Integrating across neuroimaging modalities boosts prediction accuracy of cognitive ability

Multivariate analysis of multimodal brain structure predicts individual differences in risk and intertemporal preference

Large changes to brain structure (e.g., from damage or disease) can explain alterations in behavior. It is therefore plausible that smaller structural differences in healthy samples can be used to better understand and predict individual differences in behavior. Despite the brain's multivariate and distributed structure-to-function mapping, most studies have used univariate analyses of individual structural brain measures. Here we used a multivariate approach in a multimodal data set composed of volumetric, surface-based, diffusion-based, and functional resting-state MRI measures to predict reliable individual differences in risk and intertemporal preferences. We show that combining twelve brain structure measures led to better predictions across tasks than using any individual measure, and by examining model coefficients, we visualize the relative contribution of different brain measures from different brain regions. Using a multivariate approach to brain structure-to-function mapping that combines across many brain structure properties, along with reliably measured behavior phenotypes, may increase out-of-sample prediction accuracies and insight into neural underpinnings. Furthermore, this methodological approach may be useful to improve predictions and neural insight across basic, translational, and clinical research fields.

Individual characteristics outperform resting-state fMRI for the prediction of behavioral phenotypes

In this study, we aimed to compare imaging-based features of brain function, measured by resting-state fMRI (rsfMRI), with individual characteristics such as age, gender, and total intracranial volume to predict behavioral measures. We developed a machine learning framework based on rsfMRI features in a dataset of 20,000 healthy individuals from the UK Biobank, focusing on temporal complexity and functional connectivity measures. Our analysis across four behavioral phenotypes revealed that both temporal complexity and functional connectivity measures provide comparable predictive performance. However, individual characteristics consistently outperformed rsfMRI features in predictive accuracy, particularly in analyses involving smaller sample sizes. Integrating rsfMRI features with demographic data sometimes enhanced predictive outcomes. The efficacy of different predictive modeling techniques and the choice of brain parcellation atlas were also examined, showing no significant influence on the results. To summarize, while individual characteristics are superior to rsfMRI in predicting behavioral phenotypes, rsfMRI still conveys additional predictive value in the context of machine learning, such as investigating the role of specific brain regions in behavioral phenotypes.

Brain age has limited utility as a biomarker for capturing fluid cognition in older individuals

One well-known biomarker candidate that supposedly helps capture fluid cognition is Brain Age, or a predicted value based on machine-learning models built to predict chronological age from brain MRI. To formally evaluate the utility of Brain Age for capturing fluid cognition, we built 26 age-prediction models for Brain Age based on different combinations of MRI modalities, using the Human Connectome Project in Aging (n=504, 36-100 years old). First, based on commonality analyses, we found a large overlap between Brain Age and chronological age: Brain Age could uniquely add only around 1.6% in explaining variation in fluid cognition over and above chronological age. Second, the age-prediction models that performed better at predicting chronological age did NOT necessarily create better Brain Age for capturing fluid cognition over and above chronological age. Instead, better-performing age-prediction models created Brain Age that overlapped larger with chronological age, up to around 29% out of 32%, in explaining fluid cognition. Third, Brain Age missed around 11% of the total variation in fluid cognition that could have been explained by the brain variation. That is, directly predicting fluid cognition from brain MRI data (instead of relying on Brain Age and chronological age) could lead to around a 1/3-time improvement of the total variation explained. Accordingly, we demonstrated the limited utility of Brain Age as a biomarker for fluid cognition and made some suggestions to ensure the utility of Brain Age in explaining fluid cognition and other phenotypes of interest.

Tractometry of the Human Connectome Project: resources and insights

Introduction

The Human Connectome Project (HCP) has become a keystone dataset in human neuroscience, with a plethora of important applications in advancing brain imaging methods and an understanding of the human brain. We focused on tractometry of HCP diffusion-weighted MRI (dMRI) data.

