Hongyu Li1, Mingrui Yang2, Jeehun Kim2, Ruiying Liu1, Chaoyi Zhang1, Peizhou Huang1, Sunil Kumar Gaire1, Dong Liang3, Xiaojuan Li2, and Leslie Ying1
1Department of Biomedical Engineering, Department of Electrical Engineering, The State University of New York at Buffalo, Buffalo, NY, United States, 2Program of Advanced Musculoskeletal Imaging (PAMI), Cleveland Clinic, Cleveland, OH, United States, 3Paul C. Lauterbur Research Center for Biomedical Imaging, Medical AI research center, SIAT, CAS, Shenzhen, China
Synopsis
This
abstract presents a deep learning method to generate MR parameter maps from very
few subsampled echo images. The method uses deep convolutional neural networks
to learn the nonlinear relationship between the subsampled T1rho/T2-weighted images
and the T1rho/T2 maps, bypassing the conventional exponential decay models. Experimental results show that the
proposed method is able to generate T1rho/T2 maps
from only 2 subsampled echo images with quantitative values comparable to those
of the T1rho/T2 maps generated from fully-sampled 8 echo images using the conventional
exponential decay curve fitting.
Introduction
With
the conventional model fitting method, 4-8 echoes are typically necessary for reliable estimation of the parameter maps, resulting
in the prolonged acquisition. It is of great interest to accelerate quantitative imaging to increase its clinical use.
Deep learning methods have been used
recently to accelerate MR acquisition by reconstructing images from subsampled
k-space data1-6. The
learning-based reconstruction methods have the benefit of ultrafast online
reconstruction once the offline training is completed. Although there are quite
some works on deep reconstruction of morphological images, very few works have studied tissue parameter
mapping7-9. In
this abstract, we develop a deep learning-based framework for ultrafast quantitative MR imaging. Different
from the existing works using deep learning for parameter mapping, our network learns
the information in both spatial and temporal directions such that both the
k-space measurement and the echoes can be reduced. Specifically, we formulate
the problem of parameter mapping as a deep network with multi-channel input (images
from different echoes) problem based on our previous network10 for
diffusion tensor imaging. The purpose of this study is to demonstrate the
feasibility of such a framework, named Model Skipped Convolutional Neural
Network (MSCNN), for ultrafast T1rho/ T2 mapping. Using
knee cartilage data, we demonstrate for the first time the feasibility of T1rho/T2
mapping using as few as 2 subsampled (in k-space) echo images with quantitative
maps comparable to those from fully sampled 8 echo images.
Theory and Methods
The proposed MSCNN reconstructs parametric maps directly from subsampled
echo images using a deep CNN. In our network, the goal is to learn the nonlinear relationship $$$F$$$ between input $$$x$$$ and output $$$y$$$, which is
represented as $$$y=F(x;Θ),$$$ where $$$Θ$$$ is the DL parameters to be
learned during training. Learning of such a mapping is achieved through
minimizing a loss function between the
network prediction and the corresponding ground truth data. In line with our
prior study for diffusion tensor imaging using reduced acquisition10, the loss term $$$L(Θ)=\frac{1}{n}\sum_{i=1}^{n}\| F(x_{i};Θ) -y_{i}\|^{2} (1)$$$ ensures that the reconstructed parameter maps from the end-to-end CNN are
consistent with the maps from the fully sampled echo images while by-passing
the conventional error-prone model fitting step. During the training stage, a reduced number of subsampled echo images are
used as the inputs $$$x_{i}$$$ and the corresponding reference T1rho/T2 maps $$$y_{i}$$$ (obtained by fitting all 8 fully sampled echo
images) as the output. We learn the deep learning network parameters $$$Θ$$$ that minimize the loss function, which is the
mean-square error between the network output and the reference T1rho/T2 maps (n is the number of
training dataset). For our network,
ten weighted layers were used for the training and testing. For each layer
except the last one, 64 filters with kernel size of 3 are used. The deep network exploits both the spatial correlation
among pixels and the temporal correlation between the selected echoes, while learning the complicated nonlinear
relationship between the subsampled T1rho/T2 weighted images and the T1rho/T2
maps.
