Non-negative matrix factorisation methods for the spectral decomposition of MRS data from human brain tumours

The Gaussian and Gaussian-sigmoidal primaries are introduced as initialization functions in the nonnegative matrix factorization (NNMF) method to achieve more consistent error statistics. The proposed NNMF method with multiplicative update algorithm is employed for reconstruction of spectral data of Munsell and Colorchecker DC datasets from the corresponding CIEXYZ tristimulus values and the resultant achievements are compared with those obtained from PCA and the classical NNMF techniques. Both colorimetric and spectrophotometric errors between the original and the reconstructed spectra are used for the evaluation of reconstruction methods. While run to run variability of the classical NNMF method with multiplicative update algorithm is significantly remarkable, the stability of the suggested technique is fairly high, similar to the PCA method. The ensuing findings show that the embedding of Gaussian initializing vectors in NNMF method provide the all positive bases that enhance both the accuracy of Gaussian method and the reliability of NNMF technique.

Application of phase rotation to the STRESS (=STEAM+PRESS) localization scheme, to shorten echo time, minimize J-coupling dephasing and estimate B1+ inhomogeneity. STRESS (=STEAM + PRESS) simultaneously refocuses and acquires the double spin echo (SE123 ) and stimulated echo (STE- ) pathways, combining PRESS-like signal with lower chemical shift displacement as in STEAM. Phase rotation effectively separates coherence pathways, allows reduction of spoiling gradients moments leading to reduction in echo time. Implementing it in STRESS allows one to individually phase-correct SE123 and STE- prior to combination. Moreover, B1+ inhomogeneity can be assessed by comparing the measured ratio of resonance intensities of SE123 and STE- pathways to the simulated one. In vivo spectra were acquired from a single voxel placed in the sensory-motor cortex of 10 healthy volunteers, using phase rotation-STRESS/PRESS/STEAM sequences at 3 T scanner. The phases of each slice-selective pulse were incremented by Δϕ1/2/3=22.5°/-45°/45°. Phase rotation-STRESS showed quantification accuracy (% Cramer Rao lower bounds) and reproducibility (% coefficients of variation) comparable to PRESS and STEAM, in both phantoms and in vivo study. Minimal echo time achieved was 13 ms. Phase rotation complements STRESS by reducing echo time, allowing processing of each pathway individually prior to addition and providing B1+ estimation in single voxel proton magnetic resonance spectroscopy. Magn Reson Med 79:2481-2490, 2018. © 2017 International Society for Magnetic Resonance in Medicine.

In this letter, we develop a multichannel blind source separation algorithm based on a beamspace transform and the multichannel nonnegative matrix factorization (NMF) method. The conventional multichannel NMF algorithm performs well with multichannel mixing data, but there is still room for enhancement in multichannel real-world recording data. In this letter, we consider a beamspace-time-frequency domain data model for multichannel NMF method, and enhance the conventional method using a beamspace transform. Our decomposition algorithm is applied to 2-channel and 4-channel unsupervised audio source separation, using a dataset from the international Signal Separation Evaluation Campaign 2010 (SiSEC 2010). Our algorithm shows a better performance than the conventional NMF method in an evaluation results.

Non-negative matrix factorization (NMF) has been one of the most popular methods for feature learning in the field of machine learning and computer vision. Most existing works directly apply NMF on high-dimensional image datasets for computing the effective representation of the raw images. However, in fact, the common essential information of a given class of images is hidden in their low rank parts. For obtaining an effective low-rank data representation, we in this paper propose a non-negative low-rank matrix factorization (NLMF) method for image clustering. For the purpose of improving its robustness for the data in a manifold structure, we further propose a graph regularized NLMF by incorporating the manifold structure information into our proposed objective function. Finally, we develop an efficient alternating iterative algorithm to learn the low-dimensional representation of low-rank parts of images for clustering. Alternatively, we also incorporate robust principal component analysis into our proposed scheme. Experimental results on four image datasets reveal that our proposed methods outperform four representative methods.

Non-negative matrix factorization (NMF) is a very popular dimensionality reduction method that has been widely used in computer vision and data clustering. However, NMF does not consider the intrinsic geometric information of a data set and also does not produce smooth and stable solutions. To resolve these problems, we propose a Graph regularized Lp Smooth Non-negative Matrix Factorization (GSNMF) method by incorporating graph regularization with Lp smooth constraint. The graph regularization can discover the hidden semantics and simultaneously respect the intrinsic geometric structure information of a data set. The Lp smooth constraint can combine the merits of isotropic (L2-norm) and anisotropic (L1-norm) diffusion smoothing, and produce a smooth and more accurate solution to the optimization problem. Experimental results on some data sets demonstrate that the proposed method outperforms related state-of-the-art NMF methods.