Methods

We used an open-source software library (pyAFQ; https://yeatmanlab.github.io/pyAFQ) to perform probabilistic tractography and delineate the major white matter pathways in the HCP subjects that have a complete dMRI acquisition (n = 1,041). We used diffusion kurtosis imaging (DKI) to model white matter microstructure in each voxel of the white matter, and extracted tract profiles of DKI-derived tissue properties along the length of the tracts. We explored the empirical properties of the data: first, we assessed the heritability of DKI tissue properties using the known genetic linkage of the large number of twin pairs sampled in HCP. Second, we tested the ability of tractometry to serve as the basis for predictive models of individual characteristics (e.g., age, crystallized/fluid intelligence, reading ability, etc.), compared to local connectome features. To facilitate the exploration of the dataset we created a new web-based visualization tool and use this tool to visualize the data in the HCP tractometry dataset. Finally, we used the HCP dataset as a test-bed for a new technological innovation: the TRX file-format for representation of dMRI-based streamlines.

Results

We released the processing outputs and tract profiles as a publicly available data resource through the AWS Open Data program's Open Neurodata repository. We found heritability as high as 0.9 for DKI-based metrics in some brain pathways. We also found that tractometry extracts as much useful information about individual differences as the local connectome method. We released a new web-based visualization tool for tractometry-"Tractoscope" (https://nrdg.github.io/tractoscope). We found that the TRX files require considerably less disk space-a crucial attribute for large datasets like HCP. In addition, TRX incorporates a specification for grouping streamlines, further simplifying tractometry analysis.

Improving Predictability, Test-Retest Reliability and Generalisability of Brain-Wide Associations for Cognitive Abilities via Multimodal Stacking

Brain-wide association studies (BWASs) have attempted to relate cognitive abilities with brain phenotypes, but have been challenged by issues such as predictability, test-retest reliability, and cross-cohort generalisability. To tackle these challenges, we proposed "stacking" that combines brain magnetic resonance imaging of different modalities, from task-fMRI contrasts and functional connectivity during tasks and rest to structural measures, into one prediction model. We benchmarked the benefits of stacking, using the Human Connectome Projects: Young Adults and Aging and the Dunedin Multidisciplinary Health and Development Study. For predictability, stacked models led to out-of-sample r ∼.5-.6 when predicting cognitive abilities at the time of scanning and 36 years earlier. For test-retest reliability, stacked models reached an excellent level of reliability (ICC>.75), even when we stacked only task-fMRI contrasts together. For generalisability, a stacked model with non-task MRI built from one dataset significantly predicted cognitive abilities in other datasets. Altogether, stacking is a viable approach to undertake the three challenges of BWAS for cognitive abilities.

TractGeoNet: A geometric deep learning framework for pointwise analysis of tract microstructure to predict language assessment performance

We propose a geometric deep-learning-based framework, TractGeoNet, for performing regression using diffusion magnetic resonance imaging (dMRI) tractography and associated pointwise tissue microstructure measurements. By employing a point cloud representation, TractGeoNet can directly utilize tissue microstructure and positional information from all points within a fiber tract without the need to average or bin data along the streamline as traditionally required by dMRI tractometry methods. To improve regression performance, we propose a novel loss function, the Paired-Siamese Regression loss, which encourages the model to focus on accurately predicting the relative differences between regression label scores rather than just their absolute values. In addition, to gain insight into the brain regions that contribute most strongly to the prediction results, we propose a Critical Region Localization algorithm. This algorithm identifies highly predictive anatomical regions within the white matter fiber tracts for the regression task. We evaluate the effectiveness of the proposed method by predicting individual performance on two neuropsychological assessments of language using a dataset of 20 association white matter fiber tracts from 806 subjects from the Human Connectome Project Young Adult dataset. The results demonstrate superior prediction performance of TractGeoNet compared to several popular regression models that have been applied to predict individual cognitive performance based on neuroimaging features. Of the twenty tracts studied, we find that the left arcuate fasciculus tract is the most highly predictive of the two studied language performance assessments. Within each tract, we localize critical regions whose microstructure and point information are highly and consistently predictive of language performance across different subjects and across multiple independently trained models. These critical regions are widespread and distributed across both hemispheres and all cerebral lobes, including areas of the brain considered important for language function such as superior and anterior temporal regions, pars opercularis, and precentral gyrus. Overall, TractGeoNet demonstrates the potential of geometric deep learning to enhance the study of the brain's white matter fiber tracts and to relate their structure to human traits such as language performance.

