Predictive models avoid excessive reductionism in cognitive neuroimaging

Psychiatric neuroimaging designs for individualised, cohort, and population studies

Psychiatric neuroimaging faces challenges to rigour and reproducibility that prompt reconsideration of the relative strengths and limitations of study designs. Owing to high resource demands and varying inferential goals, current designs differentially emphasise sample size, measurement breadth, and longitudinal assessments. In this overview and perspective, we provide a guide to the current landscape of psychiatric neuroimaging study designs with respect to this balance of scientific goals and resource constraints. Through a heuristic data cube contrasting key design features, we discuss a resulting trade-off among small sample, precision longitudinal studies (e.g., individualised studies and cohorts) and large sample, minimally longitudinal, population studies. Precision studies support tests of within-person mechanisms, via intervention and tracking of longitudinal course. Population studies support tests of generalisation across multifaceted individual differences. A proposed reciprocal validation model (RVM) aims to recursively leverage these complementary designs in sequence to accumulate evidence, optimise relative strengths, and build towards improved long-term clinical utility.

Dissonant music engages early visual processing

The neuroscientific examination of music processing in audio-visual contexts offers a valuable framework to assess how auditory information influences the emotional encoding of visual information. Using fMRI during naturalistic film viewing, we investigated the neural mechanisms underlying the effect of music on valence inferences during mental state attribution. Thirty-eight participants watched the same short-film accompanied by systematically controlled consonant or dissonant music. Subjects were instructed to think about the main character's intentions. The results revealed that increasing levels of dissonance led to more negatively valenced inferences, displaying the profound emotional impact of musical dissonance. Crucially, at the neuroscientific level and despite music being the sole manipulation, dissonance evoked the response of the primary visual cortex (V1). Functional/effective connectivity analysis showed a stronger coupling between the auditory ventral stream (AVS) and V1 in response to tonal dissonance and demonstrated the modulation of early visual processing via top-down feedback inputs from the AVS to V1. These V1 signal changes indicate the influence of high-level contextual representations associated with tonal dissonance on early visual cortices, serving to facilitate the emotional interpretation of visual information. Our results highlight the significance of employing systematically controlled music, which can isolate emotional valence from the arousal dimension, to elucidate the brain's sound-to-meaning interface and its distributive crossmodal effects on early visual encoding during naturalistic film viewing.

Should one go for individual- or group-level brain parcellations? A deep-phenotyping benchmark

The analysis and understanding of brain characteristics often require considering region-level information rather than voxel-sampled data. Subject-specific parcellations have been put forward in recent years, as they can adapt to individual brain organization and thus offer more accurate individual summaries than standard atlases. However, the price to pay for adaptability is the lack of group-level consistency of the data representation. Here, we investigate whether the good representations brought by individualized models are merely an effect of circular analysis, in which individual brain features are better represented by subject-specific summaries, or whether this carries over to new individuals, i.e., whether one can actually adapt an existing parcellation to new individuals and still obtain good summaries in these individuals. For this, we adapt a dictionary-learning method to produce brain parcellations. We use it on a deep-phenotyping dataset to assess quantitatively the patterns of activity obtained under naturalistic and controlled-task-based settings. We show that the benefits of individual parcellations are substantial, but that they vary a lot across brain systems.

Multilayer meta-matching: translating phenotypic prediction models from multiple datasets to small data

Resting-state functional connectivity (RSFC) is widely used to predict phenotypic traits in individuals. Large sample sizes can significantly improve prediction accuracies. However, for studies of certain clinical populations or focused neuroscience inquiries, small-scale datasets often remain a necessity. We have previously proposed a "meta-matching" approach to translate prediction models from large datasets to predict new phenotypes in small datasets. We demonstrated large improvement of meta-matching over classical kernel ridge regression (KRR) when translating models from a single source dataset (UK Biobank) to the Human Connectome Project Young Adults (HCP-YA) dataset. In the current study, we propose two meta-matching variants ("meta-matching with dataset stacking" and "multilayer meta-matching") to translate models from multiple source datasets across disparate sample sizes to predict new phenotypes in small target datasets. We evaluate both approaches by translating models trained from five source datasets (with sample sizes ranging from 862 participants to 36,834 participants) to predict phenotypes in the HCP-YA and HCP-Aging datasets. We find that multilayer meta-matching modestly outperforms meta-matching with dataset stacking. Both meta-matching variants perform better than the original "meta-matching with stacking" approach trained only on the UK Biobank. All meta-matching variants outperform classical KRR and transfer learning by a large margin. In fact, KRR is better than classical transfer learning when less than 50 participants are available for finetuning, suggesting the difficulty of classical transfer learning in the very small sample regime. The multilayer meta-matching model is publicly available at GITHUB_LINK.

