Real‐time cardiovascular MR with spatio‐temporal artifact suppression using deep learning–proof of concept in congenital heart disease

Hauptmann, Andreas; Arridge, Simon R.; Lucka, Felix; Muthurangu, Vivek; Steeden, Jennifer A.

doi:10.1002/mrm.27480

Cited by 181 publications

(205 citation statements)

References 25 publications

Supporting

Mentioning

203

Contrasting

Order By: Relevance

“…Owing to the effective de‐aliasing performance of U‐Net, the C‐net can remove aliasing artifacts, even at high AFs. This is consistent with other results in previous works . However, some structural details are still blurred and distorted in the lung, as shown in Figure C1,C2.…”

Section: Discussionsupporting

confidence: 93%

“…This is consistent with other results in previous works. 29,30,45 However, some structural details are still blurred and distorted in the lung, as shown in Figure 3C1,C2. The reason may be that the training data is corrupted by noise, which prevents the CNNs from learning the mapping between the zero-filling and reference images.…”

Section: Performance Comparisonsmentioning

confidence: 99%

See 1 more Smart Citation

Fast and accurate reconstruction of human lung gas MRI with deep learning

Duan

Xiao

et al. 2019

Magnetic Resonance in Med

View full text Add to dashboard Cite

Purpose To fast and accurately reconstruct human lung gas MRI from highly undersampled k‐space using deep learning. Methods The scheme was comprised of coarse‐to‐fine nets (C‐net and F‐net). Zero‐filling images from retrospectively undersampled k‐space at an acceleration factor of 4 were used as input for C‐net, and then output intermediate results which were fed into F‐net. During training, a L2 loss function was adopted in C‐net, while a function that united L2 loss with proton prior knowledge was used in F‐net. The 871 hyperpolarized 129Xe pulmonary ventilation images from 72 volunteers were randomly arranged as training (90%) and testing (10%) data. Ventilation defect percentage comparisons were implemented using a paired 2‐tailed Student's t‐test and correlation analysis. Furthermore, prospective acquisitions were demonstrated in 5 healthy subjects and 5 asymptomatic smokers. Results Each image with size of 96 × 84 could be reconstructed within 31 ms (mean absolute error was 4.35% and structural similarity was 0.7558). Compared with conventional compressed sensing MRI, the mean absolute error decreased by 17.92%, but the structural similarity increased by 6.33%. For ventilation defect percentage, there were no significant differences between the fully sampled and reconstructed images through the proposed algorithm (P = 0.932), but had significant correlations (r = 0.975; P < 0.001). The prospectively undersampled results validated a good agreement with fully sampled images, with no significant differences in ventilation defect percentage but significantly higher signal‐to‐noise ratio values. Conclusion The proposed algorithm outperformed classical undersampling methods, paving the way for future use of deep learning in real‐time and accurate reconstruction of gas MRI.

show abstract

Section: Discussionsupporting

confidence: 93%

Section: Performance Comparisonsmentioning

confidence: 99%

Fast and accurate reconstruction of human lung gas MRI with deep learning

Duan

Xiao

et al. 2019

Magnetic Resonance in Med

View full text Add to dashboard Cite

show abstract

“…The net is trained to map whole image sequences to whole image sequences by aligning the cardiac phases along the channel's axis and was presented in [20]. Further, we compare our method to the 3D U-net approach u xyt presented in [21], see Figure 1 (c). While for the 2D NNs, we cropped the images to 220 × 220 and 220 × 220 × 30 in order to let the networks focus on the diagnostic content of the images, for the 3D U-net, the images used for training needed to be cropped to 128 × 128 × 20, as the network is computationally more expensive.…”

Section: H Comparison With Other Deep Learning-based Methodsmentioning

confidence: 99%

Spatio-Temporal Deep Learning-Based Undersampling Artefact Reduction for 2D Radial Cine MRI With Limited Training Data

Kofler

Dewey

Schaeffter

et al. 2020

IEEE Trans. Med. Imaging

View full text Add to dashboard Cite

In this work we reduce undersampling artefacts in two-dimensional (2D) golden-angle radial cine cardiac MRI by applying a modified version of the U-net. The network is trained on 2D spatio-temporal slices which are previously extracted from the image sequences. We compare our approach to two 2D and a 3D Deep Learning-based post processing methods, three iterative reconstruction methods and two recently proposed methods for dynamic cardiac MRI based on 2D and 3D cascaded networks. Our method outperforms the 2D spatially trained U-net and the 2D spatio-temporal U-net. Compared to the 3D spatiotemporal U-net, our method delivers comparable results, but requiring shorter training times and less training data. Compared to the Compressed Sensing-based methods kt-FOCUSS and a total variation regularized reconstruction approach, our method improves image quality with respect to all reported metrics. Further, it achieves competitive results when compared to the iterative reconstruction method based on adaptive regularization with Dictionary Learning and total variation and when compared to the methods based on cascaded networks, while only requiring a small fraction of the computational and training time. A persistent homology analysis demonstrates that the data manifold of the spatio-temporal domain has a lower complexity than the one of the spatial domain and therefore, the learning of a projection-like mapping is facilitated. Even when trained on only one single subject without data-augmentation, our approach yields results which are similar to the ones obtained on a large training dataset. This makes the method particularly suitable for training a network on limited training data. Finally, in contrast to the spatial 2D U-net, our proposed method is shown to be naturally robust with respect to image rotation in image space and almost achieves rotation-equivariance where neither dataaugmentation nor a particular network design are required.

show abstract

“…The advantage in this approach lies in the analytical knowledge of the reconstruction operator, and hence networks can be designed to exploit structure in reconstruction artefacts. For instance in spatio-temporal problems, if under-sampling artefacts are known to be incoherent in time, the network only needs to learn to combine the spatial information by a temporal interpolation [27]. On the other hand, for lower dimensional 3 problems, the capacity of the network is essentially limited by the richness of the training data [28], [29].…”

Section: A Reconstruction and Post-processingmentioning

confidence: 99%

Multi-Scale Learned Iterative Reconstruction

Hauptmann

Adler

Arridge

et al. 2020

IEEE Trans. Comput. Imaging

Self Cite

View full text Add to dashboard Cite

Model-based learned iterative reconstruction methods have recently been shown to outperform classical reconstruction methods. Applicability of these methods to large scale inverse problems is however limited by the available memory for training and extensive training times. As a possible solution to these restrictions we propose a multi-scale learned iterative reconstruction algorithm that computes iterates on discretisations of increasing resolution. This procedure does not only reduce memory requirements, it also considerably speeds up reconstruction and training times, but most importantly is scalable to large scale inverse problems, like those that arise in 3D tomographic imaging. Feasibility of the proposed method to speed up training and computation times in comparison to established learned reconstruction methods in 2D is demonstrated for low dose computed tomography (CT), for which we utilise the data base of abdominal CT scans provided for the 2016 AAPM lowdose CT grand challenge. * Equal contribution.A. Hauptmann is with the Research

show abstract

Real‐time cardiovascular MR with spatio‐temporal artifact suppression using deep learning–proof of concept in congenital heart disease

Cited by 181 publications

References 25 publications

Fast and accurate reconstruction of human lung gas MRI with deep learning

Fast and accurate reconstruction of human lung gas MRI with deep learning

Spatio-Temporal Deep Learning-Based Undersampling Artefact Reduction for 2D Radial Cine MRI With Limited Training Data

Multi-Scale Learned Iterative Reconstruction

Contact Info

Product

Resources

About