Explore the vast range of titles available.

EEG-based deep learning models have trended toward models that are designed to perform classification on any individual (cross-participant models). However, because EEG varies across participants due to non-stationarity and individual differences, certain guidelines must be followed for partitioning data into training, validation, and testing sets, in order for cross-participant models to avoid overestimation of model accuracy. Despite this necessity, the majority of EEG-based cross-participant models have not adopted such guidelines. Furthermore, some data repositories may unwittingly contribute to the problem by providing partitioned test and non-test datasets for reasons such as competition support. In this study, we demonstrate how improper dataset partitioning and the resulting improper training, validation, and testing of a cross-participant model leads to overestimated model accuracy. We demonstrate this mathematically, and empirically, using five publicly available datasets. To build the cross-participant models for these datasets, we replicate published results and demonstrate how the model accuracies are significantly reduced when proper EEG cross-participant model guidelines are followed. Our empirical results show that by not following these guidelines, error rates of cross-participant models can be underestimated between 35% and 3900%. This misrepresentation of model performance for the general population potentially slows scientific progress toward truly high-performing classification models.

Global signal regression (GSR) is one of the most debated preprocessing strategies for resting-state functional MRI. GSR effectively removes global artifacts driven by motion and respiration, but also discards globally distributed neural information and introduces negative correlations between certain brain regions. The vast majority of previous studies have focused on the effectiveness of GSR in removing imaging artifacts, as well as its potential biases. Given the growing interest in functional connectivity fingerprinting, here we considered the utilitarian question of whether GSR strengthens or weakens associations between resting-state functional connectivity (RSFC) and multiple behavioral measures across cognition, personality and emotion. By applying the variance component model to the Brain Genomics Superstruct Project (GSP), we found that behavioral variance explained by whole-brain RSFC increased by an average of 47% across 23 behavioral measures after GSR. In the Human Connectome Project (HCP), we found that behavioral variance explained by whole-brain RSFC increased by an average of 40% across 58 behavioral measures, when GSR was applied after ICA-FIX de-noising. To ensure generalizability, we repeated our analyses using kernel regression. GSR improved behavioral prediction accuracies by an average of 64% and 12% in the GSP and HCP datasets respectively. Importantly, the results were consistent across methods. A behavioral measure with greater RSFC-explained variance (using the variance component model) also exhibited greater prediction accuracy (using kernel regression). A behavioral measure with greater improvement in behavioral variance explained after GSR (using the variance component model) also enjoyed greater improvement in prediction accuracy after GSR (using kernel regression). Furthermore, GSR appeared to benefit task performance measures more than self-reported measures. Since GSR was more effective at removing motion-related and respiratory-related artifacts, GSR-related increases in variance explained and prediction accuracies were unlikely the result of motion-related or respiratory-related artifacts. However, it is worth emphasizing that the current study focused on whole-brain RSFC, so it remains unclear whether GSR improves RSFC-behavioral associations for specific connections or networks. Overall, our results suggest that at least in the case for young healthy adults, GSR strengthens the associations between RSFC and most (although not all) behavioral measures. Code for the variance component model and ridge regression can be found here: https://github.com/ThomasYeoLab/CBIG/tree/master/stable_projects/preprocessing/Li2019_GSR. •Global signal regression improves RSFC-behavior associations.•Global signal regression improves RSFC-based behavioral prediction accuracies.•Improvements replicated across two large-scale datasets and methods.•Task-performance measures enjoyed greater improvements than self-reported ones.•GSR beneficial even after ICA-FIX.

Finite element (FE) model studies have made important contributions to our understanding of functional biomechanics of the lumbar spine. However, if a model is used to answer clinical and biomechanical questions over a certain population, their inherently large inter-subject variability has to be considered. Current FE model studies, however, generally account only for a single distinct spinal geometry with one set of material properties. This raises questions concerning their predictive power, their range of results and on their agreement with in vitro and in vivo values. Eight well-established FE models of the lumbar spine (L1-5) of different research centers around the globe were subjected to pure and combined loading modes and compared to in vitro and in vivo measurements for intervertebral rotations, disc pressures and facet joint forces. Under pure moment loading, the predicted L1-5 rotations of almost all models fell within the reported in vitro ranges, and their median values differed on average by only 2° for flexion-extension, 1° for lateral bending and 5° for axial rotation. Predicted median facet joint forces and disc pressures were also in good agreement with published median in vitro values. However, the ranges of predictions were larger and exceeded those reported in vitro, especially for the facet joint forces. For all combined loading modes, except for flexion, predicted median segmental intervertebral rotations and disc pressures were in good agreement with measured in vivo values. In light of high inter-subject variability, the generalization of results of a single model to a population remains a concern. This study demonstrated that the pooled median of individual model results, similar to a probabilistic approach, can be used as an improved predictive tool in order to estimate the response of the lumbar spine.

