Showing papers by "Di Guo published in 2021"
TL;DR: In this article, a guaranteed convergence analysis of the parallel imaging version pFISTA was provided to solve the two well-known parallel imaging reconstruction models, SENSE and SPIRiT.
16 citations
TL;DR: Recent progress on low rank Hankel matrix and tensor methods, that exploit the exponential property of free induction decay signals, to enable effective denoising and spectra reconstruction are summarized.
Abstract: Nuclear magnetic resonance (NMR) spectroscopy is an important analytical tool in chemistry, biology, and life science, but it suffers from relatively low sensitivity and long acquisition time. Thus, improving the apparent signal-to-noise ratio and accelerating data acquisition became indispensable. In this review, we summarize the recent progress on low-rank Hankel matrix and tensor methods, which exploit the exponential property of free-induction decay signals, to enable effective denoising and spectra reconstruction. We also outline future developments that are likely to make NMR spectroscopy a far more powerful technique.
16 citations
Posted Content•
TL;DR: This work proposed to separably construct multiple small Hankel matrices from rows and columns of the k-space and then constrain the low-rankness on these small matrices and achieves the fastest computational speed in parameter imaging reconstruction.
Abstract: The combination of the sparse sampling and the low-rank structured matrix reconstruction has shown promising performance, enabling a significant reduction of the magnetic resonance imaging data acquisition time. However, the low-rank structured approaches demand considerable memory consumption and are time-consuming due to a noticeable number of matrix operations performed on the huge-size block Hankel-like matrix. In this work, we proposed a novel framework to utilize the low-rank property but meanwhile to achieve faster reconstructions and promising results. The framework allows us to enforce the low-rankness of Hankel matrices constructing from 1D vectors instead of 2D matrices from 1D vectors and thus avoid the construction of huge block Hankel matrix for 2D k-space matrices. Moreover, under this framework, we can easily incorporate other information, such as the smooth phase of the image and the low-rankness in the parameter dimension, to further improve the image quality. We built and validated two models for parallel and parameter magnetic resonance imaging experiments, respectively. Our retrospective in-vivo results indicate that the proposed approaches enable faster reconstructions than the state-of-the-art approaches, e.g., about 8x faster than STDLRSPIRiT, and faithful removal of undersampling artifacts.
14 citations
TL;DR: In this article, the effect of the regularization parameter of a convex optimization denoising method based on low-rank Hankel matrices for exponential signals corrupted by Gaussian noise is explored.
Abstract: Nuclear magnetic resonance (NMR) spectroscopy, whose time domain data is modeled as the sum of damped exponential signals, has become an indispensable tool in various scenarios, such as biomedicine, biology, and chemistry. NMR spectroscopy signals, however, are usually corrupted by Gaussian noise in practice, raising difficulties in sequential analysis and quantification. The low-rank Hankel property of exponential signals plays an important role in the denoising issue, but selecting an appropriate parameter still remains a problem. In this work, we explore the effect of the regularization parameter of a convex optimization denoising method based on low-rank Hankel matrices for exponential signals corrupted by Gaussian noise. An accurate estimate on the spectral norm of weighted Hankel matrices is provided as a guidance to set the regularization parameter. The bound can be efficiently calculated since it only depends on the standard deviation of the noise and a constant. Aided by the bound, one can easily obtain an auto-setting regularization parameter to produce promising denoised results. Our results on synthetic and realistic NMR spectroscopy data demonstrate a superior denoising performance of the proposed approach over typical Cadzow and the state-of-the-art QR decomposition methods, especially in the low signal-to-noise ratio regime.
8 citations
TL;DR: In this article, an average smoothing singular value decomposition (ASVD) was proposed to further improve the SNR by introducing repeatedly sampled signals into multichannel coil combination.
Abstract: Magnetic resonance spectroscopy (MRS), as a noninvasive method for molecular structure determination and metabolite detection, has grown into a significant tool in clinical applications. However, the relatively low signal-to-noise ratio (SNR) limits its further development. Although the multichannel coil and repeated sampling are commonly used to alleviate this problem, there is still potential room for promotion. One possible improvement way is combining these two acquisition methods so that the complementary of them can be well utilized. In this paper, a novel coil-combination method, average smoothing singular value decomposition, is proposed to further improve the SNR by introducing repeatedly sampled signals into multichannel coil combination. Specifically, the sensitivity matrix of each sampling was pretreated by whitened singular value decomposition (WSVD), then the smoothing was performed along the repeated samplings’ dimension. By comparing with three existing popular methods, Brown, WSVD, and generalized least squares, the proposed method showed better performance in one phantom and 20 in vivo spectra.
2 citations
Posted Content•
TL;DR: XCloud-pFISTA as mentioned in this paper is an open-access, easy-to-use and high-performance medical intelligence cloud computing platform to reconstruct MRI images from undersampled k-space data.
