Linshan Xie1,2, Yilong Liu1,2, Linfang Xiao1,2, Peibei Cao1,2, Alex T. L. Leong1,2, and Ed X. Wu1,2
1Laboratory of Biomedical Imaging and Signal Processing, The University of Hong Kong, Hong Kong, China, 2Department of Electrical and Electronic Engineering, The University of Hong Kong, Hong Kong, China
Synopsis
In
this work, we proposed a residual network based reconstruction method for
multi-slice partial Fourier acquisition, where adjacent slices are sampled in a
complementary way. The anatomical structure and phase similarity of multi-slice
MR data can be exploited to provide complementary information from adjacent
slices with different sampling patterns. The proposed method enables highly
partial Fourier imaging without noise amplification.
Introduction
Partial Fourier (PF) magnetic resonance imaging (MRI) has received
abundant attention due to its potential in reducing the echo time or scan time1.
Limited symmetrically sampled central k-space region will undermine the phase
estimation accuracy, leading to degraded performance of traditional PF
reconstruction, such as the projection-onto-convex-sets (POCS) method2.
In recent years, multi-slice MR reconstruction has demonstrated its great
potential in exploiting the similarities in image contents and coil sensitivity
maps in adjacent slices3,4. The image phase across adjacent slices should also
be similar due to the slow variation of the main magnetic field and coil
sensitivity maps. The multi-slice nature allows adjacent slices with different sampling patterns,
providing complementary information across different slices3.
In this study, we proposed to jointly use multiple consecutive slices
for reconstruction using residual network (ResNet), which can be further
enhanced by sampling adjacent slices in a complementary manner. The proposed
method can fully exploit structural and phase similarity in adjacent slices to
synthesize missing k-space data. Method
Proposed
Method
Our
preliminary study explored the feasible of using deep learning for PF
reconstruction, which was applied for individual slices, termed as single-slice
partial Fourier reconstruction (SS-PF)5. In this study, we propose
to jointly use multiple partial-Fourier acquired slices for reconstruction. The
proposed multi-slice partial Fourier (MS-PF) reconstruction
can be further enhanced by sampling adjacent slices in a complementary
manner, termed as EMS-PF. In brief, odd/even slices opposite halves of k-space
are sampled for either readout or phase-encoding directions. Figure 1 illustrates the flowchart of
the proposed EMS-PF method, where 3 consecutive slices are jointly used for
reconstructing the central slice. The input of the network has 6 concatenated
channels for the real and imaginary parts of images from 3 consecutive slices. The
output has 2 channels for the real and imaginary parts of the estimated residual
image for the central slice. After that, the final reconstructed image is
obtained by adding the residual image to the image reconstructed from zero-padding
k-space.
Model
Training and Evaluation
The
knee datasets from the Center for Advanced Imaging Innovation and Research
(CAI2R)6 were used for training, validating, and testing in the work.
The coronal proton density weighted knee data were acquired using 2D fast spin
echo (FSE), with TR=2200-3000ms, TE=27-34ms, FOV=160×160mm2, matrix
size=320×320, slice thickness/gap=3/0mm. The data were acquired using a
15-channel knee coil, but combined to approximate single-channel acquisition. The
datasets contained 942 subjects (each has 16 slices), 70%, 15%, and 15% of
which were used for training, validation, and testing, respectively. The raw k-space was cropped to 128×128, retrospectively
undersampled along phase-encoding direction at PF fraction of 51%, 55%, and 65%.
At PF fraction=51%, with only 4 symmetrically central k-space lines, it would
be extremely challenging for conventional POCS reconstruction. Models for
reconstructing the odd/even slices were trained separately, as their sampling patterns
differed from each other. It took ~3 hours to train each model with 100 epochs.
The performance was quantitatively evaluated by the peak
signal-to-noise ratio (PSNR) and structural similarity (SSIM).
