Unraveling the molecular relevance of brain phenotypes: A comparative analysis of null models and test statistics.

Correlating transcriptional profiles with imaging-derived phenotypes has the potential to reveal possible molecular architectures associated with cognitive functions, brain development and disorders. Competitive null models built by resampling genes and self-contained null models built by spinning brain regions, along with varying test statistics, have been used to determine the significance of transcriptional associations. However, there has been no systematic evaluation of their performance in imaging transcriptomics analyses. Here, we evaluated the performance of eight different test statistics (mean, mean absolute value, mean squared value, max mean, median, Kolmogorov-Smirnov (KS), Weighted KS and the number of significant correlations) in both competitive null models and self-contained null models. Simulated brain maps (n = 1,000) and gene sets (n = 500) were used to calculate the probability of significance (Psig) for each statistical test. Our results suggested that competitive null models may result in false positive results driven by co-expression within gene sets. Furthermore, we demonstrated that the self-contained null models may fail to account for distribution characteristics (e.g., bimodality) of correlations between all available genes and brain phenotypes, leading to false positives. These two confounding factors interacted differently with test statistics, resulting in varying outcomes. Specifically, the sign-sensitive test statistics (i.e., mean, median, KS, Weighted KS) were influenced by co-expression bias in the competitive null models, while median and sign-insensitive test statistics were sensitive to the bimodality bias in the self-contained null models. Additionally, KS-based statistics produced conservative results in the self-contained null models, which increased the risk of false negatives. Comprehensive supplementary analyses with various configurations, including realistic scenarios, supported the results. These findings suggest utilizing sign-insensitive test statistics such as mean absolute value, max mean in the competitive null models and the mean as the test statistic for the self-contained null models. Additionally, adopting the confounder-matched (e.g., coexpression-matched) null models as an alternative to standard null models can be a viable strategy. Overall, the present study offers insights into the selection of statistical tests for imaging transcriptomics studies, highlighting areas for further investigation and refinement in the evaluation of novel and commonly used tests.

Brain structural covariance network features are robust markers of early heavy alcohol use.

BACKGROUND AND AIMS: Recently, we demonstrated that a distinct pattern of structural covariance networks (SCN) from magnetic resonance imaging (MRI)-derived measurements of brain cortical thickness characterized young adults with alcohol use disorder (AUD) and predicted current and future problematic drinking in adolescents relative to controls. Here, we establish the robustness and value of SCN for identifying heavy alcohol users in three additional independent studies. DESIGN AND SETTING: Cross-sectional and longitudinal studies using data from the Pediatric Imaging, Neurocognition and Genetics (PING) study (n = 400, age range = 14-22 years), the National Consortium on Alcohol and Neurodevelopment in Adolescence (NCANDA) (n = 272, age range = 17-22 years) and the Human Connectome Project (HCP) (n = 375, age range = 22-37 years). CASES: Cases were defined based on heavy alcohol use patterns or former alcohol use disorder (AUD) diagnoses: 50, 68 and 61 cases were identified. Controls had none or low alcohol use or absence of AUD: 350, 204 and 314 controls were selected. MEASUREMENTS: Graph theory metrics of segregation and integration were used to summarize SCN. FINDINGS: Mirroring our prior findings, and across the three data sets, cases had a lower clustering coefficient [area under the curve (AUC) = -0.029, P = 0.002], lower modularity (AUC = -0.14, P = 0.004), lower average shortest path length (AUC = -0.078, P = 0.017) and higher global efficiency (AUC = 0.007, P = 0.010). Local efficiency differences were marginal (AUC = -0.017, P = 0.052). That is, cases exhibited lower network segregation and higher integration, suggesting that adjacent nodes (i.e. brain regions) were less similar in thickness whereas spatially distant nodes were more similar. CONCLUSION: Structural covariance network (SCN) differences in the brain appear to constitute an early marker of heavy alcohol use in three new data sets and, more generally, demonstrate the utility of SCN-derived metrics to detect brain-related psychopathology.

Machine learning approaches linking brain function to behavior in the ABCD STOP task.

The stop-signal task (SST) is one of the most common fMRI tasks of response inhibition, and its performance measure, the stop-signal reaction-time (SSRT), is broadly used as a measure of cognitive control processes. The neurobiology underlying individual or clinical differences in response inhibition remain unclear, consistent with the general pattern of quite modest brain-behavior associations that have been recently reported in well-powered large-sample studies. Here, we investigated the potential of multivariate, machine learning (ML) methods to improve the estimation of individual differences in SSRT with multimodal structural and functional region of interest-level neuroimaging data from 9- to 11-year-olds children in the ABCD Study. Six ML algorithms were assessed across modalities and fMRI tasks. We verified that SST activation performed best in predicting SSRT among multiple modalities including morphological MRI (cortical surface area/thickness), diffusion tensor imaging, and fMRI task activations, and then showed that SST activation explained 12% of the variance in SSRT using cross-validation and out-of-sample lockbox data sets (n = 7298). Brain regions that were more active during the task and that showed more interindividual variation in activation were better at capturing individual differences in performance on the task, but this was only true for activations when successfully inhibiting. Cortical regions outperformed subcortical areas in explaining individual differences but the two hemispheres performed equally well. These results demonstrate that the detection of reproducible links between brain function and performance can be improved with multivariate approaches and give insight into a number of brain systems contributing to individual differences in this fundamental cognitive control process.