Differential predictability of cognitive profiles from brain structure in older males and females

Structural brain imaging parameters may successfully predict cognitive performance in neurodegenerative diseases but mostly fail to predict cognitive abilities in healthy older adults. One important aspect contributing to this might be sex differences. Behaviorally, older males and females have been found to differ in terms of cognitive profiles, which cannot be captured by examining them as one homogenous group. In the current study, we examined whether the prediction of cognitive performance from brain structure, i.e. region-wise grey matter volume (GMV), would benefit from the investigation of sex-specific cognitive profiles in a large sample of older adults (1000BRAINS; N = 634; age range 55-85 years). Prediction performance was assessed using a machine learning (ML) approach. Targets represented a) a whole-sample cognitive component solution extracted from males and females, and b) sex-specific cognitive components. Results revealed a generally low predictability of cognitive profiles from region-wise GMV. In males, low predictability was observed across both, the whole sample as well as sex-specific cognitive components. In females, however, predictability differences across sex-specific cognitive components were observed, i.e. visual working memory (WM) and executive functions showed higher predictability than fluency and verbal WM. Hence, results accentuated that addressing sex-specific cognitive profiles allowed a more fine-grained investigation of predictability differences, which may not be observable in the prediction of the whole-sample solution. The current findings not only emphasize the need to further investigate the predictive power of each cognitive component, but they also emphasize the importance of sex-specific analyses in older adults.

Gray and White Matter Metrics Demonstrate Distinct and Complementary Prediction of Differences in Cognitive Performance in Children: Findings from ABCD (N = 11,876)

Individual differences in cognitive performance in childhood are a key predictor of significant life outcomes such as educational attainment and mental health. Differences in cognitive ability are governed in part by variations in brain structure. However, studies commonly focus on either gray or white matter metrics in humans, leaving open the key question as to whether gray or white matter microstructure plays distinct or complementary roles supporting cognitive performance. To compare the role of gray and white matter in supporting cognitive performance, we used regularized structural equation models to predict cognitive performance with gray and white matter measures. Specifically, we compared how gray matter (volume, cortical thickness, and surface area) and white matter measures (volume, fractional anisotropy, and mean diffusivity) predicted individual differences in cognitive performance. The models were tested in 11,876 children (ABCD Study; 5,680 female, 6,196 male) at 10 years old. We found that gray and white matter metrics bring partly nonoverlapping information to predict cognitive performance. The models with only gray or white matter explained respectively 15.4 and 12.4% of the variance in cognitive performance, while the combined model explained 19.0%. Zooming in, we additionally found that different metrics within gray and white matter had different predictive power and that the tracts/regions that were most predictive of cognitive performance differed across metrics. These results show that studies focusing on a single metric in either gray or white matter to study the link between brain structure and cognitive performance are missing a key part of the equation.

Impact of brain parcellation on prediction performance in models of cognition and demographics

Brain connectivity analysis begins with the selection of a parcellation scheme that will define brain regions as nodes of a network whose connections will be studied. Brain connectivity has already been used in predictive modelling of cognition, but it remains unclear if the resolution of the parcellation used can systematically impact the predictive model performance. In this work, structural, functional and combined connectivity were each defined with five different parcellation schemes. The resolution and modality of the parcellation schemes were varied. Each connectivity defined with each parcellation was used to predict individual differences in age, education, sex, executive function, self-regulation, language, encoding and sequence processing. It was found that low-resolution functional parcellation consistently performed above chance at producing generalisable models of both demographics and cognition. However, no single parcellation scheme showed a superior predictive performance across all cognitive domains and demographics. In addition, although parcellation schemes impacted the graph theory measures of each connectivity type (structural, functional and combined), these differences did not account for the out-of-sample predictive performance of the models. Taken together, these findings demonstrate that while high-resolution parcellations may be beneficial for modelling specific individual differences, partial voluming of signals produced by the higher resolution of the parcellation likely disrupts model generalisability.