Task fMRI paradigms may capture more behaviorally relevant information than resting-state functional connectivity

Characterizing the optimal fMRI paradigms for detecting behaviorally relevant functional connectivity (FC) patterns is a critical step to furthering our knowledge of the neural basis of behavior. Previous studies suggested that FC patterns derived from task fMRI paradigms, which we refer to as task-based FC, are better correlated with individual differences in behavior than resting-state FC, but the consistency and generalizability of this advantage across task conditions was not fully explored. Using data from resting-state fMRI and three fMRI tasks from the Adolescent Brain Cognitive Development Study ® (ABCD), we tested whether the observed improvement in behavioral prediction power of task-based FC can be attributed to changes in brain activity induced by the task design. We decomposed the task fMRI time course of each task into the task model fit (the fitted time course of the task condition regressors from the single-subject general linear model) and the task model residuals, calculated their respective FC, and compared the behavioral prediction performance of these FC estimates to resting-state FC and the original task-based FC. The FC of the task model fit was better than the FC of the task model residual and resting-state FC at predicting a measure of general cognitive ability or two measures of performance on the fMRI tasks. The superior behavioral prediction performance of the FC of the task model fit was content-specific insofar as it was only observed for fMRI tasks that probed similar cognitive constructs to the predicted behavior of interest. To our surprise, the task model parameters, the beta estimates of the task condition regressors, were equally if not more predictive of behavioral differences than all FC measures. These results showed that the observed improvement of behavioral prediction afforded by task-based FC was largely driven by the FC patterns associated with the task design. Together with previous studies, our findings highlighted the importance of task design in eliciting behaviorally meaningful brain activation and FC patterns.

Canonical template tracking: Measuring the activation state of specific neural representations

Multivariate analyses of neural data have become increasingly influential in cognitive neuroscience since they allow to address questions about the representational signatures of neurocognitive phenomena. Here, we describe Canonical Template Tracking: a multivariate approach that employs independent localizer tasks to assess the activation state of specific representations during the execution of cognitive paradigms. We illustrate the benefits of this methodology in characterizing the particular content and format of task-induced representations, comparing it with standard (cross-)decoding and representational similarity analyses. Then, we discuss relevant design decisions for experiments using this analysis approach, focusing on the nature of the localizer tasks from which the canonical templates are derived. We further provide a step-by-step tutorial of this method, stressing the relevant analysis choices for functional magnetic resonance imaging and magneto/electroencephalography data. Importantly, we point out the potential pitfalls linked to canonical template tracking implementation and interpretation of the results, together with recommendations to mitigate them. To conclude, we provide some examples from previous literature that highlight the potential of this analysis to address relevant theoretical questions in cognitive neuroscience.

Socioeconomic resources are associated with distributed alterations of the brain's intrinsic functional architecture in youth

Little is known about how exposure to limited socioeconomic resources (SER) in childhood gets "under the skin" to shape brain development, especially using rigorous whole-brain multivariate methods in large, adequately powered samples. The present study examined resting state functional connectivity patterns from 5821 youth in the Adolescent Brain Cognitive Development (ABCD) study, employing multivariate methods across three levels: whole-brain, network-wise, and connection-wise. Across all three levels, SER was associated with widespread alterations across the connectome. However, critically, we found that parental education was the primary driver of neural associations with SER. These parental education associations with the developing connectome exhibited notable concentrations in somatosensory and subcortical regions, and they were partially accounted for by home enrichment activities, child's cognitive abilities, and child's grades, indicating interwoven links between parental education, child stimulation, and child cognitive performance. These results add a new data-driven, multivariate perspective on links between household SER and the child's developing functional connectome.

On the encoding of natural music in computational models and human brains

This article discusses recent developments and advances in the neuroscience of music to understand the nature of musical emotion. In particular, it highlights how system identification techniques and computational models of music have advanced our understanding of how the human brain processes the textures and structures of music and how the processed information evokes emotions. Musical models relate physical properties of stimuli to internal representations called features, and predictive models relate features to neural or behavioral responses and test their predictions against independent unseen data. The new frameworks do not require orthogonalized stimuli in controlled experiments to establish reproducible knowledge, which has opened up a new wave of naturalistic neuroscience. The current review focuses on how this trend has transformed the domain of the neuroscience of music.

