EEG recordings are generally affected by interference from physiological and non-physiological sources which may obscure underlying brain activity and hinder effective EEG analysis. In particular, cardiac interference can be caused by the electrical activity of the heart and/or cardiovascular activity related to blood flow. Successful EEG application in sports science settings requires a method for artifact removal that is automatic and flexible enough to be applied in a variety of acquisition conditions without requiring simultaneous ECG recordings that could restrict movement. We developed an automatic method for classifying and removing both electrical cardiac and cardiovascular artifacts (ARCI) that does not require additional ECG recording. Our method employs independent component analysis (ICA) to isolate data independent components (ICs) and identifies the artifactual ICs by evaluating specific IC features in the time and frequency domains. We applied ARCI to EEG datasets with cued artifacts and acquired during an eyes-closed condition. Data were recorded using a standard EEG wet cap with either 128 or 64 electrodes and using a novel dry electrode cap with either 97 or 64 dry electrodes. All data were decomposed into different numbers of components to evaluate the effect of ICA decomposition level on effective cardiac artifact detection. ARCI performance was evaluated by comparing automatic ICs classifications with classifications performed by experienced investigators. Automatic and investigator classifications were highly consistent resulting in an overall accuracy greater than 99% in all datasets and decomposition levels, and an average sensitivity greater than 90%. Best results were attained when data were decomposed into a fewer number of components where the method achieved perfect sensitivity (100%). Performance was also evaluated by comparing automatic component classification with externally recorded ECG. Results showed that ICs automatically classified as artifactual were significantly correlated with ECG activity whereas the other ICs were not. We also assessed that the interference affecting EEG signals was reduced by more than 82% after automatic artifact removal. Overall, ARCI represents a significant step in the detection and removal of cardiac-related EEG artifacts and can be applied in a variety of acquisition settings making it ideal for sports science applications.

Accurate removal of magnetic resonance imaging (MRI) signal outside the brain, a.k.a., skull stripping, is a key step in the brain image pre-processing pipelines. In rodents, this is mostly achieved by manually editing a brain mask, which is time-consuming and operator dependent. Automating this step is particularly challenging in rodents as compared to humans, because of differences in brain/scalp tissue geometry, image resolution with respect to brain-scalp distance, and tissue contrast around the skull. In this study, we proposed a deep-learning-based framework, U-Net, to automatically identify the rodent brain boundaries in MR images. The U-Net method is robust against inter-subject variability and eliminates operator dependence. To benchmark the efficiency of this method, we trained and validated our model using both in-house collected and publicly available datasets. In comparison to current state-of-the-art methods, our approach achieved superior averaged Dice similarity coefficient to ground truth T2-weighted rapid acquisition with relaxation enhancement and T2∗-weighted echo planar imaging data in both rats and mice (all p < 0.05), demonstrating robust performance of our approach across various MRI protocols.

Brief fragments of sleep shorter than 15 s are defined as microsleep episodes (MSEs), often subjectively perceived as sleepiness. Their main characteristic is a slowing in frequency in the electroencephalogram (EEG), similar to stage N1 sleep according to standard criteria. The maintenance of wakefulness test (MWT) is often used in a clinical setting to assess vigilance. Scoring of the MWT in most sleep-wake centers is limited to classical definition of sleep (30 s epochs), and MSEs are mostly not considered in the absence of established scoring criteria defining MSEs but also because of the laborious work. We aimed for automatic detection of MSEs with machine learning, i.e., with deep learning based on raw EEG and EOG data as input. We analyzed MWT data of 76 patients. Experts visually scored wakefulness, and according to recently developed scoring criteria MSEs, microsleep episode candidates (MSEc), and episodes of drowsiness (ED). We implemented segmentation algorithms based on convolutional neural networks (CNNs) and a combination of a CNN with a long-short term memory (LSTM) network. A LSTM network is a type of a recurrent neural network which has a memory for past events and takes them into account. Data of 53 patients were used for training of the classifiers, 12 for validation and 11 for testing. Our algorithms showed a good performance close to human experts. The detection was very good for wakefulness and MSEs and poor for MSEc and ED, similar to the low inter-expert reliability for these borderline segments. We performed a visualization of the internal representation of the data by the artificial neuronal network performing best using t-distributed stochastic neighbor embedding (t-SNE). Visualization revealed that MSEs and wakefulness were mostly separable, though not entirely, and MSEc and ED largely intersected with the two main classes. We provide a proof of principle that it is feasible to reliably detect MSEs with deep neuronal networks based on raw EEG and EOG data with a performance close to that of human experts. The code of the algorithms (https://github.com/alexander-malafeev/microsleep-detection) and data (https://zenodo.org/record/3251716) are available.

