Yufei Zhang1, Zhijun Wang1, Quan Chen1, Shuo Li1, Zekang Ding1, Chenfei Shen1, Xudong Chen1, Kang Yan1, Cong Zhang2, Xiaodong Zhou2, Yiping P. Du1, and Huajun She1
1Institute for Medical Imaging Technology, School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai, China, 2United Imaging Healthcare, Shanghai, China
Synopsis
A convolutional recurrent
neural networks (CRNN) with Non-Cartesian fidelity for
2D real-time imaging was proposed. 3D stack-of-star GRE radial sequence with
self-navigator was used to acquire the data. Multiple respiratory phases were
extracted from the navigator and the sliding window method was used to get the
training data. The Fidelity constraints
the reconstruction image to be consistent to the undersampled non-Cartesian
k-space data. Convolution and recurrence
improve the quality of the reconstructed images by using temporal dimension
information. The reconstruction speed is around 10 frames/second, which fulfills
the requirement of real-time imaging.
Introduction
Real-time MRI would be helpful in MR-guided surgery, medical robot, intervention, etc1. In interventional surgery, the electrode is sometimes inserted into the wrong place of the body due to patient movement or incorrect registration during surgery preparation. Real-time imaging would be useful for physicians to avoid this unfavorable situation, and improve the patient outcome. MRI is intrinsically slow due to the physical and physiological limitation. With the successful development of compressed sensing (CS) theory2,3, several CS techniques have been applied to accelerate imaging4,5. However, CS based methods are computational expensive, and is difficult for real-time imaging. Deep learning gives a new opportunity, due to its fast and high-quality reconstruction. While most of the deep learning methods is designed for Cartesian sampled, Cartesian is not as good as non-Cartesian sampled for dynamic MRI due to its limitation in k-space traverse. Here, we extend the deep convolutional recurrent neural network (CRNN)6, and combine with the non-Cartesian Fidelity module for real-time dynamic MRI. Trained with 3D stack-of-star GRE radial data, the Non-Cartesian CRNN (NCRNN) network reconstructs the 2D GRE radial data with a temporal resolution of 100ms and fulfils the requirements of real-time imaging. Theory and Methods
In
real-time imaging application, the NCRNN network learns the correlations in spatial and temporal domain,
and learns the correlations among iterations. As shown in Fig. 1 (c), the input
of the initial iteration is composed of undersampled images for different respiratory
phases, and the target of the output is composed of fully sampled images. The Fidelity constraints the reconstruction image to be consistent to the
undersampled k-space data. The output of the i-th iteration is inputted to the
next iteration, which will improve the quality of the output over iterations. The
Fidelity is computed as $$$ \hat{X}=\tilde{X}+\alpha
{{F}^{-1}}(Y-\beta MF\tilde{X})$$$, where $$$\tilde{X}$$$
is the output
of the CNN layers in CRNN,
$$$F$$$ is NUFFT
operator and $$${F}^{-1}$$$
is
inversion NUFFT operator,
$$$M$$$
is the
undersampling mask. $$$Y$$$ is undersampled k-space data, $$$\alpha$$$
is trainable
parameters for regularization, $$$\beta$$$
learns the
scaling factor of NUFFT operator, $$$\hat{X}$$$
is the
output of the Fidelity.
All
the data were acquired on a 3T MRI scanner (uMR790, United Imaging Healthcare, Shanghai,
China), by 3D stack-of-star GRE radial sequence with self-navigator. The center of radial k-space line was used for
navigator. Thirty respiratory phases were divided by PCA method, and the ground
truth images are reconstructed by XD-GRASP7. Thorax and abdomen images
were undersampled using reduction factor R=4. The training data has 7200 images
in total (8 volunteers×30 slices×30 respiratory phases). 5400 images were used for
training, 900 images were used for validation and 900 images were used for
test. The 4X undersampled aliased images were inputted to NCRNN, and fully
sampled images were used as ground truth. During the training, the input includes
30 images for different respiratory phases (matrix size is 128×128×30). While during the test, the input includes 30
and 10 images for different respiratory phases images (matrix size is 128×128×30 and 128×128×10). The NCRNN was implemented in Pytorch8.Results & Discussion
The architecture of NCRNN
and overall procedure of real-time imaging method by
Gadgetron9 were shown
in Fig. 1. Fig.2-4 show the
reconstructed results using NCRNN. In Fig.2-4, Columns (a-e) represent images for different respiratory
phases. The first row is the 4X undersampled images, which are the input of the
NCRNN network. The second row is the output of the NCRNN network for each
respiratory phase. The third row is the fully sampled images, which are the ground
truth during the NCRNN training. The fourth row is the difference between the
ground truth and the output for each respiratory phase. In Fig. 2 and Fig. 3
show reconstructed results of two different slice, and the input has 30
different respiratory phases. Fig.4 shows the reconstructed results of the same
slice in Fig.3, but the input has 10 different respiratory phases. The NCRNN show
the compatibility for different input size. Fig. 5 shows the comparison between NCRNN and
XD-GRASP. (a) NUFFT reconstructed 4X undersampled image. (b) Output of the NCRNN
network, with structural similarity index (SSIM) = 0.8823 compared
with the ground truth. (c) XD-GRASP reconstruction, with SSIM = 0.9023 compared
with the ground truth. (d) The ground truth. The absolute value of difference times
2 of the fully sampled image with reconstrued images of different methods
were shown in (e-g).Conclusion
We proposed and evaluated a deep learning
reconstruction method for real-time imaging by NCRNN network. The in vivo results
demonstrate that at acceleration rate R=4, the reconstruction quality of NCRNN
is comparable to XD-GRASP, while the reconstruction time is only 100ms compared with
40s of XD-GRASP, fulfilling the requirements of real-time imaging. Acknowledgements
The authors thank United Imaging Healthcare for making the United
Imaging Healthcare(UIH) Application Development Environment and Programming Tools (ADEPT) available for convenient development of the MRI pulse sequences and real-time imaging system.References
[1] Emmanuel Candes, et al. Robust
uncertainty principles: exact signal reconstruction from highly incomplete
frequency information. IEEE Trans Inf Theory. 2006; 52:489‐509.
[2] Donoho DL. Compressed sensing.
IEEE Trans Inf Theory. 2006; 52:1289‐1306.
[3] Lingala SG, et al. Blind
compressed sensing dynamic MRI. IEEE Trans Med Imaging. 2013; 32:1132‐1145.
[4] Otazo R, et al. Combination of
Compressed Sensing and Parallel Imaging for Highly Accelerated First-Pass
Cardiac Perfusion MRI. MRM 2010; 64:767–776.
[5] Lustig M, et al. Sparse MRI:
The Application of Compressed Sensing for Rapid MR Imaging. MRM 2007; 58:1182–1195.
[6]
Qin C, et al. Convolutional Recurrent Neural Networks for Dynamic MR Image
Reconstruction. arXiv:1712.01751.
[7] Feng, et al. XD‐GRASP:
Golden‐angle radial MRI with reconstruction of extra motion‐state dimensions
using compressed sensing. MRM 2016; 75:775–788.
[8] https://pytorch.org
[9] http://gadgetron.github.io