Prediction of cognitive performance differences in older age from multimodal neuroimaging data

Differences in brain structure and functional and structural network architecture have been found to partly explain cognitive performance differences in older ages. Thus, they may serve as potential markers for these differences. Initial unimodal studies, however, have reported mixed prediction results of selective cognitive variables based on these brain features using machine learning (ML). Thus, the aim of the current study was to investigate the general validity of cognitive performance prediction from imaging data in healthy older adults. In particular, the focus was with examining whether (1) multimodal information, i.e., region-wise grey matter volume (GMV), resting-state functional connectivity (RSFC), and structural connectivity (SC) estimates, may improve predictability of cognitive targets, (2) predictability differences arise for global cognition and distinct cognitive profiles, and (3) results generalize across different ML approaches in 594 healthy older adults (age range: 55-85 years) from the 1000BRAINS study. Prediction potential was examined for each modality and all multimodal combinations, with and without confound (i.e., age, education, and sex) regression across different analytic options, i.e., variations in algorithms, feature sets, and multimodal approaches (i.e., concatenation vs. stacking). Results showed that prediction performance differed considerably between deconfounding strategies. In the absence of demographic confounder control, successful prediction of cognitive performance could be observed across analytic choices. Combination of different modalities tended to marginally improve predictability of cognitive performance compared to single modalities. Importantly, all previously described effects vanished in the strict confounder control condition. Despite a small trend for a multimodal benefit, developing a biomarker for cognitive aging remains challenging.

White matter and literacy: A dynamic system in flux

Cross-sectional studies have linked differences in white matter tissue properties to reading skills. However, past studies have reported a range of, sometimes conflicting, results. Some studies suggest that white matter properties act as individual-level traits predictive of reading skill, whereas others suggest that reading skill and white matter develop as a function of an individual's educational experience. In the present study, we tested two hypotheses: a) that diffusion properties of the white matter reflect stable brain characteristics that relate to stable individual differences in reading ability or b) that white matter is a dynamic system, linked with learning over time. To answer these questions, we examined the relationship between white matter and reading in a five-year longitudinal dataset and a series of large-scale, single-observation, cross-sectional datasets (N = 14,249 total participants). We find that gains in reading skill correspond to longitudinal changes in the white matter. However, in the cross-sectional datasets, we find no evidence for the hypothesis that individual differences in white matter predict reading skill. These findings highlight the link between dynamic processes in the white matter and learning.

Grey and white matter metrics demonstrate distinct and complementary prediction of differences in cognitive performance in children: Findings from ABCD (N= 11 876)

Individual differences in cognitive performance in childhood are a key predictor of significant life outcomes such as educational attainment and mental health. Differences in cognitive ability are governed in part by variations in brain structure. However, studies commonly focus on either grey or white matter metrics in humans, leaving open the key question as to whether grey or white matter microstructure play distinct or complementary roles supporting cognitive performance. To compare the role of grey and white matter in supporting cognitive performance, we used regularized structural equation models to predict cognitive performance with grey and white matter measures. Specifically, we compared how grey matter (volume, cortical thickness and surface area) and white matter measures (volume, fractional anisotropy and mean diffusivity) predicted individual differences in cognitive performance. The models were tested in 11,876 children (ABCD Study, 5680 female; 6196 male) at 10 years old. We found that grey and white matter metrics bring partly non-overlapping information to predict cognitive performance. The models with only grey or white matter explained respectively 15.4% and 12.4% of the variance in cognitive performance, while the combined model explained 19.0%. Zooming in we additionally found that different metrics within grey and white matter had different predictive power, and that the tracts/regions that were most predictive of cognitive performance differed across metric. These results show that studies focusing on a single metric in either grey or white matter to study the link between brain structure and cognitive performance are missing a key part of the equation.

