Annu Int Conf IEEE Eng Med Biol Soc. 2022 Jul;2022:2066-2070. doi: 10.1109/EMBC48229.2022.9871475.
Magnetic resonance imaging (MRI) is a widely used non-radiative and non-invasive method for clinical interro-gation of organ structures and metabolism, with an inherently long scanning time. Methods by k-space undersampling and deep learning based reconstruction have been popularised to accelerate the scanning process. This work focuses on investigating how powerful transformers are for fast MRI by exploiting and comparing different novel network architectures. In particular, a generative adversarial network (GAN) based Swin transformer (ST-GAN) was introduced for the fast MRI reconstruction. To further preserve the edge and texture information, edge enhanced GAN based Swin transformer (EES-GAN) and texture enhanced GAN based Swin transformer (TES-GAN) were also developed, where a dual-discriminator GAN structure was applied. We compared our proposed GAN based transformers, standalone Swin transformer and other convolutional neural networks based GAN model in terms of the evaluation metrics PSNR, SSIM and FID. We showed that transformers work well for the MRI reconstruction from different undersampling conditions. The utilisation of GAN's adversarial structure improves the quality of images reconstructed when undersampled for 30% or higher. The code is publicly available at https://github.comJayanglab/SwinGANMR.
磁共振成像（MRI）是一种广泛应用于临床器官结构和代谢研究的非放射性、非侵入性方法，但扫描时间较长。通过欠采样 k 空间和基于深度学习的重建方法已经得到了广泛应用，以加速扫描过程。本工作重点研究了利用和比较不同的新型网络架构，变压器在快速 MRI 中的强大功能。具体来说，我们引入了基于生成对抗网络（GAN）的 Swin 变压器（ST-GAN）用于快速 MRI 重建。为了进一步保留边缘和纹理信息，我们还开发了基于边缘增强 GAN 的 Swin 变压器（EES-GAN）和基于纹理增强 GAN 的 Swin 变压器（TES-GAN），其中应用了双鉴别器 GAN 结构。我们在 PSNR、SSIM 和 FID 等评估指标方面比较了我们提出的基于 GAN 的变压器、独立的 Swin 变压器和其他基于卷积神经网络的 GAN 模型。我们表明，变压器在从不同欠采样条件重建 MRI 方面表现良好。当以 30%或更高的欠采样率进行采样时，GAN 的对抗结构的利用可以提高重建图像的质量。代码可在 https://github.comJayanglab/SwinGANMR 上获得。
