scholarly journals Functional Annotation of Human Cognitive States using Deep Graph Convolution

2020 ◽  
Author(s):  
Yu Zhang ◽  
Loïc Tetrel ◽  
Bertrand Thirion ◽  
Pierre Bellec
Keyword(s):  
Human Brain ◽  
Brain Activity ◽  
Brain Regions ◽  
Test Accuracy ◽  
Experimental Conditions ◽  
Cognitive Domains ◽  
Brain Decoding ◽  
Cognitive States ◽  
Human Connectome Project ◽  
Fmri Response

AbstractA key goal in neuroscience is to understand brain mechanisms of cognitive functions. An emerging approach is “brain decoding”, which consists of inferring a set of experimental conditions performed by a participant, using pattern classification of brain activity. Few works so far have attempted to train a brain decoding model that would generalize across many different cognitive tasks drawn from multiple cognitive domains. To tackle this problem, we proposed a domain-general brain decoder that automatically learns the spatiotemporal dynamics of brain response within a short time window using a deep learning approach. By leveraging our prior knowledge on network organization of human brain cognition, we constructed deep graph convolutional neural networks to annotate cognitive states by first mapping the task-evoked fMRI response onto a brain graph, propagating brain dynamics among interconnected brain regions and functional networks, and generating state-specific representations of recorded brain activity. We evaluated the decoding model on a large population of 1200 participants, under 21 different experimental conditions spanning 6 different cognitive domains, acquired from the Human Connectome Project task-fMRI database. Using a 10s window of fMRI response, the 21 cognitive states were identified with a test accuracy of 89% (chance level 4.8%). Performance remained good when using a 6s window (82%). It was even feasible to decode cognitive states from a single fMRI volume (720ms), with the performance following the shape of the hemodynamic response. Moreover, a saliency map analysis demonstrated that the high decoding performance was driven by the response of biologically meaningful brain regions. Together, we provide an automated tool to annotate human brain activity with fine temporal resolution and fine cognitive granularity. Our model shows potential applications as a reference model for domain adaptation, possibly making contributions in a variety of domains, including neurological and psychiatric disorders.

scholarly journals Deep learning models of cognitive processes constrained by human brain connectomes

2021 ◽  
Author(s):  
Yu Zhang ◽  
Nicolas et Farrugia ◽  
Pierre Bellec
Keyword(s):  
Deep Learning ◽  
Cognitive Processes ◽  
Brain Activity ◽  
Neural Substrates ◽  
Brain Regions ◽  
Human Cognition ◽  
Experimental Conditions ◽  
Cognitive States ◽  
Learning Techniques ◽  
Human Connectome Project

Brain decoding aims to infer cognitive states from recordings of brain activity. Current literature has mainly focused on isolated brain regions engaged in specific experimental conditions, but ignored the integrative nature of cognitive processes recruiting distributed brain networks. To tackle this issue, we propose a connectome-based graph neural network to integrate distributed patterns of brain activity in a multiscale manner, ranging from localized brain regions, to a specific brain circuit/network and towards the full brain. We evaluate the decoding model using a large task-fMRI database from the human connectome project. By implementing connectomic constraints and multiscale interactions in deep graph convolutions, the model achieves high accuracy of decoding 21 cognitive states (93%, chancel level: 4.8%) and shows high robustness against adversarial attacks on the graph architecture. Our study bridges human connectomes with deep learning techniques and provides new avenues to study the underlying neural substrates of human cognition at scale.

scholarly journals Spatial Patterns for Discriminative Estimation

2019 ◽  
Author(s):  
Alberto Llera ◽  
Roselyne Chauvin ◽  
Peter Mulders ◽  
Jilly Naaijen ◽  
Maarten Mennes ◽  
...  
Keyword(s):  
Spatial Patterns ◽  
Brain Connectivity ◽  
Covariance Structure ◽  
Brain Regions ◽  
Linear Filters ◽  
Cognitive Changes ◽  
Experimental Conditions ◽  
Cognitive States ◽  
Human Connectome Project ◽  
Perfect Discrimination

