Variational mode decomposition-based EEG analysis for the classification of disorders of consciousness.

Aberrant alterations in any of the two dimensions of consciousness, namely awareness and arousal, can lead to the emergence of disorders of consciousness (DOC). The development of DOC may arise from more severe or targeted lesions in the brain, resulting in widespread functional abnormalities. However, when it comes to classifying patients with disorders of consciousness, particularly utilizing resting-state electroencephalogram (EEG) signals through machine learning methods, several challenges surface. The non-stationarity and intricacy of EEG data present obstacles in understanding neuronal activities and achieving precise classification. To address these challenges, this study proposes variational mode decomposition (VMD) of EEG before feature extraction along with machine learning models. By decomposing preprocessed EEG signals into specified modes using VMD, features such as sample entropy, spectral entropy, kurtosis, and skewness are extracted across these modes. The study compares the performance of the features extracted from VMD-based approach with the frequency band-based approach and also the approach with features extracted from raw-EEG. The classification process involves binary classification between unresponsive wakefulness syndrome (UWS) and the minimally conscious state (MCS), as well as multi-class classification (coma vs. UWS vs. MCS). Kruskal-Wallis test was applied to determine the statistical significance of the features and features with a significance of p < 0.05 were chosen for a second round of classification experiments. Results indicate that the VMD-based features outperform the features of other two approaches, with the ensemble bagged tree (EBT) achieving the highest accuracy of 80.5% for multi-class classification (the best in the literature) and 86.7% for binary classification. This approach underscores the potential of integrating advanced signal processing techniques and machine learning in improving the classification of patients with disorders of consciousness, thereby enhancing patient care and facilitating informed treatment decision-making.

Increased Entropy of Gamma Oscillations in the Frontal Region during Meditation.

Meditation practices are considered mental training and have increasingly received attention from the scientific community due to their potential psychological and physical health benefits. We compared the EEG data recorded from long-term rajayoga practitioners during different meditative and non-meditative periods. Minimum variance modified fuzzy entropy (MVMFE) is computed for each EEG band for all channels of a given lobe. The means across all the channel entropy values were obtained and compared during meditative and non-meditative states. Meditators showed higher frontal entropy in the lower gamma band (25-45Hz) during the meditative states. Independent component analysis was applied to ensure that muscle or eye artifacts did not contribute to the gamma activity. Our results extend previous findings on the changes in entropy observed in long-term meditators during rajayoga practice. Gamma band in EEG is implicated in cognitive processes requiring high-level processing such as attention, learning, memory control, and retrieval. Gamma activity is also suggested as a potential biomarker for therapeutic progress in patients with clinical depression. Based on our findings, there is an excellent possibility to utilize the practice of meditation as a training tool to strengthen the neural circuits, where age-related degeneration is making its pathological impact.

Midline EEG Functional Connectivity As Biomarker for Conscious States in Sleep and Wakefulness.

Functional connectivity (FC) between different cortical regions of the brain has long been hypothesized to be necessary for conscious states in several modeling and empirical studies. The work presented herein estimates the FC between two bipolar midline electroencephalogram (EEG) recordings to evaluate its utility in discriminating consciousness levels across wakefulness and sleep. Consciousness levels were defined as Low, Medium, and High depending upon the ability of a subject to self-report their experiences at a later stage. The sleep EDF [expanded] dataset available in the Physionet data repository was used for analyses. FC was estimated using the debiased estimator of the squared Weighted Phase Lag Index (dWPLI2) metric. A total of 40 features extracted from the FC spectra for 10 EEG sub-bands were considered. FC trends demonstrated the highest alpha synchrony in the 'Low' conscious state. While the 'Medium' conscious state demonstrated superior phase synchronization in the low-gamma band, the 'High' conscious state was characterized by comparatively lower phase synchronization in all frequency bands. A Multi-Layer Perceptron (MLP) framework using a combination of 7 features yielded the highest cross-validation accuracy of 95.15% in distinguishing these conscious states. The study results provide a pertinent validation for the hypothesis that midline EEG FC is a reliable and robust signature of conscious states in sleep and wakefulness.

Brain Functional Connectivity as Biomarker for Propofol-Induced Alterations of Consciousness.