Longitudinal assessment of brain structure and behaviour in youth with rapid weight gain: Potential contributing causes and consequences.

OBJECTIVE: Independent of weight status, rapid weight gain has been associated with underlying brain structure variation in regions associated with food intake and impulsivity among pre-adolescents. Yet, we lack clarity on how developmental maturation coincides with rapid weight gain and weight stability. METHODS: We identified brain predictors of 2-year rapid weight gain and its longitudinal effects on brain structure and impulsivity in the Adolescent Brain Cognitive DevelopmentSM Study®. Youth were categorized as Healthy Weight/Weight Stable (WSHW , n = 527) or Weight Gainers (WG, n = 221, >38lbs); 63% of the WG group were healthy weight at 9-to-10-years-old. RESULTS: A fivefold cross-validated logistic elastic-net regression revealed that rapid weight gain was associated with structural variation amongst 39 brain features at 9-to-10-years-old in regions involved with executive functioning, appetitive control and reward sensitivity. Two years later, WG youth showed differences in change over time in several of these regions and performed worse on measures of impulsivity. CONCLUSIONS: These findings suggest that brain structure in pre-adolescence may predispose some to rapid weight gain and that weight gain itself may alter maturational brain change in regions important for food intake and impulsivity. Behavioural interventions that target inhibitory control may improve trajectories of brain maturation and facilitate healthier behaviours.

Bayesian causal network modeling suggests adolescent cannabis use accelerates prefrontal cortical thinning.

While there is substantial evidence that cannabis use is associated with differences in human brain development, most of this evidence is correlational in nature. Bayesian causal network (BCN) modeling attempts to identify probable causal relationships in correlational data using conditional probabilities to estimate directional associations between a set of interrelated variables. In this study, we employed BCN modeling in 637 adolescents from the IMAGEN study who were cannabis naïve at age 14 to provide evidence that the accelerated prefrontal cortical thinning found previously in adolescent cannabis users by Albaugh et al. [1] is a result of cannabis use causally affecting neurodevelopment. BCNs incorporated data on cannabis use, prefrontal cortical thickness, and other factors related to both brain development and cannabis use, including demographics, psychopathology, childhood adversity, and other substance use. All BCN algorithms strongly suggested a directional relationship from adolescent cannabis use to accelerated cortical thinning. While BCN modeling alone does not prove a causal relationship, these results are consistent with a body of animal and human research suggesting that adolescent cannabis use adversely affects brain development.

Performance scaling for structural MRI surface parcellations: a machine learning analysis in the ABCD Study.

The use of predefined parcellations on surface-based representations of the brain as a method for data reduction is common across neuroimaging studies. In particular, prediction-based studies typically employ parcellation-driven summaries of brain measures as input to predictive algorithms, but the choice of parcellation and its influence on performance is often ignored. Here we employed preprocessed structural magnetic resonance imaging (sMRI) data from the Adolescent Brain Cognitive Development Study® to examine the relationship between 220 parcellations and out-of-sample predictive performance across 45 phenotypic measures in a large sample of 9- to 10-year-old children (N = 9,432). Choice of machine learning (ML) pipeline and use of alternative multiple parcellation-based strategies were also assessed. Relative parcellation performance was dependent on the spatial resolution of the parcellation, with larger number of parcels (up to ~4,000) outperforming coarser parcellations, according to a power-law scaling of between 1/4 and 1/3. Performance was further influenced by the type of parcellation, ML pipeline, and general strategy, with existing literature-based parcellations, a support vector-based pipeline, and ensembling across multiple parcellations, respectively, as the highest performing. These findings highlight the choice of parcellation as an important influence on downstream predictive performance, showing in some cases that switching to a higher resolution parcellation can yield a relatively large boost to performance.

Predicting alcohol dependence from multi-site brain structural measures.

To identify neuroimaging biomarkers of alcohol dependence (AD) from structural magnetic resonance imaging, it may be useful to develop classification models that are explicitly generalizable to unseen sites and populations. This problem was explored in a mega-analysis of previously published datasets from 2,034 AD and comparison participants spanning 27 sites curated by the ENIGMA Addiction Working Group. Data were grouped into a training set used for internal validation including 1,652 participants (692 AD, 24 sites), and a test set used for external validation with 382 participants (146 AD, 3 sites). An exploratory data analysis was first conducted, followed by an evolutionary search based feature selection to site generalizable and high performing subsets of brain measurements. Exploratory data analysis revealed that inclusion of case- and control-only sites led to the inadvertent learning of site-effects. Cross validation methods that do not properly account for site can drastically overestimate results. Evolutionary-based feature selection leveraging leave-one-site-out cross-validation, to combat unintentional learning, identified cortical thickness in the left superior frontal gyrus and right lateral orbitofrontal cortex, cortical surface area in the right transverse temporal gyrus, and left putamen volume as final features. Ridge regression restricted to these features yielded a test-set area under the receiver operating characteristic curve of 0.768. These findings evaluate strategies for handling multi-site data with varied underlying class distributions and identify potential biomarkers for individuals with current AD.