In this paper, we present a novel muscle synergy extraction method based on multivariate curve resolution–alternating least squares (MCR-ALS) to overcome the limitation of the nonnegative matrix factorization (NMF) method for extracting non-sparse muscle synergy, and we study its potential application for evaluating motor function of stroke survivors. Nonnegative matrix factorization (NMF) is the most widely used method for muscle synergy extraction. However, NMF is susceptible to components’ sparseness and usually provides inferior reliability, which significantly limits the promotion of muscle synergy. In this study, MCR-ALS was employed to extract muscle synergy from electromyography (EMG) data. Its performance was compared with two other matrix factorization algorithms, NMF and self-modeling mixture analysis (SMMA). Simulated data sets were utilized to explore the influences of the sparseness and noise on the extracted synergies. As a result, the synergies estimated by MCR-ALS were the most similar to true synergies as compared with SMMA and NMF. MCR-ALS was used to analyze the muscle synergy characteristics of upper limb movements performed by healthy (n = 11) and stroke (n = 5) subjects. The repeatability and intra-subject consistency were used to evaluate the performance of MCR-ALS. As a result, MCR-ALS provided much higher repeatability and intra-subject consistency as compared with NMF, which were important for the reliability of the motor function evaluation. The stroke subjects had lower intra-subject consistency and seemingly had more synergies as compared with the healthy subjects. Thus, MCR-ALS is a promising muscle synergy analysis method for motor function evaluation of stroke patients.

We apply the vectorized non-negative matrix factorization (NMF) method to the post-processing of the direct imaging data of exoplanetary systems such as circumstellar disks. NMF is an iterative approach, which first creates a nonorthogonal and non-negative basis of components using the given reference images and then models a target with the components. The constructed model is then rescaled with a factor to compensate for the contribution from the disks. We compare NMF with existing methods (classical reference differential imaging method, and the Karhunen–Loève image projection algorithm) using synthetic circumstellar disks and demonstrate the superiority of NMF: with no need of prior selection of references, NMF not only can detect fainter circumstellar disks but also better preserves their morphology and does not require forward modeling. As an application to a well-known disk example, we process the archival Hubble Space Telescope STIS coronagraphic observations of HD 181327 with different methods and compare them, and NMF is able to extract some circumstellar materials inside the primary ring for the first time. In an appendix, we mathematically investigate the stability of NMF components during the iteration and the linearity of NMF modeling.

Proton magnetic resonance spectroscopy in children with acute central nervous system injury

Previous studies showed alterations of brain function in the ventromedial prefrontal cortex of schizophrenia patients. Also, neurochemical changes, especially GABA level alteration, have been found in the medial prefrontal cortex of schizophrenia patients. However, the relationship between GABA level in the ventromedial prefrontal cortex and brain functional activity in schizophrenia patients remains unexplored. In total, 23 drug-naïve, first-episode psychosis patients and 26 matched healthy controls completed the study. The single voxel proton magnetic resonance spectroscopy data were acquired in ventromedial prefrontal cortex region, which was used as the seed region for resting-state functional connectivity analysis. The proton magnetic resonance spectroscopy data were processed to quantify the concentrations of GABA+, glutamine and glutamate, and N-acetylaspartate in ventromedial prefrontal cortex. Spearman correlation analysis was used to examine the relationship between metabolite concentration, functional connectivity and clinical variables. Pearson correlation analysis was used to examine the relationship between GABA+ concentration and functional connectivity value. In first-episode psychosis patients, GABA+ level in ventromedial prefrontal cortex was higher and was positively correlated with ventromedial prefrontal cortex-left middle orbital frontal cortex functional connectivity. N-acetylaspartate level was positively correlated with positive symptoms, and the functional connectivity between ventromedial prefrontal cortex and left precuneus was negatively associated with negative symptoms of first-episode psychosis patients. Our results indicated that ventromedial prefrontal cortex functional connectivity changes were positively correlated with higher local GABA+ level in first-episode psychosis patients. The altered neurochemical concentration and functional connectivity provide insights into the pathology of schizophrenia.

