Interpretability of Multivariate Brain Maps in Linear Brain Decoding: Definition, and Heuristic Quantification in Multivariate Analysis of MEG Time-Locked Effects

Decoding N400m Evoked Component: A Tutorial on Multivariate Pattern Analysis for OP-MEG Data

Multivariate pattern analysis (MVPA) has played an extensive role in interpreting brain activity, which has been applied in studies with modalities such as functional Magnetic Resonance Imaging (fMRI), Magnetoencephalography (MEG) and Electroencephalography (EEG). The advent of wearable MEG systems based on optically pumped magnetometers (OPMs), i.e., OP-MEG, has broadened the application of bio-magnetism in the realm of neuroscience. Nonetheless, it also raises challenges in temporal decoding analysis due to the unique attributes of OP-MEG itself. The efficacy of decoding performance utilizing multimodal fusion, such as MEG-EEG, also remains to be elucidated. In this regard, we investigated the impact of several factors, such as processing methods, models and modalities, on the decoding outcomes of OP-MEG. Our findings indicate that the number of averaged trials, dimensionality reduction (DR) methods, and the number of cross-validation folds significantly affect the decoding performance of OP-MEG data. Additionally, decoding results vary across modalities and fusion strategy. In contrast, decoder type, resampling frequency, and sliding window length exert marginal effects. Furthermore, we introduced mutual information (MI) to investigate how information loss due to OP-MEG data processing affect decoding accuracy. Our study offers insights for linear decoding research using OP-MEG and expand its application in the fields of cognitive neuroscience.

Groupwise structural sparsity for discriminative voxels identification

This paper investigates the selection of voxels for functional Magnetic Resonance Imaging (fMRI) brain data. We aim to identify a comprehensive set of discriminative voxels associated with human learning when exposed to a neutral visual stimulus that predicts an aversive outcome. However, due to the nature of the unconditioned stimuli (typically a noxious stimulus), it is challenging to obtain sufficient sample sizes for psychological experiments, given the tolerability of the subjects and ethical considerations. We propose a stable hierarchical voting (SHV) mechanism based on stability selection to address this challenge. This mechanism enables us to evaluate the quality of spatial random sampling and minimizes the risk of false and missed detections. We assess the performance of the proposed algorithm using simulated and publicly available datasets. The experiments demonstrate that the regularization strategy choice significantly affects the results' interpretability. When applying our algorithm to our collected fMRI dataset, it successfully identifies sparse and closely related patterns across subjects and displays stable weight maps for three experimental phases under the fear conditioning paradigm. These findings strongly support the causal role of aversive conditioning in altering visual-cortical activity.

Bidirectional connectivity alterations in schizophrenia: a multivariate, machine-learning approach

Objective

It is well known that altered functional connectivity is a robust neuroimaging marker of schizophrenia. However, there is inconsistency in the direction of alterations, i.e., increased or decreased connectivity. In this study, we aimed to determine the direction of the connectivity alteration associated with schizophrenia using a multivariate, data-driven approach.

Methods

Resting-state functional magnetic resonance imaging data were acquired from 109 individuals with schizophrenia and 120 controls across two openly available datasets. A whole-brain resting-state functional connectivity (rsFC) matrix was computed for each individual. A modified connectome-based predictive model (CPM) with a support vector machine (SVM) was used to classify patients and controls. We conducted a series of multivariate classification analyses using three different feature sets, increased, decreased, and both increased and decreased rsFC.

Results

For both datasets, combining information from both increased and decreased rsFC substantially improved prediction accuracy (Dataset 1: accuracy = 70.2%, permutation p = 0.001; Dataset 2: accuracy = 64.4%, permutation p = 0.003). When tested across datasets, the prediction model using decreased rsFC performed best. The identified predictive features of decreased rsFC were distributed mostly in the motor network for both datasets.

Conclusion

These findings suggest that bidirectional alterations in rsFC are distributed in schizophrenia patients, with the pattern of decreased rsFC being more similar across different populations.