Meta-matching as a simple framework to translate phenotypic predictive models from big to small data

We propose a simple framework-meta-matching-to translate predictive models from large-scale datasets to new unseen non-brain-imaging phenotypes in small-scale studies. The key consideration is that a unique phenotype from a boutique study likely correlates with (but is not the same as) related phenotypes in some large-scale dataset. Meta-matching exploits these correlations to boost prediction in the boutique study. We apply meta-matching to predict non-brain-imaging phenotypes from resting-state functional connectivity. Using the UK Biobank (N = 36,848) and Human Connectome Project (HCP) (N = 1,019) datasets, we demonstrate that meta-matching can greatly boost the prediction of new phenotypes in small independent datasets in many scenarios. For example, translating a UK Biobank model to 100 HCP participants yields an eight-fold improvement in variance explained with an average absolute gain of 4.0% (minimum = -0.2%, maximum = 16.0%) across 35 phenotypes. With a growing number of large-scale datasets collecting increasingly diverse phenotypes, our results represent a lower bound on the potential of meta-matching.

Comprehensive decoding mental processes from Web repositories of functional brain images

Associating brain systems with mental processes requires statistical analysis of brain activity across many cognitive processes. These analyses typically face a difficult compromise between scope-from domain-specific to system-level analysis-and accuracy. Using all the functional Magnetic Resonance Imaging (fMRI) statistical maps of the largest data repository available, we trained machine-learning models that decode the cognitive concepts probed in unseen studies. For this, we leveraged two comprehensive resources: NeuroVault-an open repository of fMRI statistical maps with unconstrained annotations-and Cognitive Atlas-an ontology of cognition. We labeled NeuroVault images with Cognitive Atlas concepts occurring in their associated metadata. We trained neural networks to predict these cognitive labels on tens of thousands of brain images. Overcoming the heterogeneity, imbalance and noise in the training data, we successfully decoded more than 50 classes of mental processes on a large test set. This success demonstrates that image-based meta-analyses can be undertaken at scale and with minimal manual data curation. It enables broad reverse inferences, that is, concluding on mental processes given the observed brain activity.

How to remove or control confounds in predictive models, with applications to brain biomarkers

BACKGROUND

With increasing data sizes and more easily available computational methods, neurosciences rely more and more on predictive modeling with machine learning, e.g., to extract disease biomarkers. Yet, a successful prediction may capture a confounding effect correlated with the outcome instead of brain features specific to the outcome of interest. For instance, because patients tend to move more in the scanner than controls, imaging biomarkers of a disease condition may mostly reflect head motion, leading to inefficient use of resources and wrong interpretation of the biomarkers.

RESULTS

Here we study how to adapt statistical methods that control for confounds to predictive modeling settings. We review how to train predictors that are not driven by such spurious effects. We also show how to measure the unbiased predictive accuracy of these biomarkers, based on a confounded dataset. For this purpose, cross-validation must be modified to account for the nuisance effect. To guide understanding and practical recommendations, we apply various strategies to assess predictive models in the presence of confounds on simulated data and population brain imaging settings. Theoretical and empirical studies show that deconfounding should not be applied to the train and test data jointly: modeling the effect of confounds, on the training data only, should instead be decoupled from removing confounds.

CONCLUSIONS

Cross-validation that isolates nuisance effects gives an additional piece of information: confound-free prediction accuracy.

Towards a model of language neurobiology in early development

Understanding language neurobiology in early childhood is essential for characterizing the developmental structural and functional changes that lead to the mature adult language network. In the last two decades, the field of language neurodevelopment has received increasing attention, particularly given the rapid advances in the implementation of neuroimaging techniques and analytic approaches that allow detailed investigations into the developing brain across a variety of cognitive domains. These methodological and analytical advances hold the promise of developing early markers of language outcomes that allow diagnosis and clinical interventions at the earliest stages of development. Here, we argue that findings in language neurobiology need to be integrated within an approach that captures the dynamic nature and inherent variability that characterizes the developing brain and the interplay between behavior and (structural and functional) neural patterns. Accordingly, we describe a framework for understanding language neurobiology in early development, which minimally requires an explicit characterization of the following core domains: i) computations underlying language learning mechanisms, ii) developmental patterns of change across neural and behavioral measures, iii) environmental variables that reinforce language learning (e.g., the social context), and iv) brain maturational constraints for optimal neural plasticity, which determine the infant's sensitivity to learning from the environment. We discuss each of these domains in the context of recent behavioral and neuroimaging findings and consider the need for quantitatively modeling two main sources of variation: individual differences or trait-like patterns of variation and within-subject differences or state-like patterns of variation. The goal is to enable models that allow prediction of language outcomes from neural measures that take into account these two types of variation. Finally, we examine how future methodological approaches would benefit from the inclusion of more ecologically valid paradigms that complement and allow generalization of traditional controlled laboratory methods.