AbstractFunctional connectivity between brain regions is modulated by cognitive states or experimental conditions. A multivariate methodology that can capture fMRI connectivity maps in light of different experimental conditions would be of primary importance to learn about the specific roles of the different brain areas involved in the observed connectivity variations. Here we detail, adapt, optimize and evaluate a supervised dimensionality reduction model to fMRI timeseries. We demonstrate the strength of such an approach for fMRI data using data from the Human Connectome Project to show that the model provides close to perfect discrimination between different fMRI tasks at low dimensionality. The straightforward interpretability and relevance of the model results is demonstrated by the obtained linear filters relating to anatomical areas well known to be involved on each considered task, and its robustness by testing discriminatory generalization and spatial reproducibility with respect to the number of subjects and fMRI time-points acquired. We additionally suggest how such approach can provide a complementary view to traditional task fMRI analyses by looking at changes in the covariance structure as a substitute to changes in the mean signal. We conclude that the presented methodology provides a robust tool to investigate brain connectivity alterations across induced cognitive changes and has the potential to be used in pathological or pharmacological cohort studies. A publicly available toolbox is provided to facilitate the end use and further development of this methodology to extract Spatial Patterns for Discriminative Estimation (SP♠DE).

scholarly journals Representational learning of brain responses in executive function and higher-order cognition using deep graph convolutions

2021 ◽  
Author(s):  
Yu Zhang ◽  
Nicolas et Farrugia ◽  
Alain Dagher ◽  
Pierre Bellec
Keyword(s):  
Working Memory ◽  
Neural Activity ◽  
Brain Activity ◽  
High Order ◽  
High Order Cognition ◽  
Brain Decoding ◽  
Cognitive States ◽  
Human Connectome Project ◽  
Convolution Model ◽  
Sensory Processes

Brain decoding aims to infer human cognition from recordings of neural activity using modern neuroimaging techniques. Studies so far often concentrated on a limited number of cognitive states and aimed to classifying patterns of brain activity within a local area. This procedure demonstrated a great success on classifying motor and sensory processes but showed limited power over higher cognitive functions. In this work, we investigate a high-order graph convolution model, named ChebNet, to model the segregation and integration organizational principles in neural dynamics, and to decode brain activity across a large number of cognitive domains. By leveraging our prior knowledge on brain organization using a graph-based model, ChebNet graph convolution learns a new representation from task-evoked neural activity, which demonstrates a highly predictive signature of cognitive states and task performance. Our results reveal that between-network integration significantly boosts the decoding of high-order cognition such as visual working memory tasks, while the segregation of localized brain activity is sufficient to classify motor and sensory processes. Using twin and family data from the Human Connectome Project (n = 1,070), we provide evidence that individual variability in the graph representations of working-memory tasks are under genetic control and strongly associated with participants in-scanner behaviors. These findings uncover the essential role of functional integration in brain decoding, especially when decoding high-order cognition other than sensory and motor functions.

scholarly journals How the human brain introspects about one’s own episodes of cognitive control

2017 ◽  
Author(s):  
David Soto ◽  
Mona Theodoraki ◽  
Pedro M. Paz-Alonso
Keyword(s):  
Cognitive Control ◽  
Human Brain ◽  
Internal Model ◽  
Large Scale ◽  
Brain Activity ◽  
Temporal Correlation ◽  
Control Networks ◽  
Control Functions ◽  
Cognitive States ◽  
Behavioural Performance

AbstractMetacognition refers to our capacity to reflect upon our experiences, thoughts and actions. Metacognition processes are linked to cognitive control functions that allow keeping our actions on-task. But it is unclear how the human brain builds an internal model of one’s cognition and behaviour. We conducted 2 fMRI experiments in which brain activity was recorded ‘online’ as participants engaged in a memory-guided search task and then later ‘offline’ when participants introspected about their prior experience and cognitive states during performance. In Experiment 1 the memory cues were task-relevant while in Experiment 2 they were irrelevant. Across Experiments, the patterns of brain activity, including frontoparietal regions, were similar during on-task and introspection states. However the connectivity profile amongst frontoparietal areas was distint during introspection and modulated by the relevance of the memory cues. Introspection was also characterized by increased temporal correlation between the default-mode network (DMN), frontoparietal and dorsal attention networks and visual cortex. We suggest that memories of one’s own experience during task performance are encoded in large-scale patterns of brain activity and that coupling between DMN and frontoparietal control networks may be crucial to build an internal model of one’s behavioural performance.

scholarly journals Estimation of task-based modulations in functional connectivity with MEG: a comparison of methods

2018 ◽  
Author(s):  
Juan L.P. Soto ◽  
Karim Jerbi
Keyword(s):  
Brain Activity ◽  
Correlation Coefficients ◽  
Brain Regions ◽  
The Other ◽  
Functional Magnetic Resonance ◽  
Visuomotor Coordination ◽  
Experimental Conditions ◽  
Magnetic Resonance Data ◽  
Resonance Data ◽  
Mathematical Techniques

