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

Comparing the stability and reproducibility of brain-behavior relationships found using canonical correlation analysis and partial least squares within the ABCD sample

Canonical correlation analysis (CCA) and partial least squares correlation (PLS) detect linear associations between two data matrices by computing latent variables (LVs) having maximal correlation (CCA) or covariance (PLS). This study compared the similarity and generalizability of CCA- and PLS-derived brain-behavior relationships. Data were accessed from the baseline Adolescent Brain Cognitive Development (ABCD) dataset (N > 9,000, 9-11 years). The brain matrix consisted of cortical thickness estimates from the Desikan-Killiany atlas. Two phenotypic scales were examined separately as the behavioral matrix; the Child Behavioral Checklist (CBCL) subscale scores and NIH Toolbox performance scores. Resampling methods were used to assess significance and generalizability of LVs. LV1 for the CBCL brain relationships was found to be significant, yet not consistently stable or reproducible, across CCA and PLS models (singular value: CCA = .13, PLS = .39, p < .001). LV1 for the NIH brain relationships showed similar relationships between CCA and PLS and was found to be stable and reproducible (singular value: CCA = .21, PLS = .43, p < .001). The current study suggests that stability and reproducibility of brain-behavior relationships identified by CCA and PLS are influenced by the statistical characteristics of the phenotypic measure used when applied to a large population-based pediatric sample.

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.

Network and state specificity in connectivity-based predictions of individual behavior

Predicting individual behavior from brain functional connectivity (FC) patterns can contribute to our understanding of human brain functioning. This may apply in particular if predictions are based on features derived from circumscribed, a priori defined functional networks, which improves interpretability. Furthermore, some evidence suggests that task-based FC data may yield more successful predictions of behavior than resting-state FC data. Here, we comprehensively examined to what extent the correspondence of functional network priors and task states with behavioral target domains influences the predictability of individual performance in cognitive, social, and affective tasks. To this end, we used data from the Human Connectome Project for large-scale out-of-sample predictions of individual abilities in working memory (WM), theory-of-mind cognition (SOCIAL), and emotion processing (EMO) from FC of corresponding and non-corresponding states (WM/SOCIAL/EMO/resting-state) and networks (WM/SOCIAL/EMO/whole-brain connectome). Using root mean squared error and coefficient of determination to evaluate model fit revealed that predictive performance was rather poor overall. Predictions from whole-brain FC were slightly better than those from FC in task-specific networks, and a slight benefit of predictions based on FC from task versus resting state was observed for performance in the WM domain. Beyond that, we did not find any significant effects of a correspondence of network, task state, and performance domains. Together, these results suggest that multivariate FC patterns during both task and resting states contain rather little information on individual performance levels, calling for a reconsideration of how the brain mediates individual differences in mental 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.

Release the Krakencoder: A unified brain connectome translation and fusion tool

Brain connectivity can be estimated in many ways, depending on modality and processing strategy. Here we present the Krakencoder, a joint connectome mapping tool that simultaneously, bidirectionally translates between structural (SC) and functional connectivity (FC), and across different atlases and processing choices via a common latent representation. These mappings demonstrate unprecedented accuracy and individual-level identifiability; the mapping between SC and FC has identifiability 42-54% higher than existing models. The Krakencoder combines all connectome flavors via a shared low-dimensional latent space. This "fusion" representation i) better reflects familial relatedness, ii) preserves age- and sex-relevant information and iii) enhances cognition-relevant information. The Krakencoder can be applied without retraining to new, out-of-age-distribution data while still preserving inter-individual differences in the connectome predictions and familial relationships in the latent representations. The Krakencoder is a significant leap forward in capturing the relationship between multi-modal brain connectomes in an individualized, behaviorally- and demographically-relevant way.