The challenges and prospects of brain-based prediction of behaviour

Relating individual brain patterns to behaviour is fundamental in system neuroscience. Recently, the predictive modelling approach has become increasingly popular, largely due to the recent availability of large open datasets and access to computational resources. This means that we can use machine learning models and interindividual differences at the brain level represented by neuroimaging features to predict interindividual differences in behavioural measures. By doing so, we could identify biomarkers and neural correlates in a data-driven fashion. Nevertheless, this budding field of neuroimaging-based predictive modelling is facing issues that may limit its potential applications. Here we review these existing challenges, as well as those that we anticipate as the field develops. We focus on the impacts of these challenges on brain-based predictions. We suggest potential solutions to address the resolvable challenges, while keeping in mind that some general and conceptual limitations may also underlie the predictive modelling approach.

Using graph theory as a common language to combine neural structure and function in models of healthy cognitive performance

Graph theory has been used in cognitive neuroscience to understand how organisational properties of structural and functional brain networks relate to cognitive function. Graph theory may bridge the gap in integration of structural and functional connectivity by introducing common measures of network characteristics. However, the explanatory and predictive value of combined structural and functional graph theory have not been investigated in modelling of cognitive performance of healthy adults. In this work, a Principal Component Regression approach with embedded Step-Wise Regression was used to fit multiple regression models of Executive Function, Self-regulation, Language, Encoding and Sequence Processing with a collection of 20 different graph theoretic measures of structural and functional network organisation used as regressors. The predictive ability of graph theory-based models was compared to that of connectivity-based models. The present work shows that using combinations of graph theory metrics to predict cognition in healthy populations does not produce a consistent benefit relative to making predictions based on structural and functional connectivity values directly.

Classification and prediction of cognitive performance differences in older age based on brain network patterns using a machine learning approach

Age-related cognitive decline varies greatly in healthy older adults, which may partly be explained by differences in the functional architecture of brain networks. Resting-state functional connectivity (RSFC) derived network parameters as widely used markers describing this architecture have even been successfully used to support diagnosis of neurodegenerative diseases. The current study aimed at examining whether these parameters may also be useful in classifying and predicting cognitive performance differences in the normally aging brain by using machine learning (ML). Classifiability and predictability of global and domain-specific cognitive performance differences from nodal and network-level RSFC strength measures were examined in healthy older adults from the 1000BRAINS study (age range: 55-85 years). ML performance was systematically evaluated across different analytic choices in a robust cross-validation scheme. Across these analyses, classification performance did not exceed 60% accuracy for global and domain-specific cognition. Prediction performance was equally low with high mean absolute errors (MAEs ≥ 0.75) and low to none explained variance (R2 ≤ 0.07) for different cognitive targets, feature sets, and pipeline configurations. Current results highlight limited potential of functional network parameters to serve as sole biomarker for cognitive aging and emphasize that predicting cognition from functional network patterns may be challenging.

Longitudinally stable, brain-based predictive models mediate the relationships between childhood cognition and socio-demographic, psychological and genetic factors

Cognitive abilities are one of the major transdiagnostic domains in the National Institute of Mental Health's Research Domain Criteria (RDoC). Following RDoC's integrative approach, we aimed to develop brain-based predictive models for cognitive abilities that (a) are developmentally stable over years during adolescence and (b) account for the relationships between cognitive abilities and socio-demographic, psychological and genetic factors. For this, we leveraged the unique power of the large-scale, longitudinal data from the Adolescent Brain Cognitive Development (ABCD) study (n ~ 11 k) and combined MRI data across modalities (task-fMRI from three tasks: resting-state fMRI, structural MRI and DTI) using machine-learning. Our brain-based, predictive models for cognitive abilities were stable across 2 years during young adolescence and generalisable to different sites, partially predicting childhood cognition at around 20% of the variance. Moreover, our use of 'opportunistic stacking' allowed the model to handle missing values, reducing the exclusion from around 80% to around 5% of the data. We found fronto-parietal networks during a working-memory task to drive childhood-cognition prediction. The brain-based, predictive models significantly, albeit partially, accounted for variance in childhood cognition due to (1) key socio-demographic and psychological factors (proportion mediated = 18.65% [17.29%-20.12%]) and (2) genetic variation, as reflected by the polygenic score of cognition (proportion mediated = 15.6% [11%-20.7%]). Thus, our brain-based predictive models for cognitive abilities facilitate the development of a robust, transdiagnostic research tool for cognition at the neural level in keeping with the RDoC's integrative framework.

