Yunpeng Zhang1, Yibo Zhao2,3, Yudu Li2,3, Rong Guo2,3, Yao Li1, and Zhi-Pei Liang2,3
1School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai, China, 2Beckman Institute for Advanced Science and Technology, University of Illinois at Urbana-Champaign, Urbana, IL, United States, 3Department of Electrical and Computer Engineering, University of Illinois at Urbana-Champaign, Urbana, IL, United States
Synopsis
Spin-Echo
(SE) MRSI can encode J-coupling information and is desirable for brain imaging
applications. But it uses long TR, leading to long scan time and thus low
resolution. Consequently, removal of subcutaneous lipid signals from
low-resolution SE data is challenging. This paper presents a novel method to
solve this problem. The proposed method uses a high-resolution FID reference
and a neural network to transform it into SE signals, which are then used to
construct a generalized-series model for lipid signal removal from the SE 1H-MRSI
data. The proposed method has been tested using in vivo data, producing very
encouraging results.
Introduction
Spin-Echo (SE) acquisitions have several unique
advantages over FID acquisitions, including the capability for encoding
J-coupling and diffusion weighting1. SE-MRSI is, therefore, often used to obtain
J-resolved spectral information desired for accurate separation of brain
metabolites and neurotransmitters. However, SE acquisitions use long TR,
leading to long scan time and thus low spatial resolution. Consequently,
removal of subcutaneous lipid signals from low-resolution SE 1H-MRSI
data is challenging2. Conventional MRSI methods use lipid
suppression to alleviate the problem but suppression pulses are often
susceptible to system imperfections such as B0 inhomogeneity3.
Various post-processing methods have also been proposed, which use prior
information such as spatial support of lipid signals4, spectral
support of metabolite signal5, sparsity6, and
spatiospectral structures of lipid signals in the form of a union-of-subspaces
model7. These post-processing methods work well with MRSI data
acquired with lipid suppression; for MRSI data acquired with no lipid
suppression and only a small number of spatial encodings as often is the case
in J-resolved MRSI experiments, the lipid removal problem remains very
challenging. This paper presents a novel method to solve this problem. The
proposed method uses a high-resolution FID reference that can be acquired
quickly and a neural network to transform it into SE signals. The generated SE
lipid signals are then used to construct a generalized series (GS) model for
reconstruction and removal of the subcutaneous lipid signals from the SE 1H-MRSI
data. Methods
We assume that we have two data sets: one set of
SE MRSI data, $$$d_{\rm SE}\left( {\bf k} ,t\right)$$$, with a small number of spatial encodings (i.e.,
limited k-space coverage), and a high-resolution reference containing only the
subcutaneous lipid signals, $$$d_{\rm ref}\left({\bf k},t\right)$$$. The reference data
set can be acquired quickly using an FID sequence, or can be obtained using a
machine learning-based generative model. In this work, we assume that $$$d_{\rm ref}({\bf k},t)$$$, is obtained using an
FID sequence. The proposed method, as illustrated in Fig. 1, consists of two
key components: a) a neural network trained to map $$$\rho_{\rm ref}\left( {\bf x} ,t\right)$$$, the spatiotemporal function corresponding to $$$d_{\rm ref}\left({\bf k},t\right)$$$, to SE data, $$$\widetilde{\rho}_{\rm SE}\left( {\bf x} ,t\right)$$$, and b) a GS model
constructed based on $$$\widetilde{\rho}_{\rm SE}\left( {\bf x} ,t\right)$$$.
To map $$$\rho_{\rm ref}( {\bf x} ,t)$$$ to $$$\widetilde{\rho}_{\rm SE}( {\bf x} ,t)$$$, a 1D ResNet-based convolution neural network
(CNN) was used. The architecture of the network is shown in Fig. 2.
Specifically, the network consisted of 10 residual blocks followed by a
convolutional output layer. Each residual block included a convolution layer, a
deconvolution layer, and a batch normalization layer. The network was trained
using pairs of high-resolution FID and SE lipid data acquired from healthy
volunteers. After proper training, the network was capable of producing the
desired SE lipid reference $$$\widetilde{\rho}_{\rm SE}( {\bf x} ,t)$$$ from the corresponding FID lipid spectra
voxel-by-voxel.