Beyond the brain-computer interface: Decoding brain activity as a tool to understand neuronal mechanisms subtending cognition and behavior

One of the major challenges in system neurosciences consists in developing techniques for estimating the cognitive information content in brain activity. This has an enormous potential in different domains spanning from clinical applications, cognitive enhancement to a better understanding of the neural bases of cognition. In this context, the inclusion of machine learning techniques to decode different aspects of human cognition and behavior and its use to develop brain-computer interfaces for applications in neuroprosthetics has supported a genuine revolution in the field. However, while these approaches have been shown quite successful for the study of the motor and sensory functions, success is still far from being reached when it comes to covert cognitive functions such as attention, motivation and decision making. While improvement in this field of BCIs is growing fast, a new research focus has emerged from the development of strategies for decoding neural activity. In this review, we aim at exploring how the advanced in decoding of brain activity is becoming a major neuroscience tool moving forward our understanding of brain functions, providing a robust theoretical framework to test predictions on the relationship between brain activity and cognition and behavior.

Application of Empirical Mode Decomposition for Decoding Perception of Faces Using Magnetoencephalography

Neural decoding is useful to explore the timing and source location in which the brain encodes information. Higher classification accuracy means that an analysis is more likely to succeed in extracting useful information from noises. In this paper, we present the application of a nonlinear, nonstationary signal decomposition technique—the empirical mode decomposition (EMD), on MEG data. We discuss the fundamental concepts and importance of nonlinear methods when it comes to analyzing brainwave signals and demonstrate the procedure on a set of open-source MEG facial recognition task dataset. The improved clarity of data allowed further decoding analysis to capture distinguishing features between conditions that were formerly over-looked in the existing literature, while raising interesting questions concerning hemispheric dominance to the encoding process of facial and identity information.

Neuroimage-Based Consciousness Evaluation of Patients with Secondary Doubtful Hydrocephalus Before and After Lumbar Drainage

Hydrocephalus is often treated with a cerebrospinal fluid shunt (CFS) for excessive amounts of cerebrospinal fluid in the brain. However, it is very difficult to distinguish whether the ventricular enlargement is due to hydrocephalus or other causes, such as brain atrophy after brain damage and surgery. The non-trivial evaluation of the consciousness level, along with a continuous drainage test of the lumbar cistern is thus clinically important before the decision for CFS is made. We studied 32 secondary mild hydrocephalus patients with different consciousness levels, who received T1 and diffusion tensor imaging magnetic resonance scans before and after lumbar cerebrospinal fluid drainage. We applied a novel machine-learning method to find the most discriminative features from the multi-modal neuroimages. Then, we built a regression model to regress the JFK Coma Recovery Scale-Revised (CRS-R) scores to quantify the level of consciousness. The experimental results showed that our method not only approximated the CRS-R scores but also tracked the temporal changes in individual patients. The regression model has high potential for the evaluation of consciousness in clinical practice.

Neural Decoding of Multi-Modal Imagery Behavior Focusing on Temporal Complexity

Mental imagery behaviors of various modalities include visual, auditory, and motor behaviors. Their alterations are pathologically involved in various psychiatric disorders. Results of earlier studies suggest that imagery behaviors are correlated with the modulated activities of the respective modality-specific regions and the additional activities of supramodal imagery-related regions. Additionally, despite the availability of complexity analysis in the neuroimaging field, it has not been used for neural decoding approaches. Therefore, we sought to characterize neural oscillation related to multimodal imagery through complexity-based neural decoding. For this study, we modified existing complexity measures to characterize the time evolution of temporal complexity. We took magnetoencephalography (MEG) data of eight healthy subjects as they performed multimodal imagery and non-imagery tasks. The MEG data were decomposed into amplitude and phase of sub-band frequencies by Hilbert-Huang transform. Subsequently, we calculated the complexity values of each reconstructed time series, along with raw data and band power for comparison, and applied these results as inputs to decode visual perception (VP), visual imagery (VI), motor execution (ME), and motor imagery (MI) functions. Consequently, intra-subject decoding with the complexity yielded a characteristic sensitivity map for each task with high decoding accuracy. The map is inverted in the occipital regions between VP and VI and in the central regions between ME and MI. Additionally, replacement of the labels into two classes as imagery and non-imagery also yielded better classification performance and characteristic sensitivity with the complexity. It is particularly interesting that some subjects showed characteristic sensitivities not only in modality-specific regions, but also in supramodal regions. These analyses indicate that two-class and four-class classifications each provided better performance when using complexity than when using raw data or band power as input. When inter-subject decoding was used with the same model, characteristic sensitivity maps were also obtained, although their decoding performance was lower. Results of this study underscore the availability of complexity measures in neural decoding approaches and suggest the possibility of a modality-independent imagery-related mechanism. The use of time evolution of temporal complexity in neural decoding might extend our knowledge of the neural bases of hierarchical functions in the human brain.