Due to its safety, portability, and cheapness, transcranial direct current stimulation (tDCS) use largely increased in research and clinical settings. Despite tDCS’s wide application, previous works pointed out inconsistent and low replicable results, sometimes leading to extreme conclusions about tDCS’s ineffectiveness in modulating behavioral performance across cognitive domains. Traditionally, this variability has been linked to significant differences in the stimulation protocols across studies, including stimulation parameters, target regions, and electrodes montage. Here, we reviewed and discussed evidence of heterogeneity emerging at the intra-study level, namely inter-individual differences that may influence the response to tDCS within each study. This source of variability has been largely neglected by literature, being results mainly analyzed at the group level. Previous research, however, highlighted that only a half—or less—of studies’ participants could be classified as responders, being affected by tDCS in the expected direction. Stable and variable inter-individual differences, such as morphological and genetic features vs. hormonal/exogenous substance consumption, partially account for this heterogeneity. Moreover, variability comes from experiments’ contextual elements, such as participants’ engagement/baseline capacity and individual task difficulty. We concluded that increasing knowledge on inter-dividual differences rather than undermining tDCS effectiveness could enhance protocols’ efficiency and reproducibility.

Quantifying movement variability is a crucial aspect for clinical and laboratory investigations in several contexts. However, very few studies have assessed, in detail, the intra-subject variability across movements and the inter-subject variability. Muscle synergies are a valuable method that can be used to assess such variability. In this study, we assess, in detail, intra-subject and inter-subject variability in a scenario based on a comprehensive dataset, including multiple repetitions of multi-directional reaching movements. The results show that muscle synergies are a valuable tool for quantifying variability at the muscle level and reveal that intra-subject variability is lower than inter-subject variability in synergy modules and related temporal coefficients, and both intra-subject and inter-subject similarity are higher than random synergy matching, confirming shared underlying control structures. The study deepens the available knowledge on muscle synergy-based motor function assessment and rehabilitation applications, discussing their applicability to real scenarios.

The purpose of this study is to create a white matter atlas of the human brain using diffusion tensor imaging (DTI) tractography and to describe the constant and variable features of the major pathways. DTI was acquired from 40 healthy right-handed adults and reconstructed tracts mapped within a common reference space (MNI). Group effect maps of each tract defined constant anatomical features while overlap maps were generated to study inter-subject variability and to compare DTI derived anatomy with a histological atlas. Two patients were studied to assess the localizing validity of the atlas. The DTI-derived maps are overall consistent with a previously published histological atlas. A statistically significant leftward asymmetry was found for the volume and number of streamlines of the cortico-spinal tract and the direct connections between Broca's and Wernicke's territories (long segment). A statistically significant rightward asymmetry was found for the inferior fronto-occipital fasciculus and the fronto-parietal connections (anterior segment) of the arcuate fasciculus. Furthermore, males showed a left lateralization of the fronto-temporal segment of the arcuate fasciculus (long segment), while females had a more bilateral distribution. In two patients with brain lesions, DTI was acquired and tractography used to show that the tracts affected by the lesions were correctly identified by the atlas. This study suggests that DTI-derived maps can be used together with a previous histological atlas to establish the relationship of focal lesions with nearby tracts and improve clinico-anatomical correlation. ►The anterior segment of the arcuate fasciculus and the inferior fronto-occipital fasciculus (IFOF) are asymmetric; with the right side larger than the left. ►Variability maps of the white matter produced with DTI tractography are consistent with the variability maps generated by prior postmortem histological studies. ►Our DTI-derived atlas is a valuable tool for learning the neuroanatomy of white matter, and establishing the relationship of focal lesions with nearby tracts.

Communication is challenging for disabled individuals, but with advancement of brain-computer interface (BCI) systems, alternative communication systems can be developed. Current BCI spellers, such as P300, SSVEP, and MI, have drawbacks like reliance on external stimuli or conversation irrelevant mental tasks. In contrast to these systems, Imagined speech based BCI systems rely on directly decoding the vowels/words user is thinking, making them more intuitive, user friendly and highly popular among Brain-Computer-Interface (BCI) researchers. However, more research needs to be conducted on how subject-specific characteristics such as mental state, age, handedness, nativeness and resting state activity affects the brain's output during imagined speech. In an overt speech, it is evident that native and non-native speakers' brains function differently. Therefore, this paper explores how nativeness to language affects EEG signals while imagining vowel phonemes, using brain-map analysis and scalogram and also investigates the inclusion of features extracted from resting state EEG with imagined state EEG. The Fourteen-channel EEG for Imagined Speech (FEIS) dataset was used to analyse the EEG signals recorded while imagining vowel phonemes for 16 subjects (nine native English and seven non-native Chinese). For the classification of vowel phonemes, different connectivity measures such as covariance, coherence, and Phase Synchronous Index-PSI were extracted and analysed using statistics based Multivariate Analysis of Variance (MANOVA) approach. Different fusion strategies (difference, concatenation, Common Spatial Pattern-CSP and Canonical Correlation Analysis-CCA) were carried out to incorporate resting state EEG connectivity measures with imagined state connectivity measures for enhancing the accuracy of imagined vowel phoneme recognition. Simulation results revealed that concatenating imagined state and rest state covariance and PSI features provided the maximum accuracy of 92.78% for native speakers and 94.07% for non-native speakers.