Predicting depression risk in early adolescence via multimodal brain imaging

Depression is an incapacitating psychiatric disorder with increased risk through adolescence. Among other factors, children with family history of depression have significantly higher risk of developing depression. Early identification of pre-adolescent children who are at risk of depression is crucial for early intervention and prevention. In this study, we used a large longitudinal sample from the Adolescent Brain Cognitive Development (ABCD) Study (2658 participants after imaging quality control, between 9-10 years at baseline), we applied advanced machine learning methods to predict depression risk at the two-year follow-up from the baseline assessment, using a set of comprehensive multimodal neuroimaging features derived from structural MRI, diffusion tensor imaging, and task and rest functional MRI. Prediction performance underwent a rigorous cross-validation method of leave-one-site-out. Our results demonstrate that all brain features had prediction scores significantly better than expected by chance, with brain features from rest-fMRI showing the best classification performance in the high-risk group of participants with parental history of depression (N = 625). Specifically, rest-fMRI features, which came from functional connectomes, showed significantly better classification performance than other brain features. This finding highlights the key role of the interacting elements of the connectome in capturing more individual variability in psychopathology compared to measures of single brain regions. Our study contributes to the effort of identifying biological risks of depression in early adolescence in population-based samples.

Voxelwise Multivariate Analysis of Brain-Psychosocial Associations in Adolescents Reveals 6 Latent Dimensions of Cognition and Psychopathology

BACKGROUND

Adolescence heralds the onset of considerable psychopathology, which may be conceptualized as an emergence of altered covariation between symptoms and brain measures. Multivariate methods can detect such modes of covariation or latent dimensions, but none specifically relating to psychopathology have yet been found using population-level structural brain data. Using voxelwise (instead of parcellated) brain data may strengthen latent dimensions' brain-psychosocial relationships, but this creates computational challenges.

METHODS

We obtained voxelwise gray matter density and psychosocial variables from the baseline (ages 9-10 years) Adolescent Brain Cognitive Development (ABCD) Study cohort (N = 11,288) and employed a state-of-the-art segmentation method, sparse partial least squares, and a rigorous machine learning framework to prevent overfitting.

RESULTS

We found 6 latent dimensions, 4 of which pertain specifically to mental health. The mental health dimensions were related to overeating, anorexia/internalizing, oppositional symptoms (all ps < .002) and attention-deficit/hyperactivity disorder symptoms (p = .03). Attention-deficit/hyperactivity disorder was related to increased and internalizing symptoms related to decreased gray matter density in dopaminergic and serotonergic midbrain areas, whereas oppositional symptoms were related to increased gray matter in a noradrenergic nucleus. Internalizing symptoms were related to increased and oppositional symptoms to reduced gray matter density in the insular, cingulate, and auditory cortices. Striatal regions featured strongly, with reduced caudate nucleus gray matter in attention-deficit/hyperactivity disorder and reduced putamen gray matter in oppositional/conduct problems. Voxelwise gray matter density generated stronger brain-psychosocial correlations than brain parcellations.

CONCLUSIONS

Voxelwise brain data strengthen latent dimensions of brain-psychosocial covariation, and sparse multivariate methods increase their psychopathological specificity. Internalizing and externalizing symptoms are associated with opposite gray matter changes in similar cortical and subcortical areas.

The Commonality and Individuality of Human Brains When Performing Tasks

It is imperative to study individual brain functioning toward understanding the neural bases responsible for individual behavioral and clinical traits. The complex and dynamic brain activity varies from area to area and from time to time across the entire brain, and BOLD-fMRI measures this spatiotemporal activity at large-scale systems level. We present a novel method to investigate task-evoked whole brain activity that varies not only from person to person but also from task trial to trial within each task type, offering a means of characterizing the individuality of human brains when performing tasks. For each task trial, the temporal correlation of task-evoked ideal time signal with the time signal of every point in the brain yields a full spatial map that characterizes the whole brain's functional co-activity (FC) relative to the task-evoked ideal response. For any two task trials, regardless of whether they are the same task or not, the spatial correlation of their corresponding two FC maps over the entire brain quantifies the similarity between these two maps, offering a means of investigating the variation in the whole brain activity trial to trial. The results demonstrated a substantially varied whole brain activity from trial to trial for each task category. The degree of this variation was task type-dependent and varied from subject to subject, showing a remarkable individuality of human brains when performing tasks. It demonstrates the potential of using the presented method to investigate the relationship of the whole brain activity with individual behavioral and clinical traits.