The "Narratives" fMRI dataset for evaluating models of naturalistic language comprehension

The "Narratives" collection aggregates a variety of functional MRI datasets collected while human subjects listened to naturalistic spoken stories. The current release includes 345 subjects, 891 functional scans, and 27 diverse stories of varying duration totaling ~4.6 hours of unique stimuli (~43,000 words). This data collection is well-suited for naturalistic neuroimaging analysis, and is intended to serve as a benchmark for models of language and narrative comprehension. We provide standardized MRI data accompanied by rich metadata, preprocessed versions of the data ready for immediate use, and the spoken story stimuli with time-stamped phoneme- and word-level transcripts. All code and data are publicly available with full provenance in keeping with current best practices in transparent and reproducible neuroimaging.

Biomarker-Informed Machine Learning Model of Cognitive Fatigue from a Heart Rate Response Perspective

Cognitive fatigue is a psychological state characterised by feelings of tiredness and impaired cognitive functioning arising from high cognitive demands. This paper examines the recent research progress on the assessment of cognitive fatigue and provides informed recommendations for future research. Traditionally, cognitive fatigue is introspectively assessed through self-report or objectively inferred from a decline in behavioural performance. However, more recently, researchers have attempted to explore the biological underpinnings of cognitive fatigue to understand and measure this phenomenon. In particular, there is evidence indicating that the imbalance between sympathetic and parasympathetic nervous activity appears to be a physiological correlate of cognitive fatigue. This imbalance has been indexed through various heart rate variability indices that have also been proposed as putative biomarkers of cognitive fatigue. Moreover, in contrast to traditional inferential methods, there is also a growing research interest in using data-driven approaches to assessing cognitive fatigue. The ubiquity of wearables with the capability to collect large amounts of physiological data appears to be a major facilitator in the growth of data-driven research in this area. Preliminary findings indicate that such large datasets can be used to accurately predict cognitive fatigue through various machine learning approaches. Overall, the potential of combining domain-specific knowledge gained from biomarker research with machine learning approaches should be further explored to build more robust predictive models of cognitive fatigue.

Extracting representations of cognition across neuroimaging studies improves brain decoding

Cognitive brain imaging is accumulating datasets about the neural substrate of many different mental processes. Yet, most studies are based on few subjects and have low statistical power. Analyzing data across studies could bring more statistical power; yet the current brain-imaging analytic framework cannot be used at scale as it requires casting all cognitive tasks in a unified theoretical framework. We introduce a new methodology to analyze brain responses across tasks without a joint model of the psychological processes. The method boosts statistical power in small studies with specific cognitive focus by analyzing them jointly with large studies that probe less focal mental processes. Our approach improves decoding performance for 80% of 35 widely-different functional-imaging studies. It finds commonalities across tasks in a data-driven way, via common brain representations that predict mental processes. These are brain networks tuned to psychological manipulations. They outline interpretable and plausible brain structures. The extracted networks have been made available; they can be readily reused in new neuro-imaging studies. We provide a multi-study decoding tool to adapt to new data.

Cortical response to naturalistic stimuli is largely predictable with deep neural networks

Naturalistic stimuli, such as movies, activate a substantial portion of the human brain, invoking a response shared across individuals. Encoding models that predict neural responses to arbitrary stimuli can be very useful for studying brain function. However, existing models focus on limited aspects of naturalistic stimuli, ignoring the dynamic interactions of modalities in this inherently context-rich paradigm. Using movie-watching data from the Human Connectome Project, we build group-level models of neural activity that incorporate several inductive biases about neural information processing, including hierarchical processing, temporal assimilation, and auditory-visual interactions. We demonstrate how incorporating these biases leads to remarkable prediction performance across large areas of the cortex, beyond the sensory-specific cortices into multisensory sites and frontal cortex. Furthermore, we illustrate that encoding models learn high-level concepts that generalize to task-bound paradigms. Together, our findings underscore the potential of encoding models as powerful tools for studying brain function in ecologically valid conditions.

Where You Lead, I Will Follow: Exploring Sibling Similarity in Brain and Behavior During Risky Decision Making

This exploratory study examined whether social learning increases similarity in adolescent siblings' behavior and neural patterns during risky decision making. Participants included 86 adolescents (43 sibling dyads; younger siblings: M_age  = 12.2 years; 22 females; older siblings: M_age  = 14.6 years; 20 females) who completed questionnaires, and a decision-making task during an fMRI scan. Younger siblings became more similar to their older siblings' risky decision making after observing their older sibling take risks). Younger siblings who reported greater modeling of their older sibling, and less differentiation from them, showed increased neural similarity to their older siblings in the ventromedial prefrontal cortex, and the right anterior insula and ventral striatum, respectively. These findings highlight siblings as salient social agents in how adolescents process risky decision making.

