Deep Residual Learning for Accelerated MRI Using Magnitude and Phase Networks

Lee, Dongwook; Yoo, Jaejun; Tak, Sungho; Ye, Jong Chul

doi:10.1109/tbme.2018.2821699

Cited by 275 publications

(210 citation statements)

References 53 publications

Supporting

Mentioning

196

Contrasting

Unclassified

Order By: Relevance

“…Under our experimental condition, uniform sampling with densely sampled center lines of 70% of all under-sampled phase encoding lines was appropriate for X-net reconstruction. As observable in previous work, 13 reconstructions by the proposed networks from too high or low a percentage of densely sampled center are expected to have reduced details or residual artifacts respectively. When the acceleration factor was 8, both outputs from X-net and Y-net were slightly blurred.…”

Section: Discussionsupporting

confidence: 62%

“…This scheme can induce fast convergence during network training. Therefore, the U‐net convolutional network combined with a residual learning scheme has shown great success in many image processing applications . However, it continues to be difficult to reduce the MR scan time significantly when using a convolutional network, as the reconstructed image becomes blurred or visually different from the fully sampled image, a problem which is more severe at higher acceleration factors.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Reconstruction of multicontrast MR images through deep learning

et al. 2020

Self Cite

View full text Add to dashboard Cite

Purpose Magnetic resonance (MR) imaging with a long scan time can lead to degraded images due to patient motion, patient discomfort, and increased costs. For these reasons, the role of rapid MR imaging is important. In this study, we propose the joint reconstruction of multicontrast brain MR images from down‐sampled data to accelerate the data acquisition process using a novel deep‐learning network. Methods Twenty‐one healthy volunteers (female/male = 7/14, age = 26 ± 4 yr, range 22–35 yr) and 16 postoperative patients (female/male = 7/9, age = 49 ± 9 yr, range 37–62 yr) were scanned on a 3T whole‐body scanner for prospective and retrospective studies, respectively, using both T1‐weighted spin‐echo (SE) and T2‐weighted fast spin‐echo (FSE) sequences. We proposed a network which we term “X‐net” to reconstruct both T1‐ and T2‐weighted images from down‐sampled images as well as a network termed “Y‐net” which reconstructs T2‐weighted images from highly down‐sampled T2‐weighted images and fully sampled T1‐weighted images. Both X‐net and Y‐net are composed of two concatenated subnetworks. We investigate optimal sampling patterns, the optimal patch size for augmentation, and the optimal acceleration factors for network training. An additional Y‐net combined with a generative adversarial network (GAN) was also implemented and tested to investigate the effects of the GAN on the Y‐net performance. Single‐ and joint‐reconstruction parallel‐imaging and compressed‐sensing algorithms along with a conventional U‐net were also tested and compared with the proposed networks. For this comparison, the structural similarity (SSIM), normalized mean square error (NMSE), and Fréchet inception distance (FID) were calculated between the outputs of the networks and fully sampled images. The statistical significance of the performance was evaluated by assessing the interclass correlation and in paired t‐tests. Results The outputs from the two concatenated subnetworks were closer to the fully sampled images compared to those from one subnetwork, with this result showing statistical significance. Uniform down‐sampling led to a statically significant improvement in the image quality compared to random or central down‐sampling patterns. In addition, the proposed networks provided higher SSIM and NMSE values than U‐net, compressed‐sensing, and parallel‐imaging algorithms, all at statistically significant levels. The GAN‐based Y‐net showed a better FID and more realistic images compared to a non‐GAN‐based Y‐net. The performance capabilities of the networks were similar between normal subjects and patients. Conclusions The proposed X‐net and Y‐net effectively reconstructed full images from down‐sampled images, outperforming the conventional parallel‐imaging, compressed‐sensing and U‐net methods and providing more realistic images in combination with a GAN. The developed networks potentially enable us to accelerate multicontrast anatomical MR imaging in routine clinical studies including T1‐and T2‐weighted imaging.

show abstract

Section: Discussionsupporting

confidence: 62%

Section: Introductionmentioning

confidence: 99%

Reconstruction of multicontrast MR images through deep learning

et al. 2020

Self Cite

View full text Add to dashboard Cite

show abstract

“…Supporting Information Figure shows that adding phase information did not improve the performance in recovering the vessel signals and removing aliasing artifacts. One study has been proposed that the magnitude network, which was trained with magnitude input, showed better performance than the complex network, which was trained with 2 channels of real and imaginary components . In our case, the 3D TOF MRA does not require phase information in MIP images.…”

Section: Discussionmentioning

confidence: 75%

Parallel imaging in time‐of‐flight magnetic resonance angiography using deep multistream convolutional neural networks