Feature-space selection with banded ridge regression

Encoding models provide a powerful framework to identify the information represented in brain recordings. In this framework, a stimulus representation is expressed within a feature space and is used in a regularized linear regression to predict brain activity. To account for a potential complementarity of different feature spaces, a joint model is fit on multiple feature spaces simultaneously. To adapt regularization strength to each feature space, ridge regression is extended to banded ridge regression, which optimizes a different regularization hyperparameter per feature space. The present paper proposes a method to decompose over feature spaces the variance explained by a banded ridge regression model. It also describes how banded ridge regression performs a feature-space selection, effectively ignoring non-predictive and redundant feature spaces. This feature-space selection leads to better prediction accuracy and to better interpretability. Banded ridge regression is then mathematically linked to a number of other regression methods with similar feature-space selection mechanisms. Finally, several methods are proposed to address the computational challenge of fitting banded ridge regressions on large numbers of voxels and feature spaces. All implementations are released in an open-source Python package called Himalaya.

A cross-cohort replicable and heritable latent dimension linking behaviour to multi-featured brain structure

Identifying associations between interindividual variability in brain structure and behaviour requires large cohorts, multivariate methods, out-of-sample validation and, ideally, out-of-cohort replication. Moreover, the influence of nature vs nurture on brain-behaviour associations should be analysed. We analysed associations between brain structure (grey matter volume, cortical thickness, and surface area) and behaviour (spanning cognition, emotion, and alertness) using regularized canonical correlation analysis and a machine learning framework that tests the generalisability and stability of such associations. The replicability of brain-behaviour associations was assessed in two large, independent cohorts. The load of genetic factors on these associations was analysed with heritability and genetic correlation. We found one heritable and replicable latent dimension linking cognitive-control/executive-functions and positive affect to brain structural variability in areas typically associated with higher cognitive functions, and with areas typically associated with sensorimotor functions. These results revealed a major axis of interindividual behavioural variability linking to a whole-brain structural pattern.

Comparison of individualized behavioral predictions across anatomical, diffusion and functional connectivity MRI

A fundamental goal across the neurosciences is the characterization of relationships linking brain anatomy, functioning, and behavior. Although various MRI modalities have been developed to probe these relationships, direct comparisons of their ability to predict behavior have been lacking. Here, we compared the ability of anatomical T1, diffusion and functional MRI (fMRI) to predict behavior at an individual level. Cortical thickness, area and volume were extracted from anatomical T1 images. Diffusion Tensor Imaging (DTI) and approximate Neurite Orientation Dispersion and Density Imaging (NODDI) models were fitted to the diffusion images. The resulting metrics were projected to the Tract-Based Spatial Statistics (TBSS) skeleton. We also ran probabilistic tractography for the diffusion images, from which we extracted the stream count, average stream length, and the average of each DTI and NODDI metric across tracts connecting each pair of brain regions. Functional connectivity (FC) was extracted from both task and resting-state fMRI. Individualized prediction of a wide range of behavioral measures were performed using kernel ridge regression, linear ridge regression and elastic net regression. Consistency of the results were investigated with the Human Connectome Project (HCP) and Adolescent Brain Cognitive Development (ABCD) datasets. In both datasets, FC-based models gave the best prediction performance, regardless of regression model or behavioral measure. This was especially true for the cognitive component. Furthermore, all modalities were able to predict cognition better than other behavioral components. Combining all modalities improved prediction of cognition, but not other behavioral components. Finally, across all behaviors, combining resting and task FC yielded prediction performance similar to combining all modalities. Overall, our study suggests that in the case of healthy children and young adults, behaviorally-relevant information in T1 and diffusion features might reflect a subset of the variance captured by FC.