Predicting Student Performance Using Machine Learning in fNIRS Data

Increasing student involvement in classes has always been a challenge for teachers and school managers. In online learning, some interactivity mechanisms like quizzes are increasingly used to engage students during classes and tasks. However, there is a high demand for tools that evaluate the efficiency of these mechanisms. In order to distinguish between high and low levels of engagement in tasks, it is possible to monitor brain activity through functional near-infrared spectroscopy (fNIRS). The main advantages of this technique are portability, low cost, and a comfortable way for students to concentrate and perform their tasks. This setup provides more natural conditions for the experiments if compared to the other acquisition tools. In this study, we investigated levels of task involvement through the identification of correct and wrong answers of typical quizzes used in virtual environments. We collected data from the prefrontal cortex region (PFC) of 18 students while watching a video lecture. This data was modeled with supervised learning algorithms. We used random forests and penalized logistic regression to classify correct answers as a function of oxyhemoglobin and deoxyhemoglobin concentration. These models identify which regions best predict student performance. The random forest and penalized logistic regression (GLMNET with LASSO) obtained, respectively, 0.67 and 0.65 area of the ROC curve. Both models indicate that channels F4-F6 and AF3-AFz are the most relevant for the prediction. The statistical significance of these models was confirmed through cross-validation (leave-one-subject-out) and a permutation test. This methodology can be useful to better understand the teaching and learning processes in a video lecture and also provide improvements in the methodologies used in order to better adapt the presentation content.

Multivariate spatial feature selection in fMRI

Multivariate neuroimaging analyses constitute a powerful class of techniques to identify psychological representations. However, not all psychological processes are represented at the same spatial scale throughout the brain. This heterogeneity is apparent when comparing hierarchically organized local representations of perceptual processes to flexible transmodal representations of more abstract cognitive processes such as social and affective operations. An open question is how the spatial scale of analytic approaches interacts with the spatial scale of the representations under investigation. In this article, we describe how multivariate analyses can be viewed as existing on a spatial spectrum, anchored by searchlights used to identify locally distributed patterns of information on one end, whole brain approach used to identify diffuse neural representations at the other and region-based approaches in between. We describe how these distinctions are an important and often overlooked analytic consideration and provide heuristics to compare these different techniques to choose based on the analyst’s inferential goals.

Brain topography beyond parcellations: Local gradients of functional maps

Functional neuroimaging provides the unique opportunity to characterize brain regions based on their response to tasks or ongoing activity. As such, it holds the premise to capture brain spatial organization. Yet, the conceptual framework to describe this organization has remained elusive: on the one hand, parcellations build implicitly on a piecewise constant organization, i.e. flat regions separated by sharp boundaries; on the other hand, the recently popularized concept of functional gradient hints instead at a smooth structure. Noting that both views converge to a topographic scheme that pieces together local variations of functional features, we perform a quantitative assessment of local gradient-based models. Using as a driving case the prediction of functional Magnetic Resonance Imaging (fMRI) data -concretely, the prediction of task-fMRI from rest-fMRI maps across subjects- we develop a parcel-wise linear regression model based on a dictionary of reference topographies. Our method uses multiple random parcellations -as opposed to a single fixed parcellation- and aggregates estimates across these parcellations to predict functional features in left-out subjects. Our experiments demonstrate the existence of an optimal cardinality of the parcellation to capture local gradients of functional maps.

Keep it real: rethinking the primacy of experimental control in cognitive neuroscience

Naturalistic experimental paradigms in neuroimaging arose from a pressure to test the validity of models we derive from highly-controlled experiments in real-world contexts. In many cases, however, such efforts led to the realization that models developed under particular experimental manipulations failed to capture much variance outside the context of that manipulation. The critique of non-naturalistic experiments is not a recent development; it echoes a persistent and subversive thread in the history of modern psychology. The brain has evolved to guide behavior in a multidimensional world with many interacting variables. The assumption that artificially decoupling and manipulating these variables will lead to a satisfactory understanding of the brain may be untenable. We develop an argument for the primacy of naturalistic paradigms, and point to recent developments in machine learning as an example of the transformative power of relinquishing control. Naturalistic paradigms should not be deployed as an afterthought if we hope to build models of brain and behavior that extend beyond the laboratory into the real world.