Although
trained with knee data only, the proposed method was also evaluated with human
brain datasets acquired on a 3T Philips MRI scanner using a single-channel head
coil. T2-weighted images were acquired using 3D FSE with TR/TE=2500/213ms, FOV=240×240×120mm3,
matrix size=240×240×120. T1-weighted images were acquired using 3D GRE with TR/TE=19/4ms,
flip angle=30°, FOV=240×240×130mm3, matrix size=240×240×130. 1D
inverse Fourier transform was applied to the raw k-space, generating 2D k-space
for multiple consecutive axial slices with slice thickness/gap=1/0mm. The generated
2D k-space was cropped to 128×128 to fit the trained models, retrospectively
undersampled along phase-encoding direction.Results
Figures 2
and 3 compare the reconstruction
results and corresponding error maps for the conventional POCS, and our
proposed SS-PF/MS-PF/EMS-PF methods. Note that at PF fraction=51%, the
performance of conventional POCS reconstruction degraded dramatically due to
insufficient central k-space data for phase estimation. The proposed EMS-PF method
showed the best performance on recovering image details without noise
amplification among the aforementioned approaches. The MS-PF method and SS-PF
method had similar performance, which suggested that without complementary
sampling across adjacent slices, jointly using multiple slices for
reconstruction cannot fully exploit their structural and phase similarities. Figure 4 illustrates that the EMS-PF method yields slightly higher
error as the PF fraction decreased, while the performance of the POCS method experiences
a substantial deterioration. This demonstrates the proposed EMS-PF enables
highly partial Fourier imaging. Figure 5
presents reconstructed image from T1-weighted/T2-weighted brain images,
demonstrating the robustness of the proposed EMS-PF method for MR data of
different anatomical regions and/or acquired with different sequences. Discussion and Conclusion
Our
proposed method exploits the structural and phase similarity in adjacent slices
to synthesize the missing k-space in the slice to be reconstructed, which is
superior in preserving the image details without amplifying noise, especially for
highly partial Fourier imaging. Note that the slice thickness/gap will affect
the performance of the proposed approach as increased slice thickness/gap
decreases similarities of adjacent slices, which can be considered by adjusting
the number of jointly used slices. Future studies will also adapt the proposed
approach for 2D partial Fourier imaging, multi-channel MR acquisition, and/or
integrated with parallel imaging.Acknowledgements
This
study was supported by Hong Kong Research Grant Council (R7003-19, C7048-16G,
HKU17112120, HKU17103819 and HKU17104020), Guangdong Key Technologies for
Treatment of Brain Disorders (2018B030332001), and Guangdong Key Technologies
for Alzheimer’s Disease Diagnosis and Treatment (2018B030336001).References
- Margosian, Paul M., DeMeester, Gordon, and Liu,
Haiying. "Partial Fourier Acquisition in MRI." Encyclopedia of Magnetic Resonance. Highland Heights: Picker
International, 2007.
- Koopmans, Peter J., and Pfaffenrot, Viktor.
"Enhanced POCS reconstruction for partial Fourier imaging in multi-echo
and time-series acquisitions." Magnetic
Resonance in Medicine 85.1 (2020): 140-151.
- Liu, Yilong, et al. "Calibrationless
parallel imaging reconstruction for multislice MR data using low-rank tensor
completion." Magnetic Resonance in Medicine 85.2 (2020):
897-911.
-
Weizman, Lior, et al. "Exploiting
similarity in adjacent slices for compressed sensing MRI." 2014
36th Annual International Conference of the IEEE Engineering in Medicine and
Biology Society. IEEE, 2014.
-
Cao, Peipei, et al. "Partial Fourier MRI
Reconstruction Using Convolutional Neural Networks." Proceedings
of International Society of Magnetic Resonance in Medicine. 2020.
-
Knoll, Florian, et al. "Welcome to the fastMRI Dataset. "
NYU Langone Health. https://fastmri.med.nyu.edu/. Accessed 14 October 2020.