# Paired Conditional Generative Adversarial Network for Highly Accelerated Liver 4D MRI

arXiv: https://arxiv.org/abs/2405.12357 · HTML: https://mlsanity.com/paper/2405.12357/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 60 references that are in the map.
- First posted on arXiv 20 May 2024.

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

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Perceptual Losses for Real-Time Style Transfer and Super-Resolution](https://mlsanity.com/paper/1603.08155/) (2016)
- [Image Super-Resolution via Iterative Refinement](https://mlsanity.com/paper/2104.07636/) (2021)
- [Context Encoders: Feature Learning by Inpainting](https://mlsanity.com/paper/1604.07379/) (2016)
- [Video Swin Transformer](https://mlsanity.com/paper/2106.13230/) (2021)
- [Least Squares Generative Adversarial Networks](https://mlsanity.com/paper/1611.04076/) (2016)
- [A Deep Cascade of Convolutional Neural Networks for Dynamic MR Image Reconstruction](https://mlsanity.com/paper/1704.02422/) (2017)
- [Convolutional Recurrent Neural Networks for Dynamic MR Image Reconstruction](https://mlsanity.com/paper/1712.01751/) (2017)
- [How to Train Vision Transformer on Small-scale Datasets?](https://mlsanity.com/paper/2210.07240/) (2022)
- [One-dimensional Deep Low-rank and Sparse Network for Accelerated MRI](https://mlsanity.com/paper/2112.04721/) (2021)
- [SANTIS: Sampling-Augmented Neural neTwork with Incoherent Structure for MR image reconstruction](https://mlsanity.com/paper/1812.03278/) (2018)
- [Accelerated respiratory-resolved 4D-MRI with separable spatio-temporal neural networks](https://mlsanity.com/paper/2211.05678/) (2022)
- [Nodule detection and generation on chest X-rays: NODE21 Challenge](https://mlsanity.com/paper/2401.02192/) (2024)
- [Learning Dynamic MRI Reconstruction with Convolutional Network Assisted Reconstruction Swin Transformer](https://mlsanity.com/paper/2309.10227/) (2023)
- [An Efficient and Robust Method for Chest X-Ray Rib Suppression that Improves Pulmonary Abnormality Diagnosis](https://mlsanity.com/paper/2302.09696/) (2023)

## Built on by (most cited first, 3 of 3)

- [Accelerated Patient-specific Non-Cartesian MRI Reconstruction using Implicit Neural Representations](https://mlsanity.com/paper/2503.05051/) (2025)
- [Advancing MRI Reconstruction: A Systematic Review of Deep Learning and Compressed Sensing Integration](https://mlsanity.com/paper/2501.14158/) (2025)
- [B-FIRE: Binning-Free Diffusion Implicit Neural Representation for Hyper-Accelerated Motion-Resolved MRI](https://mlsanity.com/paper/2601.06166/) (2026)

## Abstract (arXiv)

Purpose: 4D MRI with high spatiotemporal resolution is desired for image-guided liver radiotherapy. Acquiring densely sampling k-space data is time-consuming. Accelerated acquisition with sparse samples is desirable but often causes degraded image quality or long reconstruction time. We propose the Reconstruct Paired Conditional Generative Adversarial Network (Re-Con-GAN) to shorten the 4D MRI reconstruction time while maintaining the reconstruction quality. Methods: Patients who underwent free-breathing liver 4D MRI were included in the study. Fully- and retrospectively under-sampled data at 3, 6 and 10 times (3x, 6x and 10x) were first reconstructed using the nuFFT algorithm. Re-Con-GAN then trained input and output in pairs. Three types of networks, ResNet9, UNet and reconstruction swin transformer, were explored as generators. PatchGAN was selected as the discriminator. Re-Con-GAN processed the data (3D+t) as temporal slices (2D+t). A total of 48 patients with 12332 temporal slices were split into training (37 patients with 10721 slices) and test (11 patients with 1611 slices). Results: Re-Con-GAN consistently achieved comparable/better PSNR, SSIM, and RMSE scores compared to CS/UNet models. The inference time of Re-Con-GAN, UNet and CS are 0.15s, 0.16s, and 120s. The GTV detection task showed that Re-Con-GAN and CS, compared to UNet, better improved the dice score (3x Re-Con-GAN 80.98%; 3x CS 80.74%; 3x UNet 79.88%) of unprocessed under-sampled images (3x 69.61%). Conclusion: A generative network with adversarial training is proposed with promising and efficient reconstruction results demonstrated on an in-house dataset. The rapid and qualitative reconstruction of 4D liver MR has the potential to facilitate online adaptive MR-guided radiotherapy for liver cancer.