Single voxel proton magnetic resonance spectroscopy in women with and without intimate partner violence-related posttraumatic stress disorder

Combination antiretroviral therapy (cART) can suppress plasma HIV RNA to undetectable levels; yet reports indicate persistent HIV-associated neurocognitive disorders (HAND) among treated individuals. We sought to investigate imaging correlates of incomplete cognitive recovery among individuals with chronic HIV. We used single voxel proton magnetic resonance spectroscopy in 4 regions of the brain to measure changes in neuronal and glia biomarkers in cART-naive subjects before (n = 59, 27 with HAND) and after 12 months of cART. At baseline, we observed elevated total choline (CHO) in the basal ganglia (BG, P = 0.002) and in the posterior cingulate gyrus (PCG, P = 0.022) associated with HIV infection. Myo-inositol (MI) was elevated in the frontal white matter (FWM, P = 0.040). N-acetylaspartate was elevated in the BG (P = 0.047). Using a mixed model approach among all HIV-infected individuals, at 6 months, we observed decreased n- acetylaspartate in FWM (P = 0.031), decreased creatine in PCG (P = 0.026) and increased MI in frontal gray matter (FGM, P = 0.023). At 12 months, we observed an increase in BG MI (P = 0.038) and in FGM (P = 0.021). Compared to those with normal cognition, HAND cases had higher FGM MI (P = 0.014) at baseline. At 12 months, individuals that remained cognitively impaired compared with those without HAND exhibited elevated CHO in the PCG (P = 0.018) and decreased glutamate in both FWM (P = 0.027) and BG (P = 0.013). cART started during chronic HIV is associated with reduced neuronal-glia and inflammatory markers. Alterations in CHO are noted among individuals who remain impaired after 12 months of cART.

This study was performed to evaluate the effect of seizures on the bilateral hippocampus in mesial temporal lobe epilepsy (mTLE) and neocortical epilepsy by single voxel proton magnetic resonance spectroscopy (MRS). Forty-one patients with mTLE having unilateral hippocampal sclerosis and 43 patients with a neocortical epilepsy who underwent subsequent epilepsy surgery were recruited. Ninety-five percent confidence intervals of N-acetyl aspartate/choline (NAA/Cho) and NAA/creatine (NAA/Cr) ratios in 20 healthy control subjects were used as threshold values to determine abnormal NAA/Cho and NAA/Cr. NAA/Cho and NAA/Cr were significantly lower in the ipsilateral hippocampus of mTLE and neocortical epilepsy. Using asymmetry indices for patients with bilaterally abnormal ratios of NAA/Cho and NAA/Cr in addition to using unilateral abnormal ratio, the seizure focus was correctly lateralized in 65.9% of patients with mTLE and 48.8% of neocortical epilepsy patients. Bilateral NAA/Cho abnormality was significantly related to a poor surgical outcome in mTLE. No significant relationship was found between the results of NAA/Cho or NAA/Cr and surgical outcome in neocortical epilepsy. The mean contralateral NAA/Cr ratio of the hippocampus in mTLE was significantly lower in patients with a history of secondary generalized tonic-clonic seizure (SGTCS) than in those without. Our results demonstrate effects of seizures on the hippocampi in neocortical epilepsy and the relation between SGTCS and NAA/Cr of the contralateral hippocampus in mTLE. This proves the presence of a seizure effect on the hippocampus in neocortical epilepsy as well as in mTLE.

Magnetic resonance spectroscopy reveals N-acetylaspartate reduction in hippocampus and cingulate cortex after fear conditioning

White matter hyperintensities (WMHs), presented on T2-weighted or fluid-attenuated inversion recovery magnetic resonance imaging (MRI) sequences, are lesions in the human brain that can be observed in both migraine and multiple sclerosis (MS). Seventeen migraine patients and 15 patients with relapsing-remitting multiple sclerosis with WMHs, and 17 healthy subjects age-and sex-matched to the migraine group were prospectively enrolled and underwent conventional and advanced MRI studies with diffusion-and perfusion-weighted imaging and single voxel proton magnetic resonance spectroscopy. In both disease groups, elevated T2 relaxation time, apparent diffusion coefficient (ADC) values, and decreased N-acetyl-aspartate levels were found in the intralesional white matter compared to the contralateral normal-appearing white matter (NAWM), while there was no difference between the hemispheres of the control subjects. Migraine patients had the lowest intralesional creatine + phosphocreatine and myo-inositol (mI) values among the three groups, while patients with MS showed the highest intralesional T1 and T2 relaxation times, ADC, and mI values. In the contralateral NAWM, the same trend with mI changes was observed in migraineurs and MS patients. No differences in perfusion variables were observed in any groups. Our multimodal study showed that tissue damage is detectable in both diseases. Despite the differences in various advanced MRI measures, with more severe injury detected in MS lesions, we could not clearly differentiate the two white matter lesion types.

Reduced Anterior Cingulate Glutamate in Pediatric Major Depression: A Magnetic Resonance Spectroscopy Study