Behavioral and brain signatures of substance use vulnerability in childhood

The prevalence of risky behavior such as substance use increases during adolescence; however, the neurobiological precursors to adolescent substance use remain unclear. Predictive modeling may complement previous work observing associations with known risk factors or substance use outcomes by developing generalizable models that predict early susceptibility. The aims of the current study were to identify and characterize behavioral and brain models of vulnerability to future substance use. Principal components analysis (PCA) of behavioral risk factors were used together with connectome-based predictive modeling (CPM) during rest and task-based functional imaging to generate predictive models in a large cohort of nine- and ten-year-olds enrolled in the Adolescent Brain & Cognitive Development (ABCD) study (NDA release 2.0.1). Dimensionality reduction (n = 9,437) of behavioral measures associated with substance use identified two latent dimensions that explained the largest amount of variance: risk-seeking (PC1; e.g., curiosity to try substances) and familial factors (PC2; e.g., family history of substance use disorder). Using cross-validated regularized regression in a subset of data (Year 1 Fast Track data; n>1,500), functional connectivity during rest and task conditions (resting-state; monetary incentive delay task; stop signal task; emotional n-back task) significantly predicted individual differences in risk-seeking (PC1) in held-out participants (partial correlations between predicted and observed scores controlling for motion and number of frames [r_p]: 0.07-0.21). By contrast, functional connectivity was a weak predictor of familial risk factors associated with substance use (PC2) (r_p: 0.03-0.06). These results demonstrate a novel approach to understanding substance use vulnerability, which—together with mechanistic perspectives—may inform strategies aimed at early identification of risk for addiction.

A naturalistic neuroimaging database for understanding the brain using ecological stimuli

Neuroimaging has advanced our understanding of human psychology using reductionist stimuli that often do not resemble information the brain naturally encounters. It has improved our understanding of the network organization of the brain mostly through analyses of 'resting-state' data for which the functions of networks cannot be verifiably labelled. We make a 'Naturalistic Neuroimaging Database' (NNDb v1.0) publically available to allow for a more complete understanding of the brain under more ecological conditions during which networks can be labelled. Eighty-six participants underwent behavioural testing and watched one of 10 full-length movies while functional magnetic resonance imaging was acquired. Resulting timeseries data are shown to be of high quality, with good signal-to-noise ratio, few outliers and low movement. Data-driven functional analyses provide further evidence of data quality. They also demonstrate accurate timeseries/movie alignment and how movie annotations might be used to label networks. The NNDb can be used to answer questions previously unaddressed with standard neuroimaging approaches, progressing our knowledge of how the brain works in the real world.

Predictive modeling of neurobehavioral state and trait variation across development

A key goal of human neurodevelopmental research is to map neural and behavioral trajectories across both health and disease. A growing number of developmental consortia have begun to address this gap by providing open access to cross-sectional and longitudinal 'big data' repositories. However, it remains challenging to develop models that enable prediction of both within-subject and between-subject neurodevelopmental variation. Here, we present a conceptual and analytical perspective of two essential ingredients for mapping neurodevelopmental trajectories: state and trait components of variance. We focus on mapping variation across a range of neural and behavioral measurements and consider concurrent alterations of state and trait variation across development. We present a quantitative framework for combining both state- and trait-specific sources of neurobehavioral variation across development. Specifically, we argue that non-linear mixed growth models that leverage state and trait components of variance and consider environmental factors are necessary to comprehensively map brain-behavior relationships. We discuss this framework in the context of mapping language neurodevelopmental changes in early childhood, with an emphasis on measures of functional connectivity and their reliability for establishing robust neurobehavioral relationships. The ultimate goal is to statistically unravel developmental trajectories of neurobehavioral relationships that involve a combination of individual differences and age-related changes.

Toward a "treadmill test" for cognition: Improved prediction of general cognitive ability from the task activated brain

General cognitive ability (GCA) refers to a trait-like ability that contributes to performance across diverse cognitive tasks. Identifying brain-based markers of GCA has been a longstanding goal of cognitive and clinical neuroscience. Recently, predictive modeling methods have emerged that build whole-brain, distributed neural signatures for phenotypes of interest. In this study, we employ a predictive modeling approach to predict GCA based on fMRI task activation patterns during the N-back working memory task as well as six other tasks in the Human Connectome Project dataset (n = 967), encompassing 15 task contrasts in total. We found tasks are a highly effective basis for prediction of GCA: The 2-back versus 0-back contrast achieved a 0.50 correlation with GCA scores in 10-fold cross-validation, and 13 out of 15 task contrasts afforded statistically significant prediction of GCA. Additionally, we found that task contrasts that produce greater frontoparietal activation and default mode network deactivation-a brain activation pattern associated with executive processing and higher cognitive demand-are more effective in the prediction of GCA. These results suggest a picture analogous to treadmill testing for cardiac function: Placing the brain in a more cognitively demanding task state significantly improves brain-based prediction of GCA.

