# Fast MRI Reconstruction: How Powerful Transformers Are?

arXiv: https://arxiv.org/abs/2201.09400 · HTML: https://mlsanity.com/paper/2201.09400/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 23 references that are in the map.
- First posted on arXiv 23 Jan 2022.

## Builds on (most cited first, 17 of 17)

- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [Sequence to Sequence Learning with Neural Networks](https://mlsanity.com/paper/1409.3215/) (2014)
- [SwinIR: Image Restoration Using Swin Transformer](https://mlsanity.com/paper/2108.10257/) (2021)
- [Image Transformer](https://mlsanity.com/paper/1802.05751/) (2018)
- [fastMRI: An Open Dataset and Benchmarks for Accelerated MRI](https://mlsanity.com/paper/1811.08839/) (2018)
- [A Deep Cascade of Convolutional Neural Networks for Dynamic MR Image Reconstruction](https://mlsanity.com/paper/1704.02422/) (2017)
- [Fast and Accurate Image Super-Resolution with Deep Laplacian Pyramid Networks](https://mlsanity.com/paper/1710.01992/) (2017)
- [A U-Net Based Discriminator for Generative Adversarial Networks](https://mlsanity.com/paper/2002.12655/) (2020)
- [Is it Time to Replace CNNs with Transformers for Medical Images?](https://mlsanity.com/paper/2108.09038/) (2021)
- [Swin Transformer for Fast MRI](https://mlsanity.com/paper/2201.03230/) (2022)
- [AI-based Reconstruction for Fast MRI -- A Systematic Review and Meta-analysis](https://mlsanity.com/paper/2112.12744/) (2021)
- [Transfer Learning Enhanced Generative Adversarial Networks for Multi-Channel MRI Reconstruction](https://mlsanity.com/paper/2105.08175/) (2021)
- [Stochastic Deep Compressive Sensing for the Reconstruction of Diffusion Tensor Cardiac MRI](https://mlsanity.com/paper/1805.12064/) (2018)
- [Edge-Enhanced Dual Discriminator Generative Adversarial Network for Fast MRI with Parallel Imaging Using Multi-view Information](https://mlsanity.com/paper/2112.05758/) (2021)
- [Generative Adversarial Networks (GAN) Powered Fast Magnetic Resonance Imaging -- Mini Review, Comparison and Perspectives](https://mlsanity.com/paper/2105.01800/) (2021)

## Built on by (most cited first, 7 of 7)

- [MambaMIR: An Arbitrary-Masked Mamba for Joint Medical Image Reconstruction and Uncertainty Estimation](https://mlsanity.com/paper/2402.18451/) (2024)
- [Transformers in Healthcare: A Survey](https://mlsanity.com/paper/2307.00067/) (2023)
- [Swin Deformable Attention U-Net Transformer (SDAUT) for Explainable Fast MRI](https://mlsanity.com/paper/2207.02390/) (2022)
- [ViGU: Vision GNN U-Net for Fast MRI](https://mlsanity.com/paper/2302.10273/) (2023)
- [Deep Learning-based Diffusion Tensor Cardiac Magnetic Resonance Reconstruction: A Comparison Study](https://mlsanity.com/paper/2304.00996/) (2023)
- [A Comprehensive Survey on Magnetic Resonance Image Reconstruction](https://mlsanity.com/paper/2503.07097/) (2025)
- [Decoupling Multi-Contrast Super-Resolution: Self-Supervised Implicit Re-Representation for Unpaired Cross-Modal Synthesis](https://mlsanity.com/paper/2505.05855/) (2025)

## Abstract (arXiv)

Magnetic resonance imaging (MRI) is a widely used non-radiative and non-invasive method for clinical interrogation 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.com/ayanglab/SwinGANMR.