Existing tools for the preprocessing of EEG data provide a large choice of methods to suitably prepare and analyse a given dataset. Yet it remains a challenge for the average user to integrate methods for batch processing of the increasingly large datasets of modern research, and compare methods to choose an optimal approach across the many possible parameter configurations. Additionally, many tools still require a high degree of manual decision making for, e.g., the classification of artifacts in channels, epochs or segments. This introduces extra subjectivity, is slow, and is not reproducible. Batching and well-designed automation can help to regularize EEG preprocessing, and thus reduce human effort, subjectivity, and consequent error. The Computational Testing for Automated Preprocessing (CTAP) toolbox facilitates: (i) batch processing that is easy for experts and novices alike; (ii) testing and comparison of preprocessing methods. Here we demonstrate the application of CTAP to high-resolution EEG data in three modes of use. First, a linear processing pipeline with mostly default parameters illustrates ease-of-use for naive users. Second, a branching pipeline illustrates CTAP's support for comparison of competing methods. Third, a pipeline with built-in parameter-sweeping illustrates CTAP's capability to support data-driven method parameterization. CTAP extends the existing functions and data structure from the well-known EEGLAB toolbox, based on Matlab, and produces extensive quality control outputs. CTAP is available under MIT open-source licence from https://github.com/bwrc/ctap.

Functional magnetic resonance imaging (fMRI) during a resting-state condition can reveal the co-activation of specific brain regions in distributed networks, called resting-state networks, which are selected by independent component analysis (ICA) of the fMRI data. One of the major difficulties with component analysis is the automatic selection of the ICA features related to brain activity. In this study we describe a method designed to automatically select networks of potential functional relevance, specifically, those regions known to be involved in motor function, visual processing, executive functioning, auditory processing, memory, and the default-mode network. To do this, image analysis was based on probabilistic ICA as implemented in FSL software. After decomposition, the optimal number of components was selected by applying a novel algorithm which takes into account, for each component, Pearson's median coefficient of skewness of the spatial maps generated by FSL, followed by clustering, segmentation, and spectral analysis. To evaluate the performance of the approach, we investigated the resting-state networks in 25 subjects. For each subject, three resting-state scans were obtained with a Siemens Allegra 3 T scanner (NYU data set). Comparison of the visually and the automatically identified neuronal networks showed that the algorithm had high accuracy (first scan: 95%, second scan: 95%, third scan: 93%) and precision (90%, 90%, 84%). The reproducibility of the networks for visual and automatic selection was very close: it was highly consistent in each subject for the default-mode network (≥92%) and the occipital network, which includes the medial visual cortical areas (≥94%), and consistent for the attention network (≥80%), the right and/or left lateralized frontoparietal attention networks, and the temporal-motor network (≥80%). The automatic selection method may be used to detect neural networks and reduce subjectivity in ICA component assessment.

During presurgical evaluation for focal epilepsy patients, the evidence supporting the use of high frequency oscillations (HFOs) for delineating the epileptogenic zone (EZ) increased over the past decade. This study aims to develop and validate an integrated automatic detection, classification and imaging pipeline of HFOs with stereoelectroencephalography (SEEG) to narrow the gap between HFOs quantitative analysis and clinical application.

