Which GAN? A comparative study of generative adversarial network-based fast MRI reconstruction

Lv, Jun; Zhu, Jin; Yang, Guang

doi:10.1098/rsta.2020.0203

Cited by 23 publications

(13 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…On top of the CNNs, conditional generative adversarial networks (cGANs) exploited the advantages of deep learning further and proved to enhance the quality of the MR image reconstruction to a large extent [48,49]. Such a competitive network introduced a two-player generator-discriminator training mechanism to competitively improve reconstruction performance by alternatively optimising θ G and θ D of the generator G and the discriminator D, in a general form as:…”

Section: Cnn-based Fast Mri Reconstructionmentioning

confidence: 99%

Swin Transformer for Fast MRI

Huang¹,

Fang²,

Wu³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Magnetic resonance imaging (MRI) is an important non-invasive clinical tool that can produce high-resolution and reproducible images. However, a long scanning time is required for high-quality MR images, which leads to exhaustion and discomfort of patients, inducing more artefacts due to voluntary movements of the patients and involuntary physiological movements. To accelerate the scanning process, methods by k -space undersampling and deep learning based reconstruction have been popularised. This work introduced SwinMR, a novel Swin transformer based method for fast MRI reconstruction. The whole network consisted of an input module (IM), a feature extraction module (FEM) and an output module (OM). The IM and OM were 2D convolutional layers and the FEM was composed of a cascaded of residual Swin transformer blocks (RSTBs) and 2D convolutional layers. The RSTB

show abstract

Section: Cnn-based Fast Mri Reconstructionmentioning

confidence: 99%

Swin Transformer for Fast MRI

Huang¹,

Fang²,

Wu³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Conditional generative models take observed data as an input to a generator and output an image reconstruction, with a discriminator evaluating the reconstructions [4,75,99,60]. This approach is limited by the need for large amounts of paired training data and the known difficulties in GAN training such as mode collapse.…”

Section: Other Approachesmentioning

confidence: 99%

Regularising Inverse Problems with Generative Machine Learning Models

Duff¹,

Campbell²,

Ehrhardt³

2021

Preprint

View full text Add to dashboard Cite

Deep neural network approaches to inverse imaging problems have produced impressive results in the last few years. In this paper, we consider the use of generative models in a variational regularisation approach to inverse problems. The considered regularisers penalise images that are far from the range of a generative model that has learned to produce images similar to a training dataset. We name this family generative regularisers. The success of generative regularisers depends on the quality of the generative model and so we propose a set of desired criteria to assess models and guide future research. In our numerical experiments, we evaluate three common generative models, autoencoders, variational autoencoders and generative adversarial networks, against our desired criteria. We also test three different generative regularisers on the inverse problems of deblurring, deconvolution, and tomography. We show that the success of solutions restricted to lie exactly in the range of the generator is highly dependent on the ability of the generative model but that allowing small deviations from the range of the generator produces more consistent results.

show abstract

“…To date, however, the majority of research studies have concentrated on downstream medical image interpretation and postprocessing activities, such as anatomical segmentation [18,19,20,21,22,23,24,25,26,27,28], lesion segmentation [29,30,31,32,33,34], co-registration [35,36,37], synthesis [38,39], and multimodal data detection [40,41,42,43,44,45,46], for disease identification [47,48,49], prognosis [50,51], and treatment prediction [52,53]. To increase the precision of these post-processing operations, imaging methods must be improved, which can also be aided by deep learning [54,55,56,57,58,59,60]. Since its principle was developed in 2006, CS has had a long history for fast imaging applications, including the embodiment of MRI reconstruction [61].…”

Section: Deep Learning Based Fast Mrimentioning

confidence: 99%

Generative Adversarial Networks (GAN) Powered Fast Magnetic Resonance Imaging -- Mini Review, Comparison and Perspectives

Yang¹,

Lv²,

Chen³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

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.

show abstract

Which GAN? A comparative study of generative adversarial network-based fast MRI reconstruction

Cited by 23 publications

References 51 publications

Swin Transformer for Fast MRI

Swin Transformer for Fast MRI

Regularising Inverse Problems with Generative Machine Learning Models

Generative Adversarial Networks (GAN) Powered Fast Magnetic Resonance Imaging -- Mini Review, Comparison and Perspectives

Contact Info

Product

Resources

About