Jun

Shin

et al. 2019

Magnetic Resonance in Med

View full text Add to dashboard Cite

Purpose To develop and evaluate a method of parallel imaging time‐of‐flight (TOF) MRA using deep multistream convolutional neural networks (CNNs). Methods A deep parallel imaging network (“DPI‐net”) was developed to reconstruct 3D multichannel MRA from undersampled data. It comprises 2 deep‐learning networks: a network of multistream CNNs for extracting feature maps of multichannel images and a network of reconstruction CNNs for reconstructing images from the multistream network output feature maps. The images were evaluated using normalized root mean square error (NRMSE), peak signal‐to‐noise ratio (PSNR), and structural similarity (SSIM) values, and the visibility of blood vessels was assessed by measuring the vessel sharpness of middle and posterior cerebral arteries on axial maximum intensity projection (MIP) images. Vessel sharpness was compared using paired t tests, between DPI‐net, 2 conventional parallel imaging methods (SAKE and ESPIRiT), and a deep‐learning method (U‐net). Results DPI‐net showed superior performance in reconstructing vessel signals in both axial slices and MIP images for all reduction factors. This was supported by the quantitative metrics, with DPI‐net showing the lowest NRMSE, the highest PSNR and SSIM (except R = 3.8 on sagittal MIP images, and R = 5.7 on axial slices and sagittal MIP images), and significantly higher vessel sharpness values than the other methods. Conclusion DPI‐net was effective in reconstructing 3D TOF MRA from highly undersampled multichannel MR data, achieving superior performance, both quantitatively and qualitatively, over conventional parallel imaging and other deep‐learning methods.

show abstract

“…The basic block of residual is to use a shortcut during two contiguous convolutional layers. Residual learning has achieved impressive performance on image low-level tasks, such as reconstruction [18]- [21], super-resolution [22]- [24], denoising [25]- [27], deraining [28]- [30], etc.…”

Section: Related Workmentioning

confidence: 99%

Compressed sensing MRI via a multi-scale dilated residual convolution network

Dai

Zhuang

2019

Magnetic Resonance Imaging

View full text Add to dashboard Cite

Magnetic resonance imaging (MRI) reconstruction is an active inverse problem which can be addressed by conventional compressed sensing (CS) MRI algorithms that exploit the sparse nature of MRI in an iterative optimization-based manner. However, two main drawbacks of iterative optimization-based CSMRI methods are time-consuming and are limited in model capacity. Meanwhile, one main challenge for recent deep learning-based CSMRI is the trade-off between model performance and network size. To address the above issues, we develop a new multi-scale dilated network for MRI reconstruction with high speed and outstanding performance. Comparing to convolutional kernels with same receptive fields, dilated convolutions reduce network parameters with smaller kernels and expand receptive fields of kernels to obtain almost same information. To maintain the abundance of features, we present global and local residual learnings to extract more image edges and details. Then we utilize concatenation layers to fuse multi-scale features and residual learnings for better reconstruction. Compared with several non-deep and deep learning CSMRI algorithms, the proposed method yields better reconstruction accuracy and noticeable visual improvements. In addition, we perform the noisy setting to verify the model stability, and then extend the proposed model on a MRI super-resolution task.Multi-scale.The first category of CSMRI algorithms are iterative optimization-based CSMRI, in which the sparsity is enforced in specific transform domain or underlying latent representation of images, and then an alternating iterative optimization scheme is adopted to CSMRI reconstruction [2]- [11]. A pioneering work of CSMRI is Sparse MRI [2], which exploits an off-the-shelf basis to capture a specific feature (wavelets recover point-like features, contourlets capture curvelike features). A hybrid TV regularizer combined with a L 0 -regularized treestructured sparsity constraint [3] is introduced to overcome model-dependent difference 0.69/0.003 3.21/0.032 0.49/0.011 and Fig. 13. It is noted that the proposed MDN performs better reconstruction results than VDSR on a huge dataset. CONCLUSION AND PROSPECTA novel multi-scale dilated network (MDN) has been presented for CSMRI. The proposed MDN is composed by cascading two basic blocks where dilated convolutions, global and local residual learnings, and concatenation layers are integrated to extend the receptive fields of convolutional kernels for reducing network parameters, maintaining features abundance, and fusing multi-scale features, respectively. Final experiments demonstrate that MDN achieves outstanding performance with training huge and diverse data, and the proposed network outperforms several competitive CSMRI algorithms in subjective and objective assessments. In addition, the proposed model is effective in MR noisy

show abstract

Deep Residual Learning for Accelerated MRI Using Magnitude and Phase Networks

Abstract: The proposed deep learning framework may have a great potential for accelerated MR reconstruction by generating accurate results immediately.

Cited by 275 publications

References 53 publications

Reconstruction of multicontrast MR images through deep learning

Reconstruction of multicontrast MR images through deep learning

Parallel imaging in time‐of‐flight magnetic resonance angiography using deep multistream convolutional neural networks

Compressed sensing MRI via a multi-scale dilated residual convolution network

Contact Info

Product

Resources

About