Predicting anxiety from wholebrain activity patterns to emotional faces in young adults: a machine learning approach

BACKGROUND

It is becoming increasingly clear that pathophysiological processes underlying psychiatric disorders categories are heterogeneous on many levels, including symptoms, disease course, comorbidity and biological underpinnings. This heterogeneity poses challenges for identifying biological markers associated with dimensions of symptoms and behaviour that could provide targets to guide treatment choice and novel treatment. In response, the research domain criteria (RDoC) (Insel et al., 2010) was developed to advocate a dimensional approach which omits any disease definitions, disorder thresholds, or cut-points for various levels of psychopathology to understanding the pathophysiological processes underlying psychiatry disorders. In the present study we aimed to apply pattern regression analysis to identify brain signatures during dynamic emotional face processing that are predictive of anxiety and depression symptoms in a continuum that ranges from normal to pathological levels, cutting across categorically-defined diagnoses.

METHODS

The sample was composed of one-hundred and fifty-four young adults (mean age=21.6 and s.d.=2.0, 103 females) consisting of eighty-two young adults seeking treatment for psychological distress that cut across categorically-defined diagnoses and 72 matched healthy young adults. Participants performed a dynamic face task involving fearful, angry and happy faces (and geometric shapes) while undergoing functional Magnetic Resonance Imaging (fMRI). Pattern regression analyses consisted of Gaussian Process Regression (GPR) implemented in the Pattern Recognition for Neuroimaging toolbox (PRoNTo). Predicted and actual clinical scores were compared using Pearson's correlation coefficient (r) and normalized mean squared error (MSE) to evaluate the models' performance. Permutation test was applied to estimate significance levels.

RESULTS

GPR identified patterns of neural activity to dynamic emotional face processing predictive of self-report anxiety in the whole sample, which covered a continuum that ranged from healthy to different levels of distress, including subthreshold to fully-syndromal psychiatric diagnoses. Results were significant using two different cross validation strategies (two-fold: r=0.28 (p-value=0.001), MSE=4.47 (p-value=0.001) and five fold r=0.28 (p-value=0.002), MSE=4.62 (p-value=0.003). The contributions of individual regions to the predictive model were very small, demonstrating that predictions were based on the overall pattern rather than on a small combination of regions.

CONCLUSIONS

These findings represent early evidence that neuroimaging techniques may inform clinical assessment of young adults irrespective of diagnoses by allowing accurate and objective quantitative estimation of psychopathology.

Embedding Anatomical or Functional Knowledge in Whole-Brain Multiple Kernel Learning Models

Pattern recognition models have been increasingly applied to neuroimaging data over the last two decades. These applications have ranged from cognitive neuroscience to clinical problems. A common limitation of these approaches is that they do not incorporate previous knowledge about the brain structure and function into the models. Previous knowledge can be embedded into pattern recognition models by imposing a grouping structure based on anatomically or functionally defined brain regions. In this work, we present a novel approach that uses group sparsity to model the whole brain multivariate pattern as a combination of regional patterns. More specifically, we use a sparse version of Multiple Kernel Learning (MKL) to simultaneously learn the contribution of each brain region, previously defined by an atlas, to the decision function. Our application of MKL provides two beneficial features: (1) it can lead to improved overall generalisation performance when the grouping structure imposed by the atlas is consistent with the data; (2) it can identify a subset of relevant brain regions for the predictive model. In order to investigate the effect of the grouping in the proposed MKL approach we compared the results of three different atlases using three different datasets. The method has been implemented in the new version of the open-source Pattern Recognition for Neuroimaging Toolbox (PRoNTo).