Understanding neural correlates of consciousness and its alterations poses a grand challenge for modern neuroscience. Even though recent years of research have shown many conceptual and empirical advances, the evolution of a system that can track anesthesia-induced loss of consciousness is hindered by the lack of reliable markers. The work presented herein estimates the functional connectivity (FC) between 21 scalp electroencephalogram (EEG) recordings to evaluate its utility in characterizing changes in brain networks during propofol sedation. The sedation dataset in the University of Cambridge data repository was used for analyses. FC was estimated using the debiased estimator of the squared Weighted Phase Lag Index (dWPLI2). Spectral FC networks before, during, and after sedation was considered for 5 EEG sub-bands. Results demonstrated significantly higher alpha band FC during baseline, mild and moderate sedation, and recovery stages. A striking association between frontal brain activity and propofol-sedation was also noticed. Furthermore, inhibition of frontal to parietal and frontal to occipital connections were observed as characteristic features of propofol-induced alterations in consciousness. A random subspace ensemble framework using logistic model tree as the base classifier, and 18 functional connections as features, yielded a cross-validation accuracy of 98.75% in discriminating baseline, mild and moderate sedation, and recovery stages. These findings validate that EEG-based FC can reliably distinguish altered conscious states associated with anaesthesia.

R-wave Amplitude Changes and Atypical Heart Rate Changes Accompanying Breath Hold During Low Breathing Rates.

This paper reports an interesting phenomenon that the amplitude of the QRS complex reduces during inhalation and increases during exhalation and the variation can exceed even 100% during very slow breathing rates (BR). The phenomenon has been consistent in all the nine normal male subjects we have studied with age ranging from 23 to 61 years. Further, at very low respiration rates which included breath holds both after inhalation and exhalation, there are highly significant second and third harmonics of the respiration frequency in the heart rate variability spectrum. On the other hand, the R-wave amplitude changes do not have any noticeable higher harmonics of the BR. Thus, the observed changes in the R-wave amplitude are neither connected to the movement of the heart nor changes in its relative position with respect to the recording electrodes nor the fluctuations in the stroke volume.

VR Glasses based Measurement of Responses to Dichoptic Stimuli: A Potential Tool for Quantifying Amblyopia?

Amblyopia is a medical condition in which the visual inputs from one of the eyes is suppressed by the brain. This leads to reduced visual acuity and poor or complete loss of stereopsis. Conventional clinical tests such as Worth 4-dot test and Bagolini striated lens test can only detect the presence of suppression but cannot quantify the extent of suppression, which is important for identifying the effectiveness of treatments for amblyopia. A novel approach for quantifying the level of suppression in amblyopia is proposed in this paper. We hypothesize that the level of suppression in amblyopia can be measured by measuring the symmetry/asymmetry in the suppression experienced during a dichoptic image recognition task. Preliminary studies done on fifty one normal subjects prove that the differences between the accuracies of the left and right eyes can be used as a measure of asymmetry. Equivalence test performed using 'two-one-sided t-tests' procedure shows that the equivalence of the accuracies of left and right eyes for normal subjects is statistically significant (p = .03, symmetric equivalence margin of 5 percentage points). To validate this method, six amblyopic children underwent this test and the results obtained are promising. To the knowledge of the authors, this is the first work to make use of VR glasses and dichoptic image recognition task for quantifying the level of ocular suppression in amblyopic patients.

Voice source characterization using pitch synchronous discrete cosine transform for speaker identification.

A characterization of the voice source (VS) signal by the pitch synchronous (PS) discrete cosine transform (DCT) is proposed. With the integrated linear prediction residual (ILPR) as the VS estimate, the PS DCT of the ILPR is evaluated as a feature vector for speaker identification (SID). On TIMIT and YOHO databases, using a Gaussian mixture model (GMM)-based classifier, it performs on par with existing VS-based features. On the NIST 2003 database, fusion with a GMM-based classifier using MFCC features improves the identification accuracy by 12% in absolute terms, proving that the proposed characterization has good promise as a feature for SID studies.

Estimation of voice-onset time in continuous speech using temporal measures.

This paper proposes an automatic acoustic-phonetic method for estimating voice-onset time of stops. This method requires neither transcription of the utterance nor training of a classifier. It makes use of the plosion index for the automatic detection of burst onsets of stops. Having detected the burst onset, the onset of the voicing following the burst is detected using the epochal information and a temporal measure named the maximum weighted inner product. For validation, several experiments are carried out on the entire TIMIT database and two of the CMU Arctic corpora. The performance of the proposed method compares well with three state-of-the-art techniques.

Detection of the closure-burst transitions of stops and affricates in continuous speech using the plosion index.