Toward a Revised Nosology for Attention-Deficit/Hyperactivity Disorder Heterogeneity

Attention-deficit/hyperactivity disorder (ADHD) is among the many syndromes in the psychiatric nosology for which etiological signal and clinical prediction are weak. Reducing phenotypic and mechanistic heterogeneity should be useful to arrive at stronger etiological and clinical prediction signals. We discuss key conceptual and methodological issues, highlighting the role of dimensional features aligned with Research Domain Criteria and cognitive, personality, and temperament theory as well as neurobiology. We describe several avenues of work in this area, utilizing different statistical, computational, and machine learning approaches to resolve heterogeneity in ADHD. We offer methodological and conceptual recommendations. Methodologically, we propose that an integrated approach utilizing theory and advanced computational logic to address targeted questions, with consideration of developmental context, can render the heterogeneity problem tractable for ADHD. Conceptually, we conclude that the field is on the cusp of justifying an emotionally dysregulated subprofile in ADHD that may be useful for clinical prediction and treatment testing. Cognitive profiles, while more nascent, may be useful for clinical prediction and treatment assignment in different ways depending on developmental stage. Targeting these psychological profiles for neurobiological and etiological study to capture different pathophysiological routes remains a near-term opportunity. Subtypes are likely to be multifactorial, cut across multiple dimensions, and depend on the research or clinical outcomes of interest for their ultimate selection. In this context parallel profiles based on cognition, emotion, and specific neural signatures appear to be on the horizon, each with somewhat different utilities. Efforts to integrate such cross-cutting profiles within a conceptual dysregulation framework are well underway.

Decoding and mapping task states of the human brain via deep learning

Support vector machine (SVM)-based multivariate pattern analysis (MVPA) has delivered promising performance in decoding specific task states based on functional magnetic resonance imaging (fMRI) of the human brain. Conventionally, the SVM-MVPA requires careful feature selection/extraction according to expert knowledge. In this study, we propose a deep neural network (DNN) for directly decoding multiple brain task states from fMRI signals of the brain without any burden for feature handcrafts. We trained and tested the DNN classifier using task fMRI data from the Human Connectome Project's S1200 dataset (N = 1,034). In tests to verify its performance, the proposed classification method identified seven tasks with an average accuracy of 93.7%. We also showed the general applicability of the DNN for transfer learning to small datasets (N = 43), a situation encountered in typical neuroscience research. The proposed method achieved an average accuracy of 89.0 and 94.7% on a working memory task and a motor classification task, respectively, higher than the accuracy of 69.2 and 68.6% obtained by the SVM-MVPA. A network visualization analysis showed that the DNN automatically detected features from areas of the brain related to each task. Without incurring the burden of handcrafting the features, the proposed deep decoding method can classify brain task states highly accurately, and is a powerful tool for fMRI researchers.

Model-based whole-brain effective connectivity to study distributed cognition in health and disease

Neuroimaging techniques are now widely used to study human cognition. The functional associations between brain areas have become a standard proxy to describe how cognitive processes are distributed across the brain network. Among the many analysis tools available, dynamic models of brain activity have been developed to overcome the limitations of original connectivity measures such as functional connectivity. This goes in line with the many efforts devoted to the assessment of directional interactions between brain areas from the observed neuroimaging activity. This opinion article provides an overview of our model-based whole-brain effective connectivity to analyze fMRI data, while discussing the pros and cons of our approach with respect to other established approaches. Our framework relies on the multivariate Ornstein-Uhlenbeck (MOU) process and is thus referred to as MOU-EC. Once tuned, the model provides a directed connectivity estimate that reflects the dynamical state of BOLD activity, which can be used to explore cognition. We illustrate this approach using two applications on task-evoked fMRI data. First, as a connectivity measure, MOU-EC can be used to extract biomarkers for task-specific brain coordination, understood as the patterns of areas exchanging information. The multivariate nature of connectivity measures raises several challenges for whole-brain analysis, for which machine-learning tools present some advantages over statistical testing. Second, we show how to interpret changes in MOU-EC connections in a collective and model-based manner, bridging with network analysis. Our framework provides a comprehensive set of tools that open exciting perspectives to study distributed cognition, as well as neuropathologies.

