Deep learning for undersampled MRI reconstruction

Hyun, Chang Min; Kim, Hwa Pyung; Lee, Sung Min; Lee, Sungchul; Seo, Jin Keun

doi:10.1088/1361-6560/aac71a

Cited by 392 publications

(305 citation statements)

References 18 publications

Supporting

Mentioning

300

Contrasting

Unclassified

Order By: Relevance

“…Previous literature in deep learning‐based MR image reconstruction only shows the feasibility of reconstruction with single‐coil data and lacks a clear demonstration of how the clinical multiple‐coil data are handled. Compared to the selected single‐coil–based network used in this work, the proposed PI‐CNN network includes multicoil information to allow the network to better de‐alias the artifact‐contaminated zero‐filled input image.…”

Section: Discussionmentioning

confidence: 99%

Parallel imaging and convolutional neural network combined fast MR image reconstruction: Applications in low‐latency accelerated real‐time imaging

et al. 2019

View full text Add to dashboard Cite

Purpose To develop and evaluate a parallel imaging and convolutional neural network combined image reconstruction framework for low‐latency and high‐quality accelerated real‐time MR imaging. Methods Conventional Parallel Imaging reconstruction resolved as gradient descent steps was compacted as network layers and interleaved with convolutional layers in a general convolutional neural network. All parameters of the network were determined during the offline training process, and applied to unseen data once learned. The proposed network was first evaluated for real‐time cardiac imaging at 1.5 T and real‐time abdominal imaging at 0.35 T, using threefold to fivefold retrospective undersampling for cardiac imaging and threefold retrospective undersampling for abdominal imaging. Then, prospective undersampling with fourfold acceleration was performed on cardiac imaging to compare the proposed method with standard clinically available GRAPPA method and the state‐of‐the‐art L1‐ESPIRiT method. Results Both retrospective and prospective evaluations confirmed that the proposed network was able to images with a lower noise level and reduced aliasing artifacts in comparison with the single‐coil based and L1‐ESPIRiT reconstructions for cardiac imaging at 1.5 T, and the GRAPPA and L1‐ESPIRiT reconstructions for abdominal imaging at 0.35 T. Using the proposed method, each frame can be reconstructed in less than 100 ms, suggesting its clinical compatibility. Conclusion The proposed Parallel Imaging and convolutional neural network combined reconstruction framework is a promising technique that allows low‐latency and high‐quality real‐time MR imaging.

show abstract

Section: Discussionmentioning

confidence: 99%

Parallel imaging and convolutional neural network combined fast MR image reconstruction: Applications in low‐latency accelerated real‐time imaging

et al. 2019

View full text Add to dashboard Cite

show abstract

“…The first X‐net was trained to reconstruct fully sampled T1‐ and T2‐weighted images from down‐sampled T1‐ and T2‐weighted images. The reconstructed T1‐ and T2‐weighted images were Fourier‐transformed to be combined with the original k‐space data in the frequency domain for data consistency . For refining purposes, another X‐net was trained with patch augmentation to reconstruct fully sampled T1‐ and T2‐weighted images from the combination of the output of the first X‐net and the original data.…”

Section: Methodsmentioning

confidence: 99%

Reconstruction of multicontrast MR images through deep learning

et al. 2020

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

“…To evaluate the effectiveness of DPI‐net, we also compared it with U‐net, a conventional deep‐learning method that has been widely used for undersampled MR image reconstruction . The original U‐net was slightly modified to be effectively applicable to our data sets in this study.…”

Section: Methodsmentioning

confidence: 99%

“…In recent years, various deep‐learning–based methods have been proposed, with convolutional neural networks (CNNs), an architecture widely used in deep‐learning, outperforming conventional image processing algorithms in image super‐resolution, denoising, and inpainting . Several studies have applied deep‐learning to processing medical images, especially for MR image reconstruction from undersampled k‐space data, demonstrating better performance than with the conventional compressed sensing or PI‐based methods even when the reduction factor was high …”

Section: Introductionmentioning

confidence: 99%

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

Deep learning for undersampled MRI reconstruction

Cited by 392 publications

References 18 publications

Parallel imaging and convolutional neural network combined fast MR image reconstruction: Applications in low‐latency accelerated real‐time imaging

Parallel imaging and convolutional neural network combined fast MR image reconstruction: Applications in low‐latency accelerated real‐time imaging

Reconstruction of multicontrast MR images through deep learning

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

Contact Info

Product

Resources

About