Compressed sensing (CS) utilizes the sparsity of magnetic resonance (MR) images to enable accurate reconstruction from undersampled k-space data. Recent CS methods have employed analytical sparsifying transforms such as wavelets, curvelets, and finite differences. In this paper, we propose a novel framework for adaptively learning the sparsifying transform (dictionary), and reconstructing the image simultaneously from highly undersampled k-space data. The sparsity in this framework is enforced on overlapping image patches emphasizing local structure. Moreover, the dictionary is adapted to the particular image instance thereby favoring better sparsities and consequently much higher undersampling rates. The proposed alternating reconstruction algorithm learns the sparsifying dictionary, and uses it to remove aliasing and noise in one step, and subsequently restores and fills-in the k-space data in the other step. Numerical experiments are conducted on MR images and on real MR data of several anatomies with a variety of sampling schemes. The results demonstrate dramatic improvements on the order of 4-18 dB in reconstruction error and doubling of the acceptable undersampling factor using the proposed adaptive dictionary as compared to previous CS methods. These improvements persist over a wide range of practical data signal-to-noise ratios, without any parameter tuning.

MR Image Reconstruction From Highly Undersampled k-Space Data by Dictionary Learning

Compressive Sensing (CS) is an effective approach for fast Magnetic Resonance Imaging (MRI). It aims at reconstructing MR image from a small number of under-sampled data in k-space, and accelerating the data acquisition in MRI. To improve the current MRI system in reconstruction accuracy and computational speed, in this paper, we propose a novel deep architecture, dubbed ADMM-Net. ADMM-Net is defined over a data flow graph, which is derived from the iterative procedures in Alternating Direction Method of Multipliers (ADMM) algorithm for optimizing a CS-based MRI model. In the training phase, all parameters of the net, e.g., image transforms, shrinkage functions, etc., are discriminatively trained end-to-end using L-BFGS algorithm. In the testing phase, it has computational overhead similar to ADMM but uses optimized parameters learned from the training data for CS-based reconstruction task. Experiments on MRI image reconstruction under different sampling ratios in k-space demonstrate that it significantly improves the baseline ADMM algorithm and achieves high reconstruction accuracies with fast computational speed.

https://proceedings.neurips.cc/paper/2016/file/1679091c5a880faf6fb5e6087eb1b2dc-Paper.pdf

Deep ADMM-Net for compressive sensing MRI

Compressed sensing magnetic resonance imaging (CS-MRI) enables fast acquisition, which is highly desirable for numerous clinical applications. This can not only reduce the scanning cost and ease patient burden, but also potentially reduce motion artefacts and the effect of contrast washout, thus yielding better image quality. Different from parallel imaging-based fast MRI, which utilizes multiple coils to simultaneously receive MR signals, CS-MRI breaks the Nyquist–Shannon sampling barrier to reconstruct MRI images with much less required raw data. This paper provides a deep learning-based strategy for reconstruction of CS-MRI, and bridges a substantial gap between conventional non-learning methods working only on data from a single image, and prior knowledge from large training data sets. In particular, a novel conditional Generative Adversarial Networks-based model (DAGAN)-based model is proposed to reconstruct CS-MRI. In our DAGAN architecture, we have designed a refinement learning method to stabilize our U-Net based generator, which provides an end-to-end network to reduce aliasing artefacts. To better preserve texture and edges in the reconstruction, we have coupled the adversarial loss with an innovative content loss. In addition, we incorporate frequency-domain information to enforce similarity in both the image and frequency domains. We have performed comprehensive comparison studies with both conventional CS-MRI reconstruction methods and newly investigated deep learning approaches. Compared with these methods, our DAGAN method provides superior reconstruction with preserved perceptual image details. Furthermore, each image is reconstructed in about 5 ms, which is suitable for real-time processing.

