SARA-GAN: Self-Attention and Relative Average Discriminator Based Generative Adversarial Networks for Fast Compressed Sensing MRI Reconstruction

Yuan, Zhenmou; Jiang, Mingfeng; Wang, Yaming; Wei, Bo; Li, Yongming; Wang, Pin; Menpes-Smith, Wade; Niu, Zhangming; Yang, Guang

doi:10.3389/fninf.2020.611666

Cited by 60 publications

(36 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, the DA-FWGAN [ 24 ] architecture used a fine-tuning method for training the neural network and the Wasserstein distance as the discrepancy measure between the reference and reconstructed images. SARA-GAN [ 26 ] integrated the self-attention mechanism with relative average discriminator to reconstruct images with more realistic details and better integrity. Meanwhile, in contrast to most supervised deep learning reconstruction method, an unsupervised GAN based approach [ 25 ] was proposed for accelerated imaging where fully-sampled datasets are difficult to be obtained.…”

Section: Discussionmentioning

confidence: 99%

“…In addition, Cole et al [ 25 ] proposed an unsupervised GAN framework for MRI reconstruction that does not rely on fully-sampled datasets for supervision. Yuan et al [ 26 ] developed a self-attention GAN that combines the Self-Attention mechanism with Relative Average discriminator (SARA-GAN) for under-sampled k-space data reconstruction. Thanks to the long-range global dependence constructed by the self-attention module, this approach can reconstruct images with more realistic image details and higher quantitative metrics.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

PIC-GAN: A Parallel Imaging Coupled Generative Adversarial Network for Accelerated Multi-Channel MRI Reconstruction

2021

Self Cite

View full text Add to dashboard Cite

In this study, we proposed a model combing parallel imaging (PI) with generative adversarial network (GAN) architecture (PIC-GAN) for accelerated multi-channel magnetic resonance imaging (MRI) reconstruction. This model integrated data fidelity and regularization terms into the generator to benefit from multi-coils information and provide an “end-to-end” reconstruction. Besides, to better preserve image details during reconstruction, we combined the adversarial loss with pixel-wise loss in both image and frequency domains. The proposed PIC-GAN framework was evaluated on abdominal and knee MRI images using 2, 4 and 6-fold accelerations with different undersampling patterns. The performance of the PIC-GAN was compared to the sparsity-based parallel imaging (L1-ESPIRiT), the variational network (VN), and conventional GAN with single-channel images as input (zero-filled (ZF)-GAN). Experimental results show that our PIC-GAN can effectively reconstruct multi-channel MR images at a low noise level and improved structure similarity of the reconstructed images. PIC-GAN has yielded the lowest Normalized Mean Square Error (in ×10−5) (PIC-GAN: 0.58 ± 0.37, ZF-GAN: 1.93 ± 1.41, VN: 1.87 ± 1.28, L1-ESPIRiT: 2.49 ± 1.04 for abdominal MRI data and PIC-GAN: 0.80 ± 0.26, ZF-GAN: 0.93 ± 0.29, VN:1.18 ± 0.31, L1-ESPIRiT: 1.28 ± 0.24 for knee MRI data) and the highest Peak Signal to Noise Ratio (PIC-GAN: 34.43 ± 1.92, ZF-GAN: 31.45 ± 4.0, VN: 29.26 ± 2.98, L1-ESPIRiT: 25.40 ± 1.88 for abdominal MRI data and PIC-GAN: 34.10 ± 1.09, ZF-GAN: 31.47 ± 1.05, VN: 30.01 ± 1.01, L1-ESPIRiT: 28.01 ± 0.98 for knee MRI data) compared to ZF-GAN, VN and L1-ESPIRiT with an under-sampling factor of 6. The proposed PIC-GAN framework has shown superior reconstruction performance in terms of reducing aliasing artifacts and restoring tissue structures as compared to other conventional and state-of-the-art reconstruction methods.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

PIC-GAN: A Parallel Imaging Coupled Generative Adversarial Network for Accelerated Multi-Channel MRI Reconstruction

2021

Self Cite

View full text Add to dashboard Cite

show abstract

“…Meanwhile, the attention mechanism in GAN facilitates GAN to generate images that fulfill the clinical medical standards. Previous studies have shown [29][30][31][32][33] that channel-wise attention in GAN can be used to reconstruct more details in MR images than other methods without channel-wise attention. However, the spatial attention has been neglected by these approaches.…”

