomedical Engineering & Imaging Sciences, King's College London, 1 Lambeth Palace Rd, South Bank, London, SE1 7EU, UK.
- Department of Biomedical Engineering, University of Michigan, 1107 Carl A. Gerstacker Bldg 2200 Bonisteel Blvd., Ann Arbor, MI 48109-2099, USA.
- Department of Physics, University of Greifswald, Felix-Hausdorff-Str. 6, Greifswald, 174 89, Germany.
- Department of Aerospace Engineering, University of Michigan, 1320 Beal Avenue, Ann Arbor, MI 48109-2140, USA.
- Dept. Molecular Medicine and Surgery, Karolinska Institutet, Karolinska Universitetssjukhuset Solna (L1:00), Stockholm, 171 76, Sweden; Department of Neuroradiology, Karolinska University Hospital, Hälsovägen 13, O42, Stockholm, 141 86, Sweden.
- Dept. Molecular Medicine and Surgery, Karolinska Institutet, Karolinska Universitetssjukhuset Solna (L1:00), Stockholm, 171 76, Sweden; Department of Clinical Physiology, Karolinska University Hospital, Eugeniavägen 3, A8:01, Solna, 171 64, Sweden.
- Dept. Molecular Medicine and Surgery, Karolinska Institutet, Karolinska Universitetssjukhuset Solna (L1:00), Stockholm, 171 76, Sweden; Institute for Medical Engineering and Science, Massachusetts Institute of Technology, 45 Carleton St, Cambridge, MA 02142, USA.
Abstract
Time-resolved three-dimensional phase-contrast MRI (4D Flow MRI) enables non-invasive quantification of blood flow and derivation of hemodynamic parameters. However, its clinical application is limited by low spatial resolution and noise, particularly affecting velocity measurements near vessel walls. Machine learning-based super-resolution has shown promise in addressing these limitations, but challenges remain, not least in recovering near-wall velocities. Generative adversarial networks (GANs) offer a compelling solution, having demonstrated strong capabilities in restoring sharp boundaries in non-medical super-resolution settings. Yet, their application in 4D Flow MRI remains unexplored, with implementation challenged by known issues such as training instability and non-convergence. In this study, we investigate GAN-based super-resolution and denoising in 4D Flow MRI. Training and validation were conducted using patient-specific cerebrovascular in-silico models, converted into synthetic images via an MR-true reconstruction pipeline, with complementary validation on in-vivo acquisitions. A dedicated GAN architecture was implemented and evaluated across three adversarial loss functions: Vanilla, Relativistic, and Wasserstein. Our results demonstrate that the proposed GAN improved near-wall velocity recovery compared to a non-adversarial reference (vector Normalized Root Mean Square Error (vNRMSE): 6.9% vs. 9.6%); however, implementation specifics are critical for stable network training. While Vanilla and Relativistic GANs proved unstable compared to generator-only training (vNRMSE: 8.1% and 7.8% vs. 7.2%), a Wasserstein GAN demonstrated optimal stability and incremental improvement (vNRMSE: 6.9% vs. 7.2%). Moreover, strong in-vivo performance supports clinical translation. Together, these findings highlight the potential of GAN-based super-resolution in enhancing 4D Flow MRI, particularly in challenging cerebrovascular regions, while emphasizing the importance of carefully selecting adversarial training strategies.