Automatic and accurate detection of the closure-burst transition events of stops and affricates serves many applications in speech processing. A temporal measure named the plosion index is proposed to detect such events, which are characterized by an abrupt increase in energy. Using the maxima of the pitch-synchronous normalized cross correlation as an additional temporal feature, a rule-based algorithm is designed that aims at selecting only those events associated with the closure-burst transitions of stops and affricates. The performance of the algorithm, characterized by receiver operating characteristic curves and temporal accuracy, is evaluated using the labeled closure-burst transitions of stops and affricates of the entire TIMIT test and training databases. The robustness of the algorithm is studied with respect to global white and babble noise as well as local noise using the TIMIT test set and on telephone quality speech using the NTIMIT test set. For these experiments, the proposed algorithm, which does not require explicit statistical training and is based on two one-dimensional temporal measures, gives a performance comparable to or better than the state-of-the-art methods. In addition, to test the scalability, the algorithm is applied on the Buckeye conversational speech corpus and databases of two Indian languages.

Low cost calibrated mechanical noisemaker for hearing screening of neonates in resource constrained settings.

BACKGROUND & OBJECTIVES: There is a need to develop an affordable and reliable tool for hearing screening of neonates in resource constrained, medically underserved areas of developing nations. This study valuates a strategy of health worker based screening of neonates using a low cost mechanical calibrated noisemaker followed up with parental monitoring of age appropriate auditory milestones for detecting severe-profound hearing impairment in infants by 6 months of age. METHODS: A trained health worker under the supervision of a qualified audiologist screened 425 neonates of whom 20 had confirmed severe-profound hearing impairment. Mechanical calibrated noisemakers of 50, 60, 70 and 80 dB (A) were used to elicit the behavioural responses. The parents of screened neonates were instructed to monitor the normal language and auditory milestones till 6 months of age. This strategy was validated against the reference standard consisting of a battery of tests - namely, auditory brain stem response (ABR), otoacoustic emissions (OAE) and behavioural assessment at 2 years of age. Bayesian prevalence weighted measures of screening were calculated. RESULTS: The sensitivity and specificity was high with least false positive referrals for 70 and 80 dB (A) noisemakers. All the noisemakers had 100 per cent negative predictive value. 70 and 80 dB (A) noisemakers had high positive likelihood ratios of 19 and 34, respectively. The probability differences for pre- and post- test positive was 43 and 58 for 70 and 80 dB (A) noisemakers, respectively. INTERPRETATION & CONCLUSIONS: In a controlled setting, health workers with primary education can be trained to use a mechanical calibrated noisemaker made of locally available material to reliably screen for severe-profound hearing loss in neonates. The monitoring of auditory responses could be done by informed parents. Multi-centre field trials of this strategy need to be carried out to examine the feasibility of community health care workers using it in resource constrained settings of developing nations to implement an effective national neonatal hearing screening programme.

Quality assessment in magnetic resonance images.

Assessing quality of medical images is critical because the subsequent course of actions depend on it. Extensive use of clinical magnetic resonance (MR) imaging warrants a study in image indices used for MR images. The quality of MR images assumes particular significance in the determination of their reliability for diagnostics, response to therapies, synchronization across different imaging cycles, optimization of interventional imaging, and image restoration. In this paper, we review various techniques developed for the assessment of MR image quality. The reported quality indices can be broadly classified as subjective/objective, automatic/semi-automatic, region-of-interest/non-region-of-interest-based, full-reference/no-reference and HVS incorporated/non-HVS incorporated. The trade-of across the various indices lies in the computational complexity, assumptions, repeatability, and resemblance to human perception. Because images are eventually viewed by the human eye, it is found that it is important to incorporate aspects of human visual response, sensitivity, and characteristics in computing quality indices. Additionally, no-reference metrics are the most relevant due to the lack of availability of a golden standard against which images could be compared. Techniques that are objective and automatic are preferred for their repeatability and to eliminate avoidable errors due to factors like stress, which arise in human intervention.

Composite MR image reconstruction and unaliasing for general trajectories using neural networks.