Translating phenotypic prediction models from big to small anatomical MRI data using meta-matching

Individualized phenotypic prediction based on structural MRI is an important goal in neuroscience. Prediction performance increases with larger samples, but small-scale datasets with fewer than 200 participants are often unavoidable. We have previously proposed a "meta-matching" framework to translate models trained from large datasets to improve the prediction of new unseen phenotypes in small collection efforts. Meta-matching exploits correlations between phenotypes, yielding large improvement over classical machine learning when applied to prediction models using resting-state functional connectivity as input features. Here, we adapt the two best performing meta-matching variants ("meta-matching finetune" and "meta-matching stacking") from our previous study to work with T1-weighted MRI data by changing the base neural network architecture to a 3D convolution neural network. We compare the two meta-matching variants with elastic net and classical transfer learning using the UK Biobank (N = 36,461), Human Connectome Project Young Adults (HCP-YA) dataset (N = 1,017) and HCP-Aging dataset (N = 656). We find that meta-matching outperforms elastic net and classical transfer learning by a large margin, both when translating models within the same dataset, as well as translating models across datasets with different MRI scanners, acquisition protocols and demographics. For example, when translating a UK Biobank model to 100 HCP-YA participants, meta-matching finetune yielded a 136% improvement in variance explained over transfer learning, with an average absolute gain of 2.6% (minimum = -0.9%, maximum = 17.6%) across 35 phenotypes. Overall, our results highlight the versatility of the meta-matching framework.

A novel technique for delineating the effect of variation in the learning rate on the neural correlates of reward prediction errors in model-based fMRI

Introduction

Computational models play an increasingly important role in describing variation in neural activation in human neuroimaging experiments, including evaluating individual differences in the context of psychiatric neuroimaging. In particular, reinforcement learning (RL) techniques have been widely adopted to examine neural responses to reward prediction errors and stimulus or action values, and how these might vary as a function of clinical status. However, there is a lack of consensus around the importance of the precision of free parameter estimation for these methods, particularly with regard to the learning rate. In the present study, I introduce a novel technique which may be used within a general linear model (GLM) to model the effect of mis-estimation of the learning rate on reward prediction error (RPE)-related neural responses.

Methods

Simulations employed a simple RL algorithm, which was used to generate hypothetical neural activations that would be expected to be observed in functional magnetic resonance imaging (fMRI) studies of RL. Similar RL models were incorporated within a GLM-based analysis method including derivatives, with individual differences in the resulting GLM-derived beta parameters being evaluated with respect to the free parameters of the RL model or being submitted to other validation analyses.

Results

Initial simulations demonstrated that the conventional approach to fitting RL models to RPE responses is more likely to reflect individual differences in a reinforcement efficacy construct (lambda) rather than learning rate (alpha). The proposed method, adding a derivative regressor to the GLM, provides a second regressor which reflects the learning rate. Validation analyses were performed including examining another comparable method which yielded highly similar results, and a demonstration of sensitivity of the method in presence of fMRI-like noise.

Conclusion

Overall, the findings underscore the importance of the lambda parameter for interpreting individual differences in RPE-coupled neural activity, and validate a novel neural metric of the modulation of such activity by individual differences in the learning rate. The method is expected to find application in understanding aberrant reinforcement learning across different psychiatric patient groups including major depression and substance use disorder.

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.

Network and State Specificity in Connectivity-Based Predictions of Individual Behavior

Predicting individual behavior from brain functional connectivity (FC) patterns can contribute to our understanding of human brain functioning. This may apply in particular if predictions are based on features derived from circumscribed, a priori defined functional networks, which improves interpretability. Furthermore, some evidence suggests that task-based FC data may yield more successful predictions of behavior than resting-state FC data. Here, we comprehensively examined to what extent the correspondence of functional network priors and task states with behavioral target domains influences the predictability of individual performance in cognitive, social, and affective tasks. To this end, we used data from the Human Connectome Project for large-scale out-of-sample predictions of individual abilities in working memory (WM), theory-of-mind cognition (SOCIAL), and emotion processing (EMO) from FC of corresponding and non-corresponding states (WM/SOCIAL/EMO/resting-state) and networks (WM/SOCIAL/EMO/whole-brain connectome). Using root mean squared error and coefficient of determination to evaluate model fit revealed that predictive performance was rather poor overall. Predictions from whole-brain FC were slightly better than those from FC in task-specific networks, and a slight benefit of predictions based on FC from task versus resting state was observed for performance in the WM domain. Beyond that, we did not find any significant effects of a correspondence of network, task state, and performance domains. Together, these results suggest that multivariate FC patterns during both task and resting states contain rather little information on individual performance levels, calling for a reconsideration of how the brain mediates individual differences in mental abilities.