Physiological responses of two interacting individuals contain a wealth of information about the dyad: for example, the degree of engagement or trust. However, nearly all studies on dyadic physiological responses have targeted group-level analysis: e.g., correlating physiology and engagement in a large sample. Conversely, this paper presents a study where physiological measurements are combined with machine learning algorithms to dynamically estimate the engagement of individual dyads. Sixteen dyads completed 15-min naturalistic conversations and self-reported their engagement on a visual analog scale every 60 s. Four physiological signals (electrocardiography, skin conductance, respiration, skin temperature) were recorded, and both individual physiological features (e.g., each participant's heart rate) and synchrony features (indicating degree of physiological similarity between two participants) were extracted. Multiple regression algorithms were used to estimate self-reported engagement based on physiological features using either leave-interval-out crossvalidation (training on 14 60-s intervals from a dyad and testing on the 15th interval from the same dyad) or leave-dyad-out crossvalidation (training on 15 dyads and testing on the 16th). In leave-interval-out crossvalidation, the regression algorithms achieved accuracy similar to a 'baseline' estimator that simply took the median engagement of the other 14 intervals. In leave-dyad-out crossvalidation, machine learning achieved a slightly higher accuracy than the baseline estimator and higher accuracy than an independent human observer. Secondary analyses showed that removing synchrony features and personality characteristics from the input dataset negatively impacted estimation accuracy and that engagement estimation error was correlated with personality traits. Results demonstrate the feasibility of dynamically estimating interpersonal engagement during naturalistic conversation using physiological measurements, which has potential applications in both conversation monitoring and conversation enhancement. However, as many of our estimation errors are difficult to contextualize, further work is needed to determine acceptable estimation accuracies.

Purpose: In this work, we introduce a method to classify Multiple Sclerosis (MS) patients into four clinical profiles using structural connectivity information. For the first time, we try to solve this question in a fully automated way using a computer-based method. The main goal is to show how the combination of graph-derived metrics with machine learning techniques constitutes a powerful tool for a better characterization and classification of MS clinical profiles. Materials and Methods: Sixty-four MS patients [12 Clinical Isolated Syndrome (CIS), 24 Relapsing Remitting (RR), 24 Secondary Progressive (SP), and 17 Primary Progressive (PP)] along with 26 healthy controls (HC) underwent MR examination. T1 and diffusion tensor imaging (DTI) were used to obtain structural connectivity matrices for each subject. Global graph metrics, such as density and modularity, were estimated and compared between subjects' groups. These metrics were further used to classify patients using tuned Support Vector Machine (SVM) combined with Radial Basic Function (RBF) kernel. Results: When comparing MS patients to HC subjects, a greater assortativity, transitivity, and characteristic path length as well as a lower global efficiency were found. Using all graph metrics, the best F-Measures (91.8, 91.8, 75.6, and 70.6%) were obtained for binary (HC-CIS, CIS-RR, RR-PP) and multi-class (CIS-RR-SP) classification tasks, respectively. When using only one graph metric, the best F-Measures (83.6, 88.9, and 70.7%) were achieved for modularity with previous binary classification tasks. Conclusion: Based on a simple DTI acquisition associated with structural brain connectivity analysis, this automatic method allowed an accurate classification of different MS patients' clinical profiles.

Together, mitochondria and the endoplasmic reticulum (ER) occupy more than 20% of a cell's volume, and morphological abnormality may lead to cellular function disorders. With the rapid development of large-scale electron microscopy (EM), manual contouring and three-dimensional (3D) reconstruction of these organelles has previously been accomplished in biological studies. However, manual segmentation of mitochondria and ER from EM images is time consuming and thus unable to meet the demands of large data analysis. Here, we propose an automated pipeline for mitochondrial and ER reconstruction, including the mitochondrial and ER contact sites (MAMs). We propose a novel recurrent neural network to detect and segment mitochondria and a fully residual convolutional network to reconstruct the ER. Based on the sparse distribution of synapses, we use mitochondrial context information to rectify the local misleading results and obtain 3D mitochondrial reconstructions. The experimental results demonstrate that the proposed method achieves state-of-the-art performance.