Ten sets of knee data were collected at a 3T MR scanner
(Prisma, Siemens Healthineers) with a 1Tx/15Rx knee coil (QED), using a
magnetization-prepared angle-modulated partitioned k-space spoiled gradient
echo snapshots (MAPSS) T1ρ and T2
quantification sequences (time of spin-lock [TSLs] of 0, 10, 20, 30, 40, 50,
60, 70ms, spin-lock frequency 500Hz, Preparation TEs of 0,
9.7, 21.3, 32.9, 44.5, 56.1, 67.6, 79.2 ms, matrix size 160×320×8×24 [PE×FE×Echo×Slice], FOV 14cm, and slice thickness 4mm). Among them, 8 datasets were used to train the proposed MSCNN and 2 for testing. In the initial experiment, echo 1, 3 and 8 were selected
out of 8, and 2D Poisson random sampling was used with an acceleration
factor of 2 (joint AF 5.33). For further acceleration, only the
first and the last echoes were selected. A 2D Poisson random sampling pattern was used with an additional acceleration factor of 2 and 3. Parameter maps were generated with joint reduction factors of 4 (no AF in echo1&8), 8 (AF2), and 12 (AF3). Hardware specification: i9 7980XE; 64 GB; 2x NVIDIA GTX 1080Ti. Training took around 10
hours. Testing only takes 0.07 seconds to generate a complete set of T1rho/T2
map through learned network, which is in contrast to the ~15 min processing
time for the conventional exponential decay curve fitting.Results
Figures 1 and 2 show the generated T1rho and T2 maps using proposed MSCNN with different echo undersampling and different k-space subsampling. Results from all 8 echoes using the conventional fitting
model are shown as the reference. It can be seen that the quantitative maps generated by MSCNN are very close to the reference even with only 2 subsampled echo images. Performance is further verified by the NMSE shown on the bottom left of each image. Conclusion
In this abstract, we present a deep convolutional
neural network MSCNN for superfast MR quantitative imaging. The network
exploits both spatial and temporal information from the training datasets. Experimental
results show that our proposed network is capable of generating T1rho/T2 mapping
from as few as 2 subsampled echo images. Future
studies will use larger dataset for evaluating quantification accuracy and
diagnostic performance. Acknowledgements
The work was partly supported by the Arthritis Foundation.References
[1] Wang S, Su Z, Ying L,
Peng X, Liang D, et al. Accelerating magnetic resonance imaging via deep
learning. IEEE 14th International Symposium on Biomedical Imaging (ISBI), pp.
514-517, Apr. 2016.
[2] Wang S, Huang N, Ying
L, Liang D, et al. 1D Partial Fourier Parallel MR imaging with deep
convolutional neural network. Proceedings of International Society of Magnetic
Resonance in Medicine Scientific Meeting, 2017.
[3] Lee D, Yoo J, et al. Deep
residual learning for compressed sensing MRI. IEEE 14th International Symposium
on Biomedical Imaging (ISBI), Melbourne, VIC, pp. 15-18, Apr. 2017.
[4] Wang S, Zhao T, Ying L,
and Liang D. Feasibility of Multi-contrast MR imaging via deep learning. Proceedings
of International Society of Magnetic Resonance in Medicine Scientific Meeting,
2017.
[5] Schlemper J, Caballero
J, et al. A Deep Cascade of Convolutional Neural Networks for Dynamic MR Image
Reconstruction. arXiv:1704.02422, 2017.
[6] Jin K H, McCann M T et
al. Deep Convolutional Neural Network for Inverse Problems in Imaging. in IEEE Transactions on Image Processing, vol.
26, no. 9, pp. 4509-4522, Sept. 2017.
[7] Liu F, Feng L,
Kijowski R. MANTIS: Model-Augmented Neural neTwork with Incoherent k-space
Sampling for efficient estimation of MR parameters. International Society of
Magnetic Resonance in Medicine Machine Learning Workshop Part II, 2018.
[8] Zhang Q, Su P, Liao Y,
et al. Deep learning based MR fingerprinting ASL ReconStruction. Proceedings of
27th ISMRM Annual Meeting, Montreal, Canada, #0820, 2019.
[9] Pirkl C, Lipp I,
Buonincontri G, et al. Deep Learning-enabled Diffusion Tensor MR
Fingerprinting. Proceedings of 27th ISMRM Annual Meeting, Montreal, Canada,
#1102, 2019.
[10] Li H, Zhang C, Liang Z, Liang D, Shen B, et al. Deep
Learned Diffusion Tensor Imaging. Proceedings
of 27th ISMRM Annual Meeting, Montreal, Canada, #3344, 2019.