In rapid parallel magnetic resonance imaging, the problem of image reconstruction is challenging. Here, a novel image reconstruction technique for data acquired along any general trajectory in neural network framework, called "Composite Reconstruction And Unaliasing using Neural Networks" (CRAUNN), is proposed. CRAUNN is based on the observation that the nature of aliasing remains unchanged whether the undersampled acquisition contains only low frequencies or includes high frequencies too. Here, the transformation needed to reconstruct the alias-free image from the aliased coil images is learnt, using acquisitions consisting of densely sampled low frequencies. Neural networks are made use of as machine learning tools to learn the transformation, in order to obtain the desired alias-free image for actual acquisitions containing sparsely sampled low as well as high frequencies. CRAUNN operates in the image domain and does not require explicit coil sensitivity estimation. It is also independent of the sampling trajectory used, and could be applied to arbitrary trajectories as well. As a pilot trial, the technique is first applied to Cartesian trajectory-sampled data. Experiments performed using radial and spiral trajectories on real and synthetic data, illustrate the performance of the method. The reconstruction errors depend on the acceleration factor as well as the sampling trajectory. It is found that higher acceleration factors can be obtained when radial trajectories are used. Comparisons against existing techniques are presented. CRAUNN has been found to perform on par with the state-of-the-art techniques. Acceleration factors of up to 4, 6 and 4 are achieved in Cartesian, radial and spiral cases, respectively.

Improved k-t BLAST for fast fMR imaging.

A popular dynamic imaging technique, k-t BLAST (ktB) is studied here for fMR imaging. ktB utilizes correlations in k-space and time, to reconstruct the image time series with only a fraction of the data. The algorithm works by unwrapping the aliased Fourier conjugate space of k-t (y-f-space). The unwrapping process utilizes the estimate of the true y-f-space, by acquiring densely sampled low k-space data. The drawbacks of this method include separate training scan, blurred training estimates and aliased phase maps. The proposed changes are incorporation of phase information from the training map and using generalized-series-extrapolated training map. The proposed technique is compared with ktB on real fMRI data. The proposed changes allow for ktB to operate at an acceleration factor of 6. Performance is evaluated by comparing activation maps obtained using reconstructed images. An improvement of up to 10 dB is observed in the PSNR of activation maps. Besides, a 10% reduction in RMSE is obtained over the entire time series of fMRI images. Peak improvement of the proposed method over ktB is 35%, averaged over five data sets.

Spectral analysis of noise in the neonatal intensive care unit.

OBJECTIVE: To perform spectral analysis of noise generated by equipments and activities in a level III neonatal intensive care unit (NICU) and measure the real time sequential hourly noise levels over a 15 day period. METHODS: Noise generated in the NICU by individual equipments and activities were recorded with a digital spectral sound analyzer to perform spectral analysis over 0.5 - 8 KHz. Sequential hourly noise level measurements in all the rooms of the NICU were done for 15 days using a digital sound pressure level meter . Independent sample t test and one way ANOVA were used to examine the statistical significance of the results. The study has a 90 % power to detect at least 4 dB differences from the recommended maximum of 50 dB with 95 % confidence. RESULTS: The mean noise levels in the ventilator room and stable room were 19.99 dB (A) sound pressure level (SPL) and 11.81 dB (A) SPL higher than the maximum recommended of 50 dB (A) respectively ( p < 0.001). The equipments generated 19.11 dB SPL higher than the recommended norms in 1 - 8 KHz spectrum. The activities generated 21.49 dB SPL higher than the recommended norms in 1 - 8 KHz spectrum ( p< 0.001). The ventilator and nebulisers produced excess noise of 8.5 dB SPL at the 0.5 KHz spectrum. CONCLUSION: Noise level in the NICU is unacceptably high .Spectral analysis of equipment and activity noise have shown noise predominantly in the 1 - 8 KHz spectrum. These levels warrant immediate implementation of noise reduction protocols as a standard of care in the NICU.

Polarization-rich continuous wave direct imaging: modeling and visualization.

We report a study and comparison of continuous-wave, optical polarization difference imaging (PDI) and polarization modulation imaging (PMI) for imaging through scattering media. The problem is cast in the framework of a theoretical estimation, and the comparison is based on three visualization parameters, namely, the magnitude, the degree, and the orientation of the polarization. We show that PDI is superior in estimating the first two parameters in active imaging under specific conditions, while the PMI is suitable for passive imaging and is the only way to estimate polarization orientation. We also propose new schemes for rendering polarization information as a color image and for applying the newly introduced polarization-orientation imaging for segmentation. Simulation and experimental results verify the theoretical conclusions.

Wavelet-based estimation of hemodynamic response function from fMRI data.