Brain-Based Predictions of Psychiatric Illness-Linked Behaviors Across the Sexes

BACKGROUND

Individual differences in functional brain connectivity can be used to predict both the presence of psychiatric illness and variability in associated behaviors. However, despite evidence for sex differences in functional network connectivity and in the prevalence, presentation, and trajectory of psychiatric illnesses, the extent to which disorder-relevant aspects of network connectivity are shared or unique across the sexes remains to be determined.

METHODS

In this work, we used predictive modeling approaches to evaluate whether shared or unique functional connectivity correlates underlie the expression of psychiatric illness-linked behaviors in males and females in data from the Adolescent Brain Cognitive Development Study (N = 5260; 2571 females).

RESULTS

We demonstrate that functional connectivity profiles predict individual differences in externalizing behaviors in males and females but predict internalizing behaviors only in females. Furthermore, models trained to predict externalizing behaviors in males generalize to predict internalizing behaviors in females, and models trained to predict internalizing behaviors in females generalize to predict externalizing behaviors in males. Finally, the neurobiological correlates of many behaviors are largely shared within and across sexes: functional connections within and between heteromodal association networks, including default, limbic, control, and dorsal attention networks, are associated with internalizing and externalizing behaviors.

CONCLUSIONS

Taken together, these findings suggest that shared neurobiological patterns may manifest as distinct behaviors across the sexes. Based on these results, we recommend that both clinicians and researchers carefully consider how sex may influence the presentation of psychiatric illnesses, especially those along the internalizing-externalizing spectrum.

Functional connectomics in depression: insights into therapies

Depression is a common mental disorder characterized by heterogeneous cognitive and behavioral symptoms. The emerging research paradigm of functional connectomics has provided a quantitative theoretical framework and analytic tools for parsing variations in the organization and function of brain networks in depression. In this review, we first discuss recent progress in depression-associated functional connectome variations. We then discuss treatment-specific brain network outcomes in depression and propose a hypothetical model highlighting the advantages and uniqueness of each treatment in relation to the modulation of specific brain network connectivity and symptoms of depression. Finally, we look to the future promise of combining multiple treatment types in clinical practice, using multisite datasets and multimodal neuroimaging approaches, and identifying biological depression subtypes.

A meta-analysis and systematic review of single vs. multimodal neuroimaging techniques in the classification of psychosis

BACKGROUND

Psychotic disorders are characterized by structural and functional abnormalities in brain networks. Neuroimaging techniques map and characterize such abnormalities using unique features (e.g., structural integrity, coactivation). However, it is unclear if a specific method, or a combination of modalities, is particularly effective in identifying differences in brain networks of someone with a psychotic disorder.

METHODS

A systematic meta-analysis evaluated machine learning classification of schizophrenia spectrum disorders in comparison to healthy control participants using various neuroimaging modalities (i.e., T1-weighted imaging (T1), diffusion tensor imaging (DTI), resting state functional connectivity (rs-FC), or some combination (multimodal)). Criteria for manuscript inclusion included whole-brain analyses and cross-validation to provide a complete picture regarding the predictive ability of large-scale brain systems in psychosis. For this meta-analysis, we searched Ovid MEDLINE, PubMed, PsychInfo, Google Scholar, and Web of Science published between inception and March 13th 2023. Prediction results were averaged for studies using the same dataset, but parallel analyses were run that included studies with pooled sample across many datasets. We assessed bias through funnel plot asymmetry. A bivariate regression model determined whether differences in imaging modality, demographics, and preprocessing methods moderated classification. Separate models were run for studies with internal prediction (via cross-validation) and external prediction.