When using a cortical parcellation, it is generally assumed that the regions correspond across subjects, meaning regions with the same label are expected to have the same structural or functional roles from one subject to any other. However, at a fine-grained scale, environmental and genetic factors shape both cortex and white matter differently, making it challenging to consistently label all parcels for every subject. Brain networks can be constructed with regions as nodes and their connectivity as edges. One critical step while constructing those networks is the definition of the nodes due to the spatial inter-individual variability, which can limit the reliability of group studies’ results. In this work, we propose alignment criteria to register the brain nodes across subjects by allowing the permutation of tiny cortical regions. Those criteria account for multiple brain network perspectives built from different imaging modalities. Our across-subject multimodal alignment of brain networks includes constraints that restrict possible permutations to anatomically plausible ones. The identified permutations are finally applied to the brain networks not used for optimization, and also improve the alignment of these networks. This work has been validated on real magnetic resonance imaging data from the Human Connectome Project. When using a cortical parcellation, it is generally assumed that a labeled region has the same roles from one subject to any other for a structural or functional brain network’s perspective. However, at a fine-grained scale, inter-individual spatial variability due to environmental and genetic factors makes it challenging to consistently define the network nodes across subjects. A matching of the regions across subjects is proposed. It maximizes the similarity of structural and functional connectivity across subjects by permuting regions. This multimodal alignment criterion includes constraints to forbid anatomically unrealistic permutations. The identified permutations show robustness from one brain network modality to another if the proper optimization criterion with correct spatial constraints is selected.

A key challenge in functional neuroimaging is the meaningful combination of results across subjects. Even in a sample of healthy participants, brain morphology and functional organization exhibit considerable variability, such that no two individuals have the same neural activation at the same location in response to the same stimulus. This inter-subject variability limits inferences at the group-level as average activation patterns may fail to represent the patterns seen in individuals. A promising approach to multi-subject analysis is group independent component analysis (GICA), which identifies group components and reconstructs activations at the individual level. GICA has gained considerable popularity, particularly in studies where temporal response models cannot be specified. However, a comprehensive understanding of the performance of GICA under realistic conditions of inter-subject variability is lacking. In this study we use simulated functional magnetic resonance imaging (fMRI) data to determine the capabilities and limitations of GICA under conditions of spatial, temporal, and amplitude variability. Simulations, generated with the SimTB toolbox, address questions that commonly arise in GICA studies, such as: (1) How well can individual subject activations be estimated and when will spatial variability preclude estimation? (2) Why does component splitting occur and how is it affected by model order? (3) How should we analyze component features to maximize sensitivity to intersubject differences? Overall, our results indicate an excellent capability of GICA to capture between-subject differences and we make a number of recommendations regarding analytic choices for application to functional imaging data. ► We assess performance of group ICA under inter-subject variability. ► Spatial variability is captured well when activations overlap moderately. ► Component amplitude is well estimated when using a joint estimator. ► Splitting is affected by spatio-temporal variability, data quantity and quality.

•Methods that improve inter-subject decoding accuracy reduce inter-individual variability without losing signal specificity.•Functional alignment methods consistently improve inter-subject decoding on several datasets, with the best methods recovering half of the signal lost in anatomical-only alignment.•For whole-brain alignment, piecewise alignment (performed in non-overlapping regions) is more accurate and much more efficient than searchlight alignment.•Shared Response Model and Optimal Transport yield highest decoding accuracy gains. Inter-individual variability in the functional organization of the brain presents a major obstacle to identifying generalizable neural coding principles. Functional alignment—a class of methods that matches subjects’ neural signals based on their functional similarity—is a promising strategy for addressing this variability. To date, however, a range of functional alignment methods have been proposed and their relative performance is still unclear. In this work, we benchmark five functional alignment methods for inter-subject decoding on four publicly available datasets. Specifically, we consider three existing methods: piecewise Procrustes, searchlight Procrustes, and piecewise Optimal Transport. We also introduce and benchmark two new extensions of functional alignment methods: piecewise Shared Response Modelling (SRM), and intra-subject alignment. We find that functional alignment generally improves inter-subject decoding accuracy though the best performing method depends on the research context. Specifically, SRM and Optimal Transport perform well at both the region-of-interest level of analysis as well as at the whole-brain scale when aggregated through a piecewise scheme. We also benchmark the computational efficiency of each of the surveyed methods, providing insight into their usability and scalability. Taking inter-subject decoding accuracy as a quantification of inter-subject similarity, our results support the use of functional alignment to improve inter-subject comparisons in the face of variable structure-function organization. We provide open implementations of all methods used.