A deep unrolling network inspired by total variation for compressed sensing MRI

Zhang, Xiaohua; Lian, Qiusheng; Yang, Yuchi; Su, Yueming

doi:10.1016/j.dsp.2020.102856

Cited by 28 publications

(14 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Another issue with deep-learning-based CS-MRI models is their generalizability to different datasets or applications. A few studies report robust performance of the models across different datasets and noise levels [21], [27], [98], [128]. However, one study shows better performance in T1 weighted images compared with FLAIR MR images [8], and another displays higher reconstruction errors in fat-containing regions [147].…”

Section: C H a L L E N G E Smentioning

confidence: 99%

AI-Based Reconstruction for Fast MRI—A Systematic Review and Meta-Analysis

et al. 2022

View full text Add to dashboard Cite

show abstract

Section: C H a L L E N G E Smentioning

confidence: 99%

AI-Based Reconstruction for Fast MRI—A Systematic Review and Meta-Analysis

et al. 2022

View full text Add to dashboard Cite

show abstract

“…In unrolled optimization, these terms can be learned rather than manually designed. ADMM-Net [63,65], VarNet (Variational Network) [55] and TVINet (Total Variation Inspired Network) [64], which unroll ADMM, GD and PDHG, respectively, use this formulation. All three explicitly learn linear sparsifying transforms D, parameterized by convolutional layers, and non-linear sparsity-promoting functions R .…”

Section: Unrolled Optimizationmentioning

confidence: 99%

Machine learning in Magnetic Resonance Imaging: Image reconstruction

et al. 2021

View full text Add to dashboard Cite

Magnetic Resonance Imaging (MRI) plays a vital role in diagnosis, management and monitoring of many diseases. However, it is an inherently slow imaging technique. Over the last 20 years, parallel imaging, temporal encoding and compressed sensing have enabled substantial speed-ups in the acquisition of MRI data, by accurately recovering missing lines of k-space data. However, clinical uptake of vastly accelerated acquisitions has been limited, in particular in compressed sensing, due to the time-consuming nature of the reconstructions and unnatural looking images. Following the success of machine learning in a wide range of imaging tasks, there has been a recent explosion in the use of machine learning in the field of MRI image reconstruction.A wide range of approaches have been proposed, which can be applied in k-space and/or image-space.Promising results have been demonstrated from a range of methods, enabling natural looking images and rapid computation.In this review article we summarize the current machine learning approaches used in MRI reconstruction, discuss their drawbacks, clinical applications, and current trends.

show abstract

“…The second term in Eq 3 ensures the reconstructed image possesses certain attributes such as smoothness or sparsity, which is required by the theory of CS. For example, total variation-an early CS technique-uses the following regulariser term to ensure the underlying image is smooth [2,71]:…”

Section: Fundamentals Of Mri Reconstructionmentioning

confidence: 99%

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

Yang¹,

Lv²,

Chen³

et al. 2021

Preprint

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

A deep unrolling network inspired by total variation for compressed sensing MRI

Cited by 28 publications

References 50 publications

AI-Based Reconstruction for Fast MRI—A Systematic Review and Meta-Analysis

AI-Based Reconstruction for Fast MRI—A Systematic Review and Meta-Analysis

Machine learning in Magnetic Resonance Imaging: Image reconstruction

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

Contact Info

Product

Resources

About