Abstract: Machine learning and artificial intelligence have shown remarkable performance in accelerated magnetic resonance imaging (MRI). Cloud computing technologies have great advantages in building an easily accessible platform to deploy advanced algorithms. In this work, we develop an open-access, easy-to-use and high-performance medical intelligence cloud computing platform (XCloud-pFISTA) to reconstruct MRI images from undersampled k-space data. Two state-of-the-art approaches of the Projected Fast Iterative Soft-Thresholding Algorithm (pFISTA) family have been successfully implemented on the cloud. This work can be considered as a good example of cloud-based medical image reconstruction and may benefit the future development of integrated reconstruction and online diagnosis system.
1 citations
1 citations
Posted Content•
TL;DR: In this article, a virtual peak (VIP) approach is proposed to self-learn the prior spectral information, such as the central frequency and peak lineshape, and then feed these information into the process of spectral reconstruction.
Abstract: Background: Nuclear Magnetic Resonance (NMR) spectroscopy is an important
bio-engineering tool to determine the metabolic concentrations, molecule
structures and so on. The data acquisition time, however, is very long in
multi-dimensional NMR. To accelerate data acquisition, non-uniformly sampling
is an effective way but may encounter severe spectral distortions and
unfaithful quantitative measures when the acceleration factor is high.
Objective: To reconstruct high fidelity spectra from highly accelerated NMR and
achieve much better quantitative measures. Methods: A virtual peak (VIP)
approach is proposed to self-learn the prior spectral information, such as the
central frequency and peak lineshape, and then feed these information into the
reconstruction. The proposed method is further implemented with cloud computing
to facilitate online, open, and easy access. Results: Results on synthetic and
experimental data demonstrate that, compared with the state-of-the-art method,
the new approach provides much better reconstruction of low-intensity peaks and
significantly improves the quantitative measures, including the regression of
peak intensity, the distances between nuclear pairs, and concentrations of
metabolics in mixtures. Conclusion: Self-learning prior peak information can
improve the reconstruction and quantitative measures of spectra. Significance:
This approach enables highly accelerated NMR and may promote time-consuming
applications such as quantitative and time-resolved NMR experiments.
1 citations
Posted Content•
TL;DR: In this paper, a deep learning denoising method was proposed to significantly shorten the time of data acquisition, while maintaining signal accuracy and reliability, and the proposed method significantly reduced the data acquisition time with slightly compromised metabolic accuracy.
Abstract: Objective: Magnetic Resonance Spectroscopy (MRS) is a noninvasive tool to reveal metabolic information. One challenge of MRS is the relatively low Signal-Noise Ratio (SNR) due to low concentrations of metabolites. To improve the SNR, the most common approach is to average signals that are acquired in multiple times. The data acquisition time, however, is increased by multiple times accordingly, resulting in the scanned objects uncomfortable or even unbearable. Methods: By exploring the multiple sampled data, a deep learning denoising approach is proposed to learn a mapping from the low SNR signal to the high SNR one. Results: Results on simulated and in vivo data show that the proposed method significantly reduces the data acquisition time with slightly compromised metabolic accuracy. Conclusion: A deep learning denoising method was proposed to significantly shorten the time of data acquisition, while maintaining signal accuracy and reliability. Significance: Provide a solution of the fundamental low SNR problem in MRS with artificial intelligence.
TL;DR: Experimental results demonstrate that N-acetyl-aspartate/Creatine (NAA/Cr) can be used to discriminate TLES from ONES, which has not been found in the references to the best of the authors' knowledge.
Abstract: Magnetic resonance spectroscopy (MRS) is employed to investigate the brain metabolites differences between patients with temporal lobe epileptic seizures (TLES) and organic non-epileptic seizures (ONES) that appear to be epileptic seizures. Twenty-three patients with TLES and nine patients with ONES in postictal phase underwent MRS examinations on a clinical 1.5T system, with 15 healthy controls in comparison. Statistical analyses on the ratios of brain metabolites were performed using the Mann-Whitney U test with age as a covariate. The results showed that N-acetyl-aspartate/Creatine (NAA/Cr) ratio of patients with TLES was statistically different from that of patients with ONES in postictal phase, i.e., TLES 1.422±0.037, ONES 1.640±0.061, P=0.012 in left temporal pole, while TLES 1.470±0.052, ONES 1.687±0.084, P=0.023 in the right temporal pole. Besides, compared with healthy controls, patients with TLES in postictal phase present significant differences in ratios of NAA/Cr, N-acetyl-aspartate/Choline (NAA/Cho) and NAA/(Cho + Cr). Experimental results demonstrate that NAA/Cr can be used to discriminate TLES from ONES, which has not been found in the references to the best of our knowledge. Although a prospective controlled validation is needed in the future, this retrospective study reveals that MRS may provide useful metabolites information to facilitate the epilepsy diagnosis.