RESULTS

93 studies were identified for quantitative review (30 T1, 9 DTI, 40 rs-FC, and 14 multimodal). As a whole, all modalities reliably differentiated those with schizophrenia spectrum disorders from controls (OR = 2.64 (95%CI = 2.33 to 2.95)). However, classification was relatively similar across modalities: no differences were seen across modalities in the classification of independent internal data, and a small advantage was seen for rs-FC studies relative to T1 studies in classification in external datasets. We found large amounts of heterogeneity across results resulting in significant signs of bias in funnel plots and Egger's tests. Results remained similar, however, when studies were restricted to those with less heterogeneity, with continued small advantages for rs-FC relative to structural measures. Notably, in all cases, no significant differences were seen between multimodal and unimodal approaches, with rs-FC and unimodal studies reporting largely overlapping classification performance. Differences in demographics and analysis or denoising were not associated with changes in classification scores.

CONCLUSIONS

The results of this study suggest that neuroimaging approaches have promise in the classification of psychosis. Interestingly, at present most modalities perform similarly in the classification of psychosis, with slight advantages for rs-FC relative to structural modalities in some specific cases. Notably, results differed substantially across studies, with suggestions of biased effect sizes, particularly highlighting the need for more studies using external prediction and large sample sizes. Adopting more rigorous and systematized standards will add significant value toward understanding and treating this critical population.

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.

Few temporally distributed brain connectivity states predict human cognitive abilities

Human functional brain connectivity can be temporally decomposed into states of high and low cofluctuation, defined as coactivation of brain regions over time. Rare states of particularly high cofluctuation have been shown to reflect fundamentals of intrinsic functional network architecture and to be highly subject-specific. However, it is unclear whether such network-defining states also contribute to individual variations in cognitive abilities - which strongly rely on the interactions among distributed brain regions. By introducing CMEP, a new eigenvector-based prediction framework, we show that as few as 16 temporally separated time frames (< 1.5% of 10min resting-state fMRI) can significantly predict individual differences in intelligence (N = 263, p < .001). Against previous expectations, individual's network-defining time frames of particularly high cofluctuation do not predict intelligence. Multiple functional brain networks contribute to the prediction, and all results replicate in an independent sample (N = 831). Our results suggest that although fundamentals of person-specific functional connectomes can be derived from few time frames of highest connectivity, temporally distributed information is necessary to extract information about cognitive abilities. This information is not restricted to specific connectivity states, like network-defining high-cofluctuation states, but rather reflected across the entire length of the brain connectivity time series.

Distinct brain network features predict internalizing and externalizing traits in children and adults

Internalizing and externalizing traits are two distinct classes of behaviors in psychiatry. However, whether shared or unique brain network features predict internalizing and externalizing behaviors in children and adults remain poorly understood. Using a sample of 2262 children from the Adolescent Brain Cognitive Development (ABCD) study and 752 adults from the Human Connectome Project (HCP), we show that network features predicting internalizing and externalizing behavior are, at least in part, dissociable in children, but not in adults. In ABCD children, traits within internalizing and externalizing behavioral categories are predicted by more similar network features concatenated across task and resting states than those between different categories. We did not observe this pattern in HCP adults. Distinct network features predict internalizing and externalizing behaviors in ABCD children and HCP adults. These data reveal shared and unique brain network features accounting for individual variation within broad internalizing and externalizing categories across developmental stages.

PREDICTING DEPRESSION RISK IN EARLY ADOLESCENCE VIA MULTIMODAL BRAIN IMAGING

Depression is an incapacitating psychiatric disorder with high prevalence in adolescent populations that is influenced by many risk factors, including family history of depression. The ability to predict who may develop depression before adolescence, when rates of depression increase markedly, is important for early intervention and prevention. Using a large longitudinal sample from the Adolescent Brain Cognitive Development (ABCD) Study (2658 participants after imaging quality control, between 9-10 years at baseline), we applied machine learning methods on a set of comprehensive multimodal neuroimaging features to predict depression risk at the two-year follow-up from the baseline visit. Features include derivatives from structural MRI, diffusion tensor imaging, and task and rest functional MRI. A rigorous cross-validation method of leave-one-site-out was used. Additionally, we tested the prediction models in a high-risk group of participants with parental history of depression (N=625). The results showed all brain features had prediction scores significantly better than expected by chance. When predicting depression onset in the high-risk group, brain features from resting-state functional connectomes showed the best classification performance, outperforming other brain features based on structural MRI and task-based fMRI. Results demonstrate that the functional connectivity of the brain can predict the risk of depression in early adolescence better than other univariate neuroimaging derivatives, highlighting the key role of the interacting elements of the connectome capturing more individual variability in psychopathology compared to measures of single brain regions.