Depression is a common mental disorder that seriously affects patients' social function and daily life. Its accurate diagnosis remains a big challenge in depression treatment. In this study, we used electroencephalography (EEG) and functional near-infrared spectroscopy (fNIRS) and measured the whole brain EEG signals and forehead hemodynamic signals from 25 depression patients and 30 healthy subjects during the resting state. On one hand, we explored the EEG brain functional network properties, and found that the clustering coefficient and local efficiency of the delta and theta bands in patients were significantly higher than those in normal subjects. On the other hand, we extracted brain network properties, asymmetry, and brain oxygen entropy as alternative features, used a data-driven automated method to select features, and established a support vector machine model for automatic depression classification. The results showed the classification accuracy was 81.8% when using EEG features alone and increased to 92.7% when using hybrid EEG and fNIRS features. The brain network local efficiency in the delta band, hemispheric asymmetry in the theta band and brain oxygen sample entropy features differed significantly between the two groups (p < 0.05) and showed high depression distinguishing ability indicating that they may be effective biological markers for identifying depression. EEG, fNIRS and machine learning constitute an effective method for classifying depression at the individual level.

This study aimed to determine if people living with HIV (PLWH) in preclinical human immunodeficiency virus (HIV)-associated neurocognitive disorder (HAND), with no clinical symptoms and without decreased daily functioning, suffer from brain volumetric alterations and its patterns.

Conventional magnetic resonance imaging (cMRI) is poorly sensitive to pathological changes related to multiple sclerosis (MS) in normal-appearing white matter (NAWM) and gray matter (GM), with the added difficulty of not being very reproducible. Quantitative MRI (qMRI), on the other hand, attempts to represent the physical properties of tissues, making it an ideal candidate for quantitative medical image analysis or radiomics. We therefore hypothesized that qMRI-based radiomic features have added diagnostic value in MS compared to cMRI. This study investigated the ability of cMRI (T1w) and qMRI features extracted from white matter (WM), NAWM, and GM to distinguish between MS patients (MSP) and healthy control subjects (HCS). We developed exploratory radiomic classification models on a dataset comprising 36 MSP and 36 HCS recruited in CHU Liege, Belgium, acquired with cMRI and qMRI. For each image type and region of interest, qMRI radiomic models for MS diagnosis were developed on a training subset and validated on a testing subset. Radiomic models based on cMRI were developed on the entire training dataset and externally validated on open-source datasets with 167 HCS and 10 MSP. Ranked by region of interest, the best diagnostic performance was achieved in the whole WM. Here the model based on magnetization transfer imaging (a type of qMRI) features yielded a median area under the receiver operating characteristic curve (AUC) of 1.00 in the testing sub-cohort. Ranked by image type, the best performance was achieved by the magnetization transfer models, with median AUCs of 0.79 (0.69-0.90, 90% CI) in NAWM and 0.81 (0.71-0.90) in GM. The external validation of the T1w models yielded an AUC of 0.78 (0.47-1.00) in the whole WM, demonstrating a large 95% CI and a low sensitivity of 0.30 (0.10-0.70). This exploratory study indicates that qMRI radiomics could provide efficient diagnostic information using NAWM and GM analysis in MSP. T1w radiomics could be useful for a fast and automated check of conventional MRI for WM abnormalities once acquisition and reconstruction heterogeneities have been overcome. Further prospective validation is needed, involving more data for better interpretation and generalization of the results.

Hippocampal volume is one of the main biomarkers of Alzheimer's Dementia (AD). Over the years, advanced tools that performed automatic segmentation of Magnetic Resonance Imaging (MRI) T13D scans have been developed, such as FreeSurfer (FS) and ACM-Adaboost (AA). Hippocampal volume is considered abnormal when it is below the 5th percentile of the normative population. The aim of this study was to set norms, established from the Alzheimer's Disease Neuroimaging Initiative (ADNI) population, for hippocampal volume measured with FS v.6.0 and AA tools in the neuGRID platform (www.neugrid2.eu) and demonstrate their applicability for the Italian population.