With $$$\widetilde{\rho}_{\rm SE}( {\bf x} ,t)$$$ obtained, a GS model was constructed to represent the lipid signals8.
More specifically, we expressed the spatiotemporal distribution of the lipid
signals that match a specific SE MRSI data set as:
$$\rho_{\rm lipid}=\Sigma_{m=-M/2}^{M/2}h_m(t)\widetilde{\rho}_{\rm SE}( {\bf x} ,t)e^{-i2{\pi}m{\bf \triangle k \cdot x}}$$
where $$$M$$$ is the order of GS model and $$$h_m$$$ are the GS coefficients. The GS coefficients were estimated by solving the following
least-squares problem:
$$\hat h_{m}(t)={\arg}\mathop\min_{h_m(t)}\| d_{\rm SE}\left({\bf k},t\right)-\Omega {\rm F}\left(\Sigma_{m=-M/2}^{M/2}h_m(t)\widetilde{\rho}_{\rm SE}({\bf x},t)e^{-i2{\pi}m{\bf \triangle k\cdot x}}\right)\|_2^2$$
where $$$\Omega$$$ and $$${\rm F}$$$ are the (k,t)-space sampling and Fourier
encoding operators, respectively. The GS model can effectively absorb the
high-resolution SE lipid reference into the reconstruction and compensate the
discrepancies between the CNN-generated SE reference and real SE data. Results
We have evaluated our proposed method using in vivo
data collected from healthy human subjects. Figure 3 shows a set of
representative prediction results by the neural network. As can be seen from
both error map and selected spectra from individual voxels, the discrepancies
between the predicted and acquired SE lipid data were at a very low level.
Figure 4 compares the effectiveness in lipid
removal of the proposed method with conventional methods including
Fourier-based and Papoulis-Gerchberg
(PG) reconstructions. As can be
seen from the lipid integral map, the proposed method achieved the best
performance in lipid signal removal, especially for the most challenging areas
close to the subcutaneous region. To demonstrate the benefits of effective
lipid removal for metabolite reconstruction, we also compared the associated
metabolite maps as shown in Fig. 5. As expected, the proposed method
outperformed conventional PG reconstruction with better preservation of
neurometabolic signals within the brain. Conclusions
A new method has been proposed for effective removal of lipid signals from spin-echo 1H-MRSI brain data acquired with no
lipid suppression and a limited number of spatial encodings. The proposed method has been validated using in vivo data, producing very
encouraging results. With further development, the proposed method may provide
an effective solution to the lipid removal problem associated with 1H-MRSI,
especially J-resolved 1H-MRSI, of the brain.Acknowledgements
Y. L. is funded by National Science Foundation of China (No.61671292 and 81871083) and Shanghai Jiao Tong University Scientific and Technological Innovation Funds (2019QYA12).References
- Pohmann R, Von
Kienlin M, Haase A. Theoretical evaluation and comparison of fast chemical shift imaging
methods. J Magn Reson.
1997;129(2):145-160.
- Ho R J, Lam F. High-Resolution
3D Spin-Echo MRSI Using Interleaved Water Navigators, Sparse Sampling and Subspace-Based
Processing. Proc IEEE Eng Med Biol Soc. 2020;1465-1468.
- Duyn J H, Gillen
J, Sobering G, et al. Multisection proton MR spectroscopic imaging of the
brain. Radiology. 1993;188(1):277-282.
- Haupt C I,
Schuff N, Weiner M W, et al. Removal of lipid artifacts in 1H spectroscopic imaging by
data extrapolation. Magn Reson
Med. 1998;35(5):678-687.
- Hernando D,
Haldar J, Sutton B, et al. Removal of lipid signal in MRSI using spatial-spectral
constraints. Proc IEEE Int Symp Biomed Imaging. 2007;1360-1363.
- Bilgic B,
Gagoski B, Kok T, et al. Lipid suppression in CSI with spatial priors and highly
undersampled peripheral k-space. Magn
Reson Med. 2013;69(6):1501-1511.
- Ma C, Lam F,
Johnson C L, et al. Removal of nuisance signals from limited and sparse 1H MRSI data using a
union-of-subspaces model. Magn Reson
Med. 2016;75(2):488-497.
- Liang ZP,
Lauterbur PC. A generalized series approach to MR spectroscopic imaging. IEEE
Trans Med Imaging. 1991;10(2):132–137.