Comparing the stability and reproducibility of brain-behaviour relationships found using Canonical Correlation Analysis and Partial Least Squares within the ABCD Sample

Introduction

Canonical Correlation Analysis (CCA) and Partial Least Squares Correlation (PLS) detect associations between two data matrices based on computing a linear combination between the two matrices (called latent variables; LVs). These LVs maximize correlation (CCA) and covariance (PLS). These different maximization criteria may render one approach more stable and reproducible than the other when working with brain and behavioural data at the population-level. This study compared the LVs which emerged from CCA and PLS analyses of brain-behaviour relationships from the Adolescent Brain Cognitive Development (ABCD) dataset and examined their stability and reproducibility.

Methods

Structural T1-weighted imaging and behavioural data were accessed from the baseline Adolescent Brain Cognitive Development dataset (N > 9000, ages = 9-11 years). The brain matrix consisted of cortical thickness estimates in different cortical regions. The behavioural matrix consisted of 11 subscale scores from the parent-reported Child Behavioral Checklist (CBCL) or 7 cognitive performance measures from the NIH Toolbox. CCA and PLS models were separately applied to the brain-CBCL analysis and brain-cognition analysis. A permutation test was used to assess whether identified LVs were statistically significant. A series of resampling statistical methods were used to assess stability and reproducibility of the LVs.

Results

When examining the relationship between cortical thickness and CBCL scores, the first LV was found to be significant across both CCA and PLS models (singular value: CCA = .13, PLS = .39, p < .001). LV1 from the CCA model found that covariation of CBCL scores was linked to covariation of cortical thickness. LV1 from the PLS model identified decreased cortical thickness linked to lower CBCL scores. There was limited evidence of stability or reproducibility of LV1 for both CCA and PLS. When examining the relationship between cortical thickness and cognitive performance, there were 6 significant LVs for both CCA and PLS (p < .01). The first LV showed similar relationships between CCA and PLS and was found to be stable and reproducible (singular value: CCA = .21, PLS = .43, p < .001).

Conclusion

CCA and PLS identify different brain-behaviour relationships with limited stability and reproducibility when examining the relationship between cortical thickness and parent-reported behavioural measures. However, both methods identified relatively similar brain-behaviour relationships that were stable and reproducible when examining the relationship between cortical thickness and cognitive performance. The results of the current study suggest that stability and reproducibility of brain-behaviour relationships identified by CCA and PLS are influenced by characteristics of the analyzed sample and the included behavioural measurements when applied to a large pediatric dataset.

A Holistic Analysis of Individual Brain Activity Revealed the Relationship of Brain Areal Activity with the Entire Brain's Activity

The relationship between brain areal activity and the entire brain's activity is unknown, and understanding this relationship is imperative for understanding the neural mechanisms of human brain function at systems level. The complex activity of human brains varies from area to area and from time to time across the whole brain. BOLD-fMRI measures this spatiotemporal activity at a large-scale systems level. The BOLD time signal of an area reflects a collective neuronal activity of over one million neurons under that area, and the temporal correlation of this time signal with that of every point in the brain yields a full spatial map that characterizes the entire brain's functional co-activity (FC) relative to that area's activity. Here we show a quantitative relationship between brain areal activity and the activity of the entire brain. The temporal correlation coefficient r of the signal time courses of two areas quantifies the degree of co-activity between the two areas, and the spatial correlation coefficient R of their corresponding two FC maps quantifies the co-activity between these two maps. We found that a modified sigmoid function quantified this R with r, i.e., Rr=1+ra-1-ra1+ra+1-ra, revealing a relationship between the activity of brain areas and that of the entire brain. The parameter a in this equation was found to be associated with the mean degree of the temporal co-activity among all brain areas, and its value was brain functional state dependent too. Our study demonstrated a novel approach for analyzing fMRI data to holistically characterize the entire brain's activity quantitatively for any brain functional state in individual humans.