There is increasing interest in understanding how the phase and amplitude of distinct neural oscillations might interact to support dynamic communication within the brain. In particular, previous work has demonstrated a coupling between the phase of low frequency oscillations and the amplitude (or power) of high frequency oscillations during certain tasks, termed phase amplitude coupling (PAC). For instance, during visual processing in humans, PAC has been reliably observed between ongoing alpha (8-13 Hz) and gamma-band (>40 Hz) activity. However, the application of PAC metrics to electrophysiological data can be challenging due to numerous methodological issues and lack of coherent approaches within the field. Therefore, in this article we outline the various analysis steps involved in detecting PAC, using an openly available MEG dataset from 16 participants performing an interactive visual task. Firstly, we localized gamma and alpha-band power using the Fieldtrip toolbox, and extracted time courses from area V1, defined using a multimodal parcelation scheme. These V1 responses were analyzed for changes in alpha-gamma PAC, using four common algorithms. Results showed an increase in alpha (7-13 Hz)-gamma (40-100 Hz) PAC in response to the visual grating stimulus, though specific patterns of coupling were somewhat dependent upon the algorithm employed. Additionally, post-hoc analyses showed that these results were not driven by the presence of non-sinusoidal oscillations, and that trial length was sufficient to obtain reliable PAC estimates. Finally, throughout the article, methodological issues and practical guidelines for ongoing PAC research will be discussed.

Abnormalities in cortical connectivity and evoked responses have been extensively documented in autism spectrum disorder (ASD). However, specific signatures of these cortical abnormalities remain elusive, with data pointing toward abnormal patterns of both increased and reduced response amplitudes and functional connectivity. We have previously proposed, using magnetoencephalography (MEG) data, that apparent inconsistencies in prior studies could be reconciled if functional connectivity in ASD was reduced in the feedback (top-down) direction, but increased in the feedforward (bottom-up) direction. Here, we continue this line of investigation by assessing abnormalities restricted to the onset, feedforward inputs driven, component of the response to vibrotactile stimuli in somatosensory cortex in ASD. Using a novel method that measures the spatio-temporal divergence of cortical activation, we found that relative to typically developing participants, the ASD group was characterized by an increase in the initial onset component of the cortical response, and a faster spread of local activity. Given the early time window, the results could be interpreted as increased thalamocortical feedforward connectivity in ASD, and offer a plausible mechanism for the previously observed increased response variability in ASD, as well as for the commonly observed behaviorally measured tactile processing abnormalities associated with the disorder.

Using functional magnetic resonance imaging in awake behaving monkeys we investigated how species-specific vocalizations are represented in auditory and auditory-related regions of the macaque brain. We found clusters of active voxels along the ascending auditory pathway that responded to various types of complex sounds: inferior colliculus (IC), medial geniculate nucleus (MGN), auditory core, belt, and parabelt cortex, and other parts of the superior temporal gyrus (STG) and sulcus (STS). Regions sensitive to monkey calls were most prevalent in the anterior STG, but some clusters were also found in frontal and parietal cortex on the basis of comparisons between responses to calls and environmental sounds. Surprisingly, we found that spectrotemporal control sounds derived from the monkey calls ("scrambled calls") also activated the parietal and frontal regions. Taken together, our results demonstrate that species-specific vocalizations in rhesus monkeys activate preferentially the auditory ventral stream, and in particular areas of the antero-lateral belt and parabelt.