/pdf/dagan-deep-de-aliasing-generative-adversarial-networks-for-3u7cltdv1j.pdf

DAGAN: Deep De-Aliasing Generative Adversarial Networks for Fast Compressed Sensing MRI Reconstruction

Computational and Mathematical Methods in Medicine

Multi-focus image fusion with a deep convolutional neural network

Magnetic resonance spectroscopy (MRS) is an important clinical imaging method for the diagnosis of diseases. Spectrum is used to observe the signal intensity of metabolites or further infer their concentrations. Although the magnetic resonance vendors commonly provide basic functions of spectra plots and metabolite quantification, the widespread clinical research of MRS is still limited due to the lack of easy-to-use processing software or platform. To address this issue, we have developed CloudBrain-MRS, a cloud-based online platform that provides powerful hardware and advanced algorithms. The platform can be accessed simply through a web browser, without requiring any program installation on the user side. CloudBrain-MRS also integrates the classic LCModel and advanced artificial intelligence algorithms and supports batch preprocessing, quantification, and analysis of MRS data. Additionally, the platform offers useful functions: 1) Automatically statistical analysis to find biomarkers from the health and patient groups; 2) Consistency verification between the classic and artificial intelligence quantification algorithms; 3) Colorful and three-dimensional visualization for the easy observation of individual metabolite spectrum. Last, both healthy and mild cognitive impairment patient data are used to demonstrate the usefulness of the platform. To the best of our knowledge, this is the first cloud computing platform for in vivo MRS with artificial intelligence processing. We sincerely hope that this platform will facilitate efficient clinical research for MRS. CloudBrain-MRS is open-accessed at https://csrc.xmu.edu.cn/CloudBrain.html.

CloudBrain-MRS: An Intelligent Cloud Computing Platform for in vivo Magnetic Resonance Spectroscopy Preprocessing, Quantification, and Analysis

Nuclear Magnetic Resonance (NMR) spectroscopy is one of the most promising analytical chemistry techniques, although it takes a long time to acquire data. Non-uniform sampling (NUS) is an effective way to reduce the sampling time, but faithful reconstruction methods are needed. The low rank Hankel matrix (LRHM) approach uses the low rank constraint to obtain high-quality spectra from NUS signals, but the reconstruction has a considerable time overhead. In this work, we propose a sliding window based low rank Hankel matrix approach to speed up the spectra reconstruction from NUS signals. Using the sliding window to construct a matrix can effectively reduce the size of the Hankel matrix for faster reconstructions. To further decrease the reconstruction time, parallel computation is applied in the proposed approach. The experiments on both synthetic data and realistic data demonstrate that the reconstruction speed of the proposed method is the fastest among compared methods without sacrificing the quality of spectra. 

Fast NMR spectroscopy reconstruction with a sliding window based Hankel matrix.

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.

/pdf/brain-metabolic-differences-between-temporal-lobe-epileptic-1crmkmwe1t.pdf

Brain metabolic differences between temporal lobe epileptic seizures and organic non-epileptic seizures in postictal phase: a retrospective study with magnetic resonance spectroscopy.

Undersampling the k-space is an efficient way to speed up the magnetic resonance imaging (MRI). Recently emerged compressed sensing MRI shows promising results. However, most of them only enforce the sparsity of images in single transform, e.g. total variation, wavelet, etc. In this paper, based on the principle of basis pursuit, we propose a new framework to combine sparsifying transforms in compressed sensing MRI. Each transform can efficiently represent specific feature that the other can not. This framework is implemented via the state-of-art smoothed l0 norm in overcomplete sparse decomposition. Simulation results demonstrate that the proposed method can improve image quality when comparing to single sparsifying transform.

Ciatation: Xiaobo Qu, Xue Cao, Di Guo, Changwei Hu, Zhong Chen. Compressed Sensing MRI with Combined Sparsifying Transforms and Smoothed L0 Norm Minimization. The 35th International Conference on Acoustics, Speech, and Signal Processing-ICASSP'2010, Dallas, Texas, U.S.A, March 14 - 19, 2010,pp.626-629. ========================================================================== COMPRESSED SENSING MRI WITH COMBINED SPARSIFYING TRANSFORMS AND SMOOTHED ℓ0 NORM MINIMIZATION

Di Guo

Papers

CloudBrain-MRS: An Intelligent Cloud Computing Platform for in vivo Magnetic Resonance Spectroscopy Preprocessing, Quantification, and Analysis

Fast NMR spectroscopy reconstruction with a sliding window based Hankel matrix.

Brain metabolic differences between temporal lobe epileptic seizures and organic non-epileptic seizures in postictal phase: a retrospective study with magnetic resonance spectroscopy.