AbstractFor the assessment of functional interactions between distinct brain regions there is a great variety of mathematical techniques, with well-known properties, relative merits and shortcomings; however, the methods that deal specifically with task-based fluctuations in interareal coupling are scarce, and their relative performance is unclear. In the present article, we compare two approaches used in the estimation of correlation changes between the envelope amplitudes of narrowband brain activity obtained from magnetoencephalography (MEG) recordings. One approach is an implementation of semipartial canonical correlation analysis (SP-CCA), which is formally equivalent to the psychophysiological interactions technique successfully applied to functional magnetic resonance data. The other approach, which has been used in recent electrophysiology studies, consists of simply computing linear correlation coefficients of signals from two experimental conditions and taking their differences. We compared the two approaches with simulations and with multi-subject MEG signals acquired during a visuomotor coordination study. The analyses with simulated activity showed that computing differences in correlation coefficients (DCC) provided better discrimination between true coupling changes and spurious effects; on the other hand, SP-CCA resulted in significant effects around the reference location which were not found with DCC, and which may be due to field spread. Based on our findings, we recommend the use of DCC for the detection of task-based changes in connectivity, as it provided better performance than SP-CCA.

scholarly journals Estimation and Validation of Individualized Dynamic Brain Models with Resting State fMRI

2019 ◽  
Author(s):  
Matthew F. Singh ◽  
Todd S. Braver ◽  
Michael W. Cole ◽  
ShiNung Ching
Keyword(s):  
Human Brain ◽  
Resting State ◽  
Nonlinear Dynamical Systems ◽  
Brain Activity ◽  
Network Models ◽  
Resting State Fmri ◽  
Brain Regions ◽  
Data Driven ◽  
Imaging Data ◽  
Individual Level

AbstractA key challenge for neuroscience is to develop generative, causal models of the human nervous system in an individualized, data-driven manner. Previous initiatives have either constructed biologically-plausible models that are not constrained by individual-level human brain activity or used data-driven statistical characterizations of individuals that are not mechanistic. We aim to bridge this gap through the development of a new modeling approach termed Mesoscale Individualized Neurodynamic (MINDy) modeling, wherein we fit nonlinear dynamical systems models directly to human brain imaging data. The MINDy framework is able to produce these data-driven network models for hundreds to thousands of interacting brain regions in just 1-3 minutes per subject. We demonstrate that the models are valid, reliable, and robust. We show that MINDy models are predictive of individualized patterns of resting-state brain dynamical activity. Furthermore, MINDy is better able to uncover the mechanisms underlying individual differences in resting state activity than functional connectivity methods.

scholarly journals A spatiotemporal complexity architecture of human brain activity

2021 ◽  
Author(s):  
Stephan Krohn ◽  
Nina von Schwanenflug ◽  
Leonhard Waschke ◽  
Amy Romanello ◽  
Martin Gell ◽  
...  
Keyword(s):  
Human Brain ◽  
Neural Activity ◽  
Large Scale ◽  
Temporal Dynamics ◽  
Brain Activity ◽  
Brain Regions ◽  
Brain Organization ◽  
Functional Connections ◽  
Signal Complexity ◽  
The Brain

The human brain operates in large-scale functional networks, collectively subsumed as the functional connectome1-13. Recent work has begun to unravel the organization of the connectome, including the temporal dynamics of brain states14-20, the trade-off between segregation and integration9,15,21-23, and a functional hierarchy from lower-order unimodal to higher-order transmodal processing systems24-27. However, it remains unknown how these network properties are embedded in the brain and if they emerge from a common neural foundation. Here we apply time-resolved estimation of brain signal complexity to uncover a unifying principle of brain organization, linking the connectome to neural variability6,28-31. Using functional magnetic resonance imaging (fMRI), we show that neural activity is marked by spontaneous "complexity drops" that reflect episodes of increased pattern regularity in the brain, and that functional connections among brain regions are an expression of their simultaneous engagement in such episodes. Moreover, these complexity drops ubiquitously propagate along cortical hierarchies, suggesting that the brain intrinsically reiterates its own functional architecture. Globally, neural activity clusters into temporal complexity states that dynamically shape the coupling strength and configuration of the connectome, implementing a continuous re-negotiation between cost-efficient segregation and communication-enhancing integration9,15,21,23. Furthermore, complexity states resolve the recently discovered association between anatomical and functional network hierarchies comprehensively25-27,32. Finally, brain signal complexity is highly sensitive to age and reflects inter-individual differences in cognition and motor function. In sum, we identify a spatiotemporal complexity architecture of neural activity — a functional "complexome" that gives rise to the network organization of the human brain.

scholarly journals Touching to Feel: Brain Activity During In-Store Consumer Experience