Capturing Brain-Cognition Relationship: Integrating Task-Based fMRI Across Tasks Markedly Boosts Prediction and Test-Retest Reliability

Capturing individual differences in cognition is central to human neuroscience. Yet our ability to estimate cognitive abilities via brain MRI is still poor in both prediction and reliability. Our study tested if this inability can be improved by integrating MRI signals across the whole brain and across modalities, including task-based functional MRI (tfMRI) of different tasks along with other non-task MRI modalities, such as structural MRI, resting-state functional connectivity. Using the Human Connectome Project (n=873, 473 females, after quality control), we directly compared predictive models comprising different sets of MRI modalities (e.g., seven tasks vs. non-task modalities). We applied two approaches to integrate multimodal MRI, stacked vs. flat models, and implemented 16 combinations of machine-learning algorithms. The stacked model integrating all modalities via stacking Elastic Net provided the best prediction (r=.57), relatively to other models tested, as well as excellent test-retest reliability (ICC=∼.85) in capturing general cognitive abilities. Importantly, compared to the stacked model integrating across non-task modalities (r=.27), the stacked model integrating tfMRI across tasks led to significantly higher prediction (r=.56) while still providing excellent test-retest reliability (ICC=∼.83). The stacked model integrating tfMRI across tasks was driven by frontal and parietal areas and by tasks that are cognition-related (working-memory, relational processing, and language). This result is consistent with the parieto-frontal integration theory of intelligence. Accordingly, our results contradict the recently popular notion that tfMRI is not reliable enough to capture individual differences in cognition. Instead, our study suggests that tfMRI, when used appropriately (i.e., by drawing information across the whole brain and across tasks and by integrating with other modalities), provides predictive and reliable sources of information for individual differences in cognitive abilities, more so than non-task modalities.

Combination of structural and functional connectivity explains unique variation in specific domains of cognitive function

The relationship between structural and functional brain networks has been characterised as complex: the two networks mirror each other and show mutual influence but they also diverge in their organisation. This work explored whether a combination of structural and functional connectivity can improve the fit of regression models of cognitive performance. Principal Component Analysis (PCA) was first applied to cognitive data from the Human Connectome Project to identify latent cognitive components: Executive Function, Self-regulation, Language, Encoding and Sequence Processing. A Principal Component Regression approach with embedded Step-Wise Regression (SWR-PCR) was then used to fit regression models of each cognitive domain based on structural (SC), functional (FC) or combined structural-functional (CC) connectivity. Executive Function was best explained by the CC model. Self-regulation was equally well explained by SC and FC. Language was equally well explained by CC and FC models. Encoding and Sequence Processing were best explained by SC. Evaluation of out-of-sample models' skill via cross-validation showed that SC, FC and CC produced generalisable models of Language performance. SC models performed most effectively at predicting Language performance in unseen sample. Executive Function was most effectively predicted by SC models, followed only by CC models. Self-regulation was only effectively predicted by CC models and Sequence Processing was only effectively predicted by FC models. The present study demonstrates that integrating structural and functional connectivity can help explaining cognitive performance, but that the added explanatory value (in sample) may be domain-specific and can come at the expense of reduced generalisation performance (out-of-sample).

Brain Mapping of Behavioral Domains Using Multi-Scale Networks and Canonical Correlation Analysis

Simultaneous mapping of multiple behavioral domains into brain networks remains a major challenge. Here, we shed some light on this problem by employing a combination of machine learning, structural and functional brain networks at different spatial resolutions (also known as scales), together with performance scores across multiple neurobehavioral domains, including sensation, motor skills, and cognition. Provided by the Human Connectome Project, we make use of three cohorts: 640 participants for model training, 160 subjects for validation, and 200 subjects for model performance testing thus enhancing prediction generalization. Our modeling consists of two main stages, namely dimensionality reduction in brain network features at multiple scales, followed by canonical correlation analysis, which determines an optimal linear combination of connectivity features to predict multiple behavioral performance scores. To assess the differences in the predictive power of each modality, we separately applied three different strategies: structural unimodal, functional unimodal, and multimodal, that is, structural in combination with functional features of the brain network. Our results show that the multimodal association outperforms any of the unimodal analyses. Then, to answer which human brain structures were most involved in predicting multiple behavioral scores, we simulated different synthetic scenarios in which in each case we completely deleted a brain structure or a complete resting state network, and recalculated performance in its absence. In deletions, we found critical structures to affect performance when predicting single behavioral domains, but this occurred in a lesser manner for prediction of multi-domain behavior. Overall, our results confirm that although there are synergistic contributions between brain structure and function that enhance behavioral prediction, brain networks may also be mutually redundant in predicting multidomain behavior, such that even after deletion of a structure, the connectivity of the others can compensate for its lack in predicting behavior.

