Generative Adversarial Networks (GAN) Powered Fast Magnetic Resonance Imaging -- Mini Review, Comparison and Perspectives
Not on the map. Why?
Abstract (arXiv)
Magnetic Resonance Imaging (MRI) is a vital component of medical imaging. When compared to other image modalities, it has advantages such as the absence of radiation, superior soft tissue contrast, and complementary multiple sequence information. However, one drawback of MRI is its comparatively slow scanning and reconstruction compared to other image modalities, limiting its usage in some clinical applications when imaging time is critical. Traditional compressive sensing based MRI (CS-MRI) reconstruction can speed up MRI acquisition, but suffers from a long iterative process and noise-induced artefacts. Recently, Deep Neural Networks (DNNs) have been used in sparse MRI reconstruction models to recreate relatively high-quality images from heavily undersampled k-space data, allowing for much faster MRI scanning. However, there are still some hurdles to tackle. For example, directly training DNNs based on L1/L2 distance to the target fully sampled images could result in blurry reconstruction because L1/L2 loss can only enforce overall image or patch similarity and does not take into account local information such as anatomical sharpness. It is also hard to preserve fine image details while maintaining a natural appearance. More recently, Generative Adversarial Networks (GAN) based methods are proposed to solve fast MRI with enhanced image perceptual quality. The encoder obtains a latent space for the undersampling image, and the image is reconstructed by the decoder using the GAN loss. In this chapter, we review the GAN powered fast MRI methods with a comparative study on various anatomical datasets to demonstrate the generalisability and robustness of this kind of fast MRI while providing future perspectives.
Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 42 of its 101 references that are in the map. First posted on arXiv 4 May 2021.
Builds on
42 of 101 references.
References · 42
- 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
- 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
- 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
- 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
- 2017Improved Training of Wasserstein GANscited by 2,223
- 2016Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Networkcited by 1,898
- 2018Spectral Normalization for Generative Adversarial Networkscited by 1,618
- 2017Wasserstein GANcited by 635
- 2018Identifying the Best Machine Learning Algorithms for Brain Tumor Segmentation, Progression Assessment, and Overall Survival Prediction in the BRATS Challengecited by 508
- 2017Learning a Variational Network for Reconstruction of Accelerated MRI Datacited by 340
- 2017A Deep Cascade of Convolutional Neural Networks for Dynamic MR Image Reconstructioncited by 231
- 2019On instabilities of deep learning in image reconstruction - Does AI come at a cost?cited by 211
30 more
- 2020Fast Symmetric Diffeomorphic Image Registration with Convolutional Neural Networkscited by 107
- 2017Convolutional Recurrent Neural Networks for Dynamic MR Image Reconstructioncited by 105
- 2019Evaluation of Algorithms for Multi-Modality Whole Heart Segmentation: An Open-Access Grand Challengecited by 100
- 2017Compressed Sensing MRI Reconstruction using a Generative Adversarial Network with a Cyclic Losscited by 82
- 2017End-to-End Unsupervised Deformable Image Registration with a Convolutional Neural Networkcited by 75
- 2021Unbox the Black-box for the Medical Explainable AI via Multi-modal and Multi-centre Data Fusion: A Mini-Review, Two Showcases and Beyondcited by 75
- 2019Stabilizing Generative Adversarial Networks: A Surveycited by 57
- 2018Deep Residual Learning for Accelerated MRI using Magnitude and Phase Networkscited by 53
- 2017Automatic Brain Tumor Detection and Segmentation Using U-Net Based Fully Convolutional Networkscited by 42
- 2017Unrolled Optimization with Deep Priorscited by 40
- 2019Wavelet Domain Style Transfer for an Effective Perception-distortion Tradeoff in Single Image Super-Resolutioncited by 30
- 2020Unpaired Deep Learning for Accelerated MRI using Optimal Transport Driven CycleGANcited by 28
- 2020Weakly Supervised Deep Learning for COVID-19 Infection Detection and Classification from CT Imagescited by 26
- 2018MRI Reconstruction via Cascaded Channel-wise Attention Networkcited by 20
- 2019Atrial Scar Quantification via Multi-scale CNN in the Graph-cuts Frameworkcited by 19
- 2019A Review on Deep Learning in Medical Image Reconstructioncited by 17
- 2020Simultaneous Left Atrium Anatomy and Scar Segmentations via Deep Learning in Multiview Information with Attentioncited by 16
- 2018Adversarial and Perceptual Refinement for Compressed Sensing MRI Reconstructioncited by 13
- 2019Deep MRI Reconstruction: Unrolled Optimization Algorithms Meet Neural Networkscited by 13
- 2021Explainable AI For COVID-19 CT Classifiers: An Initial Comparison Studycited by 11
- 2019Automatic Prostate Zonal Segmentation Using Fully Convolutional Network with Feature Pyramid Attentioncited by 10
- 2017Face Super-Resolution Through Wasserstein GANscited by 9
- 2017Deep De-Aliasing for Fast Compressive Sensing MRIcited by 9
- 2018Stochastic Deep Compressive Sensing for the Reconstruction of Diffusion Tensor Cardiac MRIcited by 9
- 2019How Can We Make GAN Perform Better in Single Medical Image Super-Resolution? A Lesion Focused Multi-Scale Approachcited by 7
- 2018Lesion Focused Super-Resolutioncited by 5
- 2020Deep Attentive Wasserstein Generative Adversarial Networks for MRI Reconstruction with Recurrent Context-Awarenesscited by 5
- 2021JAS-GAN: Generative Adversarial Network Based Joint Atrium and Scar Segmentations on Unbalanced Atrial Targetscited by 5
- 2020Annealing Genetic GAN for Minority Oversamplingcited by 4
- 2020Automated Multi-Channel Segmentation for the 4D Myocardial Velocity Mapping Cardiac MRcited by 1
Built on by
Citing papers per year: 2022: 2; 2023: 0; 2024: 0; 2025: 1.
3 papers.