2021 ◽  
Vol 12 ◽  
Author(s):  
Michela Balconi ◽  
Irene Venturella ◽  
Roberta Sebastiani ◽  
Laura Angioletti
Keyword(s):  
Brain Activity ◽  
Power Spectral Analysis ◽  
Brain Regions ◽  
Consumer Experience ◽  
Beta Band ◽  
Experimental Conditions ◽  
Cortical Oscillations ◽  
Brain Responses ◽  
Power Spectral ◽  
High Level

To gain a deeper understanding of consumers' brain responses during a real-time in-store exploration could help retailers to get much closer to costumers' experience. To our knowledge, this is the first time the specific role of touch has been investigated by means of a neuroscientific approach during consumer in-store experience within the field of sensory marketing. This study explores the presence of distinct cortical brain oscillations in consumers' brain while navigating a store that provides a high level of sensory arousal and being allowed or not to touch products. A 16-channel wireless electroencephalogram (EEG) was applied to 23 healthy participants (mean age = 24.57 years, SD = 3.54), with interest in cosmetics but naive about the store explored. Subjects were assigned to two experimental conditions based on the chance of touching or not touching the products. Cortical oscillations were explored by means of power spectral analysis of the following frequency bands: delta, theta, alpha, and beta. Results highlighted the presence of delta, theta, and beta bands within the frontal brain regions during both sensory conditions. The absence of touch was experienced as a lack of perception that needs cognitive control, as reflected by Delta and Theta band left activation, whereas a right increase of Beta band for touch condition was associated with sustained awareness on the sensory experience. Overall, EEG cortical oscillations' functional meaning could help highlight the neurophysiological implicit responses to tactile conditions and the importance of touch integration in consumers' experience.

scholarly journals The heritability of multi-modal connectivity in human brain activity

eLife ◽  
2017 ◽  
Vol 6 ◽  
Author(s):  
Giles L Colclough ◽  
Stephen M Smith ◽  
Thomas E Nichols ◽  
Anderson M Winkler ◽  
Stamatios N Sotiropoulos ◽  
...  
Keyword(s):  
Functional Connectivity ◽  
Human Brain ◽  
Brain Activity ◽  
Dominant Role ◽  
Beta Band ◽  
Common Environment ◽  
Human Connectome Project ◽  
Oscillatory Power ◽  
The Common ◽  
Cortical Regions

Patterns of intrinsic human brain activity exhibit a profile of functional connectivity that is associated with behaviour and cognitive performance, and deteriorates with disease. This paper investigates the relative importance of genetic factors and the common environment between twins in determining this functional connectivity profile. Using functional magnetic resonance imaging (fMRI) on 820 subjects from the Human Connectome Project, and magnetoencephalographic (MEG) recordings from a subset, the heritability of connectivity among 39 cortical regions was estimated. On average over all connections, genes account for about 15% of the observed variance in fMRI connectivity (and about 10% in alpha-band and 20% in beta-band oscillatory power synchronisation), which substantially exceeds the contribution from the environment shared between twins. Therefore, insofar as twins share a common upbringing, it appears that genes, rather than the developmental environment, have the dominant role in determining the coupling of neuronal activity.

scholarly journals Bidirectional Association Between Sleep and Brain Atrophy in Aging

2021 ◽  
Vol 13 ◽  
Author(s):  
Viktória Kokošová ◽  
Pavel Filip ◽  
David Kec ◽  
Marek Baláž
Keyword(s):  
Human Brain ◽  
Brain Atrophy ◽  
Brain Aging ◽  
Brain Activity ◽  
Brain Regions ◽  
Electrical Brain Activity ◽  
Age Related ◽  
Bidirectional Association ◽  
Quality Sleep ◽  
Brain Functional Connectivity

Human brain aging is characterized by the gradual deterioration of its function and structure, affected by the interplay of a multitude of causal factors. The sleep, a periodically repeating state of reversible unconsciousness characterized by distinct electrical brain activity, is crucial for maintaining brain homeostasis. Indeed, insufficient sleep was associated with accelerated brain atrophy and impaired brain functional connectivity. Concurrently, alteration of sleep-related transient electrical events in senescence was correlated with structural and functional deterioration of brain regions responsible for their generation, implying the interconnectedness of sleep and brain structure. This review discusses currently available data on the link between human brain aging and sleep derived from various neuroimaging and neurophysiological methods. We advocate the notion of a mutual relationship between the sleep structure and age-related alterations of functional and structural brain integrity, pointing out the position of high-quality sleep as a potent preventive factor of early brain aging and neurodegeneration. However, further studies are needed to reveal the causality of the relationship between sleep and brain aging.

Sign in / Sign up

Export Citation Format

Share Document