Linking interindividual variability in brain structure to behaviour

What are the brain structural correlates of interindividual differences in behaviour? More than a decade ago, advances in structural MRI opened promising new avenues to address this question. The initial wave of research then progressively led to substantial conceptual and methodological shifts, and a replication crisis unveiled the limitations of traditional approaches, which involved searching for associations between local measurements of neuroanatomy and behavioural variables in small samples of healthy individuals. Given these methodological issues and growing scepticism regarding the idea of one-to-one mapping of psychological constructs to brain regions, new perspectives emerged. These not only embrace the multivariate nature of brain structure-behaviour relationships and promote generalizability but also embrace the representation of the relationships between brain structure and behavioural data by latent dimensions of interindividual variability. Here, we examine the past and present of the study of brain structure-behaviour associations in healthy populations and address current challenges and open questions for future investigations.

Integrating multiple brain imaging modalities does not boost prediction of subclinical atherosclerosis in midlife adults

•

Brain measures from MRI do not improve Framingham Risk Score prediction of CA-IMT.

•

Prediction stacking is a flexible approach to determine added predictive utility.

•

Multimodal stacking can be applied to individual difference factors.

Background

Human neuroimaging evidence suggests that cardiovascular disease (CVD) risk may relate to functional and structural features of the brain. The present study tested whether combining functional and structural (multimodal) brain measures, derived from magnetic resonance imaging (MRI), would yield a multivariate brain biomarker that reliably predicts a subclinical marker of CVD risk, carotid-artery intima-media thickness (CA-IMT).

Methods

Neuroimaging, cardiovascular, and demographic data were assessed in 324 midlife and otherwise healthy adults who were free of (a) clinical CVD and (b) use of medications for chronic illnesses (aged 30–51 years, 49% female). We implemented a prediction stacking algorithm that combined multimodal brain imaging measures and Framingham Risk Scores (FRS) to predict CA-IMT. We included imaging measures that could be easily obtained in clinical settings: resting state functional connectivity and structural morphology measures from T1-weighted images.

Results

Our models reliably predicted CA-IMT using FRS, as well as for several individual MRI measures; however, none of the individual MRI measures outperformed FRS. Moreover, stacking functional and structural brain measures with FRS did not boost prediction accuracy above that of FRS alone.

Conclusions

Combining multimodal functional and structural brain measures through a stacking algorithm does not appear to yield a reliable brain biomarker of subclinical CVD, as reflected by CA-IMT.

Multidimensional analysis and detection of informative features in human brain white matter

The white matter contains long-range connections between different brain regions and the organization of these connections holds important implications for brain function in health and disease. Tractometry uses diffusion-weighted magnetic resonance imaging (dMRI) to quantify tissue properties along the trajectories of these connections. Statistical inference from tractometry usually either averages these quantities along the length of each fiber bundle or computes regression models separately for each point along every one of the bundles. These approaches are limited in their sensitivity, in the former case, or in their statistical power, in the latter. We developed a method based on the sparse group lasso (SGL) that takes into account tissue properties along all of the bundles and selects informative features by enforcing both global and bundle-level sparsity. We demonstrate the performance of the method in two settings: i) in a classification setting, patients with amyotrophic lateral sclerosis (ALS) are accurately distinguished from matched controls. Furthermore, SGL identifies the corticospinal tract as important for this classification, correctly finding the parts of the white matter known to be affected by the disease. ii) In a regression setting, SGL accurately predicts "brain age." In this case, the weights are distributed throughout the white matter indicating that many different regions of the white matter change over the lifespan. Thus, SGL leverages the multivariate relationships between diffusion properties in multiple bundles to make accurate phenotypic predictions while simultaneously discovering the most relevant features of the white matter.