标题： 生成对抗网络在4D流动MRI超分辨率中的潜力与挑战 显示英文标题

标题： Potential and challenges of generative adversarial networks for super-resolution in 4D Flow MRI

摘要： 4D流动磁共振成像(4D Flow MRI)能够无创地量化血流和血流动力学参数。然而，由于空间分辨率低和噪声问题，其临床应用受到限制，特别是在近壁速度测量方面。基于机器学习的超分辨率在解决这些限制方面显示出前景，但仍然存在挑战，尤其是在恢复近壁速度方面。生成对抗网络(GANs)提供了一个有吸引力的解决方案，在非医学超分辨率任务中表现出强大的恢复清晰边界的能力。然而，它们在4D Flow MRI中的应用尚未被探索，实现上受到已知问题的挑战，如训练不稳定和不收敛。在本研究中，我们研究了基于GAN的4D Flow MRI超分辨率。训练和验证使用了患者特异性脑血管体外模型，通过MR真实重建流程转换为合成图像。实施并评估了一种专用的GAN架构，涵盖了三种对抗损失函数：Vanilla、Relativistic和Wasserstein。我们的结果表明，与非对抗性参考相比，所提出的GAN提高了近壁速度恢复(vNRMSE:6.9% vs.9.6%)；然而，实现细节对于稳定的网络训练至关重要。与仅生成器训练相比，Vanilla和Relativistic GAN显示不稳定(vNRMSE:8.1%和7.8% vs.7.2%)，而Wasserstein GAN表现出最佳稳定性并有逐步改进(vNRMSE:6.9% vs.7.2%)。Wasserstein GAN在低信噪比下进一步优于仅生成器基线(vNRMSE:8.7% vs.10.7%)。这些发现突显了基于GAN的超分辨率在增强4D Flow MRI方面的潜力，特别是在具有挑战性的脑血管区域，同时强调了对抗策略的精心选择的必要性。 显示英文摘要

摘要： 4D Flow Magnetic Resonance Imaging (4D Flow MRI) enables non-invasive quantification of blood flow and hemodynamic parameters. However, its clinical application is limited by low spatial resolution and noise, particularly affecting near-wall velocity measurements. 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 tasks. 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 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. 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 (vNRMSE: 6.9% vs. 9.6%); however, that 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%). The Wasserstein GAN further outperformed the generator-only baseline at low SNR (vNRMSE: 8.7% vs. 10.7%). These findings highlight the potential of GAN-based super-resolution in enhancing 4D Flow MRI, particularly in challenging cerebrovascular regions, while emphasizing the need for careful selection of adversarial strategies.