Section: E Spatial and Channel-wise Attentionmentioning

confidence: 99%

A Modified Generative Adversarial Network Using Spatial and Channel-Wise Attention for CS-MRI Reconstruction

Wang

2021

IEEE Access

View full text Add to dashboard Cite

Compressed sensing (CS) can speed up the magnetic resonance imaging (MRI) process and reconstruct high-quality images from under-sampled k-space data. However, traditional CS-MRI suffers from slow iterations and artifacts caused by noise when the acceleration factor is high. Currently, deep learning has been introduced to address these issues. Although some improvements have been achieved, the reconstruction problem under high under-sampling rates has not been solved. Thus, our study proposed a novel CS-MRI reconstruction method called RSCA-GAN. The generator of RSCA-GAN is a residual U-net consisting of both spatial and channel-wise attention. The proposed RSCA-GAN was compared to the zero-filling, DAGAN, RefineGAN, and RCA-GAN using both cartesian and non-cartesian undersampling masks on brain and knee datasets. The sampling rates of cartesian masks are 25%, 16.7%, and 12.5% and the sampling rates of spiral and radial masks are 30%, 20%, and 10%. Peak signal-to-noise ratio (PSNR), structural similarity (SSIM) and normalized mean square error (NMSE) were used to evaluate the reconstructed image quality, and the rank-sum test was adopted to evaluate the significant difference among different approaches. P < 0.05 indicated statistical significance. The results demonstrated that RSCA-GAN outperforms the other approaches for all the quantitative metrics. Thus, RSCA-GAN exhibits excellent reconstruction performance at high under-sampling rates and is suitable for clinical applications.

show abstract

“…Furthermore, a two-branch convolution residual network that is comprised of a two-branch convolution auto-encoder network and a residual network is proposed for CS [28]. Moreover, generative adversarial neural networks are explored in detail manner for the reconstruction of images as CS approaches [29], [30].…”

Section: Related Workmentioning

confidence: 99%

Total Variant Based Average Sparsity Model With Reweighted Analysis for Compressive Sensing of Computed Tomography

et al. 2021

View full text Add to dashboard Cite

Computed tomography (CT) in medical is an imaging procedure employed to generate detailed images of bones, soft tissue, internal organs, and blood vessels. However, prolonged acquisition time is yet a bottleneck that can lead to patient discomfort in addition to the cost constrain and exposure to X-rays used by CT. In medical imaging technologies and implementations, effective sampling and transmission techniques are some of the main areas of study to overcome such problems. To fulfill this requirement, the compressive sensing (CS) technique was introduced demonstrating that such compression is possible and can be accomplished throughout the process of data restoration; and that the uncompressed frames can be recovered employing a scalable approach of computational optimization. Sparsity averaging reweighted analysis (SARA) was proposed in compressed imaging, exploiting multi-basis sparsity with averaging approach and basis pursuit denoise (BPDN) with high signal to noise (SNR) results. In SARA, the processing time is not considered due to the high processing time because of iteration in the reweighted process and it is not feasible for the medical image that needs fast processing with high SNR result. To fulfill this gap, this paper proposes total variation based average sparsity model with reweighted analysis for CT imaging. The SNR, structural similarity index (SSIM), and processing time are used as performance metrics for the comparison of the proposed and existing techniques. From detailed experimental results, the proposed technique outperforms the existing CS techniques and is considered as a feasible solution for compressed sensing (CS) based CT images compression with faster delay process and better visual quality for medical images.INDEX TERMS Average sparsity model, compressive sensing, CT images, SARA, SNR, SSIM, total variation (TV).

show abstract

SARA-GAN: Self-Attention and Relative Average Discriminator Based Generative Adversarial Networks for Fast Compressed Sensing MRI Reconstruction

Cited by 60 publications

References 32 publications

PIC-GAN: A Parallel Imaging Coupled Generative Adversarial Network for Accelerated Multi-Channel MRI Reconstruction

PIC-GAN: A Parallel Imaging Coupled Generative Adversarial Network for Accelerated Multi-Channel MRI Reconstruction

A Modified Generative Adversarial Network Using Spatial and Channel-Wise Attention for CS-MRI Reconstruction

Total Variant Based Average Sparsity Model With Reweighted Analysis for Compressive Sensing of Computed Tomography

Contact Info

Product

Resources

About