Discovering the Computational Relevance of Brain Network Organization

Understanding neurocognitive computations will require not just localizing cognitive information distributed throughout the brain but also determining how that information got there. We review recent advances in linking empirical and simulated brain network organization with cognitive information processing. Building on these advances, we offer a new framework for understanding the role of connectivity in cognition: network coding (encoding/decoding) models. These models utilize connectivity to specify the transfer of information via neural activity flow processes, successfully predicting the formation of cognitive representations in empirical neural data. The success of these models supports the possibility that localized neural functions mechanistically emerge (are computed) from distributed activity flow processes that are specified primarily by connectivity patterns.

Whole-Brain Exploratory Analysis of Functional Task Response Following Erythropoietin Treatment in Mood Disorders: A Supervised Machine Learning Approach

A core symptom of mood disorders is cognitive impairment in attention, memory and executive functions. Erythropoietin (EPO) is a candidate treatment for cognitive impairment in unipolar and bipolar disorders (UD and BD) and modulates cognition-related neural activity across a fronto-temporo-parietal network. This report investigates predicting the pharmacological treatment from functional magnetic resonance imaging (fMRI) data using a supervised machine learning approach. A total of 84 patients with UD or BD were included in a randomized double-blind parallel-group study in which they received eight weekly infusions of either EPO (40 000 IU) or saline. Task fMRI data were collected before EPO/saline infusions started (baseline) and 6 weeks after last infusion (follow-up). During the scanning sessions, participants were given an n-back working memory and a picture encoding task. Linear classification models with different regularization techniques were used to predict treatment status from both cross-sectional data (at follow-up) and longitudinal data (difference between baseline and follow-up). For the n-back and picture encoding tasks, data were available and analyzed for 52 (EPO; n = 28, Saline; n = 24) and 59 patients (EPO; n = 31, Saline; n = 28), respectively. We found limited evidence that the classifiers used could predict treatment status at a reliable level of performance (≤60% accuracy) when tested using repeated cross-validation. There was no difference in using cross-sectional versus longitudinal data. Whole-brain multivariate decoding applied to pharmaco-fMRI in small to moderate samples seems to be suboptimal for exploring data driven neuronal treatment mechanisms.

Computational and Informatic Advances for Reproducible Data Analysis in Neuroimaging

The reproducibility of scientific research has become a point of critical concern. We argue that openness and transparency are critical for reproducibility, and we outline an ecosystem for open and transparent science that has emerged within the human neuroimaging community. We discuss the range of open data-sharing resources that have been developed for neuroimaging data, as well as the role of data standards (particularly the brain imaging data structure) in enabling the automated sharing, processing, and reuse of large neuroimaging data sets. We outline how the open source Python language has provided the basis for a data science platform that enables reproducible data analysis and visualization. We also discuss how new advances in software engineering, such as containerization, provide the basis for greater reproducibility in data analysis. The emergence of this new ecosystem provides an example for many areas of science that are currently struggling with reproducibility.

The superior longitudinal fasciculus and its functional triple-network mechanisms in brooding

Brooding, which refers to a repetitive focus on one's distress, is associated with functional connectivity within Default-Mode, Salience, and Executive-Control networks (DMN; SN; ECN), comprising the so-called "triple-network" of attention. Individual differences in brain structure that might perseverate dysfunctional connectivity of brain networks associated with brooding are less clear, however. Using diffusion and functional Magnetic Resonance Imaging, we explored multimodal relationships between brooding severity, white-matter microstructure, and resting-state functional connectivity in depressed adults (N = 32-44), and then examined whether findings directly replicated in a demographically-similar, independent sample (N = 36-45). Among the fully-replicated results, three core findings emerged. First, brooding severity is associated with functional integration and segregation of the triple-network, particularly with a Precuneal subnetwork of the DMN. Second, microstructural asymmetry of the Superior Longitudinal Fasciculus (SLF) provides a robust structural connectivity basis for brooding and may account for over 20% of its severity (Discovery: adj. R² = 0.18; Replication: adj. R² = 0.22; MSE = 0.06, Predictive R² = 0.22). Finally, microstructure of the right SLF and auxiliary white-matter is associated with the functional connectivity correlates of brooding, both within and between components of the triple-network (Discovery: adj. R² = 0.21; Replication: adj. R² = 0.18; MSE = 0.03, Predictive R² = 0.21-0.22). By cross-validating multimodal discovery with replication, the present findings help to reproducibly unify disparate perspectives of brooding etiology. Based on that synthesis, our study reformulates brooding as a microstructural-functional connectivity neurophenotype.