Successful speech perception in multi-speaker environments depends on auditory scene analysis, comprising auditory object segregation and grouping, and on focusing attention toward the speaker of interest. Changes in speaker settings (e.g., in speaker position) require object re-selection and attention re-focusing. Here, we tested the processing of changes in a realistic multi-speaker scenario in younger and older adults, employing a speech-perception task, and event-related potential (ERP) measures. Sequences of short words (combinations of company names and values) were simultaneously presented via four loudspeakers at different locations, and the participants responded to the value of a target company. Voice and position of the speaker of the target information were kept constant for a variable number of trials and then changed. Relative to the pre-change level, changes caused higher error rates, and more so in older than younger adults. The ERP analysis revealed stronger fronto-central N2 and N400 components in younger adults, suggesting a more effective inhibition of concurrent speech stimuli and enhanced language processing. The difference ERPs (post-change minus pre-change) indicated a change-related N400 and late positive complex (LPC) over parietal areas in both groups. Only the older adults showed an additional frontal LPC, suggesting increased allocation of attentional resources after changes in speaker settings. In sum, changes in speaker settings are critical events for speech perception in multi-speaker environments. Especially older persons show deficits that could be based on less flexible inhibitory control and increased distraction.

Previous imaging studies on the brain mechanisms of spatial hearing have mainly focused on sounds varying in the horizontal plane. In this study, we compared activations in human auditory cortex (AC) and adjacent inferior parietal lobule (IPL) to sounds varying in horizontal location, distance, or space (i.e., different rooms). In order to investigate both stimulus-dependent and task-dependent activations, these sounds were presented during visual discrimination, auditory discrimination, and auditory 2-back memory tasks. Consistent with previous studies, activations in AC were modulated by the auditory tasks. During both auditory and visual tasks, activations in AC were stronger to sounds varying in horizontal location than along other feature dimensions. However, in IPL, this enhancement was detected only during auditory tasks. Based on these results, we argue that IPL is not primarily involved in stimulus-level spatial analysis but that it may represent such information for more general processing when relevant to an active auditory task.

Magnetoencephalography and electroencephalography (M/EEG) measure the weak electromagnetic signals generated by neuronal activity in the brain. Using these signals to characterize and locate neural activation in the brain is a challenge that requires expertise in physics, signal processing, statistics, and numerical methods. As part of the MNE software suite, MNE-Python is an open-source software package that addresses this challenge by providing state-of-the-art algorithms implemented in Python that cover multiple methods of data preprocessing, source localization, statistical analysis, and estimation of functional connectivity between distributed brain regions. All algorithms and utility functions are implemented in a consistent manner with well-documented interfaces, enabling users to create M/EEG data analysis pipelines by writing Python scripts. Moreover, MNE-Python is tightly integrated with the core Python libraries for scientific comptutation (NumPy, SciPy) and visualization (matplotlib and Mayavi), as well as the greater neuroimaging ecosystem in Python via the Nibabel package. The code is provided under the new BSD license allowing code reuse, even in commercial products. Although MNE-Python has only been under heavy development for a couple of years, it has rapidly evolved with expanded analysis capabilities and pedagogical tutorials because multiple labs have collaborated during code development to help share best practices. MNE-Python also gives easy access to preprocessed datasets, helping users to get started quickly and facilitating reproducibility of methods by other researchers. Full documentation, including dozens of examples, is available at http://martinos.org/mne.

Alzheimer's disease is associated with the cerebral accumulation of neurofibrillary tangles of hyperphosphorylated tau protein. The progressive occurrence of tau aggregates in different brain regions is closely related to neurodegeneration and cognitive impairment. However, our current understanding of tau propagation relies almost exclusively on postmortem histopathology, and the precise propagation dynamics of misfolded tau in the living brain remain poorly understood. Here we combine longitudinal positron emission tomography and dynamic network modeling to test the hypothesis that misfolded tau propagates preferably along neuronal connections. We follow 46 subjects for three or four annual positron emission tomography scans and compare their pathological tau profiles against brain network models of intracellular and extracellular spreading. For each subject, we identify a personalized set of model parameters that characterizes the individual progression of pathological tau. Across all subjects, the mean protein production rate was 0.21 ± 0.15 and the intracellular diffusion coefficient was 0.34 ± 0.43. Our network diffusion model can serve as a tool to detect non-clinical symptoms at an earlier stage and make informed predictions about the timeline of neurodegeneration on an individual personalized basis.