We present a new algorithm to estimate hemodynamic response function (HRF) and drift components of fMRI data in wavelet domain. The HRF is modeled by both parametric and nonparametric models. The functional Magnetic resonance Image (fMRI) noise is modeled as a fractional brownian motion (fBm). The HRF parameters are estimated in wavelet domain by exploiting the property that wavelet transforms with a sufficient number of vanishing moments decorrelates a fBm process. Using this property, the noise covariance matrix in wavelet domain can be assumed to be diagonal whose entries are estimated using the sample variance estimator at each scale. We study the influence of the sampling rate of fMRI time series and shape assumption of HRF on the estimation performance. Results are presented by adding synthetic HRFs on simulated and null fMRI data. We also compare these methods with an existing method,(1) where correlated fMRI noise is modeled by a second order polynomial functions.

Contextual encoding in uniform and adaptive mesh-based lossless compression of MR images.

We propose and evaluate a number of novel improvements to the mesh-based coding scheme for 3-D brain magnetic resonance images. This includes: 1) elimination of the clinically irrelevant background leading to meshing of only the brain part of the image; 2) content-based (adaptive) mesh generation using spatial edges and optical flow between two consecutive slices; 3) a simple solution for the aperture problem at the edges, where an accurate estimation of motion vectors is not possible; and 4) context-based entropy coding of the residues after motion compensation using affine transformations. We address only lossless coding of the images, and compare the performance of uniform and adaptive mesh-based schemes. The bit rates achieved (about 2 bits per voxel) by these schemes are comparable to those of the state-of-the-art three-dimensional (3-D) wavelet-based schemes. The mesh-based schemes have been shown to be effective for the compression of 3-D brain computed tomography data also. Adaptive mesh-based schemes perform marginally better than the uniform mesh-based methods, at the expense of increased complexity.

Fetal lung maturity analysis using ultrasound image features.

This pilot study was carried out to find the feasibility of analyzing the maturity of the fetal lung using ultrasound images. Data were collected from normal pregnant women at intervals of two weeks from the gestation age of 24 to 38 weeks. Images were acquired at two centers located at different geographical locations. The total data acquired consisted of 750 images of immature and 250 images of mature class. A region of interest of 64 x 64 pixels was used for extracting the features. Various textural features were computed from the fetal lung and liver images. The ratios of fetal lung to liver feature values were investigated as possible indexes for classifying the images into those from mature (reduced pulmonary risk) and immature (possible pulmonary risk) lung. The features used are fractal dimension, lacunarity, and features derived from the histogram of the images. The following classifiers were used to classify the fetal lung images as belonging to mature or immature lung: nearest neighbor, k-nearest neighbor, modified k-nearest neighbor, multilayer perceptron, radial basis function network, and support vector machines. The classification accuracy obtained for the testing set ranges from 73% to 96%.

An investigation into the feasibility of fetal lung maturity prediction using statistical textural features.

Fetal lung and liver tissues were examined by ultrasound in 240 subjects during 24 to 38 weeks of gestational age in order to investigate the feasibility of predicting the maturity of the lung from the textural features of sonograms. A region of interest of 64 x 64 pixels is used for extracting textural features. Since the histological properties of the liver are claimed to remain constant with respect to gestational age, features obtained from the lung region are compared with those from liver. Though the mean values of some of the features show a specific trend with respect to gestation age, the variance is too high to guarantee definite prediction of the gestational age. Thus, we restricted our purview to an investigation into the feasibility of fetal lung maturity prediction using statistical textural features. Out of 64 features extracted, those features that are correlated with gestation age and less computationally intensive are selected. The results of our study show that the sonographic features hold some promise in determining whether the fetal lung is mature or immature.

Wavelet domain nonlinear filtering for evoked potential signal enhancement.

A wavelet domain nonlinear filtering method for improving the signal-to-noise ratio (SNR) of the evoked potentials (EP) is proposed. The method modifies the selective filtering technique proposed for edge detection in images by Xu et al. for the case of signals which require a smooth transition at the edge points. It identifies the significant features of a noisy signal based on the correlation between the scales of its nonorthogonal subband decompositions. The signal transition information from interscale correlation coupled with the change in variance around the identified transition region is used to differentiate between noise and the signal. A nonlinear function such as a Gaussian smoothing function applied around the identified edge in the wavelet domain leads to smoothing in the signal space also. Numerical results obtained by applying the proposed nonlinear filtering method on middle latency responses of auditory evoked potentials show that the method is well suited for signal enhancement applications.