One-year predictions of delayed reward discounting in the adolescent brain cognitive development study.

Delayed reward discounting (DRD) refers to the extent to which an individual devalues a reward based on a temporal delay and is known to be elevated in individuals with substance use disorders and many mental illnesses. DRD has been linked previously with both features of brain structure and function, as well as various behavioral, psychological, and life-history factors. However, there has been little work on the neurobiological and behavioral antecedents of DRD in childhood. This is an important question, as understanding the antecedents of DRD can provide signs of mechanisms in the development of psychopathology. The present study used baseline data from the Adolescent Brain Cognitive Development Study (N = 4,042) to build machine learning models to predict DRD at the first follow-up visit, 1 year later. In separate machine learning models, we tested elastic net regression, random forest regression, light gradient boosting regression, and support vector regression. In five-fold cross-validation on the training set, models using an array of questionnaire/task variables were able to predict DRD, with these findings generalizing to a held-out (i.e., "lockbox") test set of 20% of the sample. Key predictive variables were neuropsychological test performance at baseline, socioeconomic status, screen media activity, psychopathology, parenting, and personality. However, models using magnetic resonance imaging (MRI)-derived brain variables did not reliably predict DRD in either the cross-validation or held-out test set. These results suggest a combination of questionnaire/task variables as antecedents of excessive DRD in late childhood, which may presage the development of problematic substance use in adolescence. (PsycInfo Database Record (c) 2022 APA, all rights reserved).

White matter microstructure differences in individuals with dependence on cocaine, methamphetamine, and nicotine: Findings from the ENIGMA-Addiction working group.

BACKGROUND: Nicotine and illicit stimulants are very addictive substances. Although associations between grey matter and dependence on stimulants have been frequently reported, white matter correlates have received less attention. METHODS: Eleven international sites ascribed to the ENIGMA-Addiction consortium contributed data from individuals with dependence on cocaine (n = 147), methamphetamine (n = 132) and nicotine (n = 189), as well as non-dependent controls (n = 333). We compared the fractional anisotropy (FA), axial diffusivity (AD), radial diffusivity (RD) and mean diffusivity (MD) of 20 bilateral tracts. Also, we compared the performance of various machine learning algorithms in deriving brain-based classifications on stimulant dependence. RESULTS: The cocaine and methamphetamine groups had lower regional FA and higher RD in several association, commissural, and projection white matter tracts. The methamphetamine dependent group additionally showed lower regional AD. The nicotine group had lower FA and higher RD limited to the anterior limb of the internal capsule. The best performing machine learning algorithm was the support vector machine (SVM). The SVM successfully classified individuals with dependence on cocaine (AUC = 0.70, p < 0.001) and methamphetamine (AUC = 0.71, p < 0.001) relative to non-dependent controls. Classifications related to nicotine dependence proved modest (AUC = 0.62, p = 0.014). CONCLUSIONS: Stimulant dependence was related to FA disturbances within tracts consistent with a role in addiction. The multivariate pattern of white matter differences proved sufficient to identify individuals with stimulant dependence, particularly for cocaine and methamphetamine.

Recalibrating expectations about effect size: A multi-method survey of effect sizes in the ABCD study.

Effect sizes are commonly interpreted using heuristics established by Cohen (e.g., small: r = .1, medium r = .3, large r = .5), despite mounting evidence that these guidelines are mis-calibrated to the effects typically found in psychological research. This study's aims were to 1) describe the distribution of effect sizes across multiple instruments, 2) consider factors qualifying the effect size distribution, and 3) identify examples as benchmarks for various effect sizes. For aim one, effect size distributions were illustrated from a large, diverse sample of 9/10-year-old children. This was done by conducting Pearson's correlations among 161 variables representing constructs from all questionnaires and tasks from the Adolescent Brain and Cognitive Development Study® baseline data. To achieve aim two, factors qualifying this distribution were tested by comparing the distributions of effect size among various modifications of the aim one analyses. These modified analytic strategies included comparisons of effect size distributions for different types of variables, for analyses using statistical thresholds, and for analyses using several covariate strategies. In aim one analyses, the median in-sample effect size was .03, and values at the first and third quartiles were .01 and .07. In aim two analyses, effects were smaller for associations across instruments, content domains, and reporters, as well as when covarying for sociodemographic factors. Effect sizes were larger when thresholding for statistical significance. In analyses intended to mimic conditions used in "real-world" analysis of ABCD data, the median in-sample effect size was .05, and values at the first and third quartiles were .03 and .09. To achieve aim three, examples for varying effect sizes are reported from the ABCD dataset as benchmarks for future work in the dataset. In summary, this report finds that empirically determined effect sizes from a notably large dataset are smaller than would be expected based on existing heuristics.

Multimodal brain predictors of current weight and weight gain in children enrolled in the ABCD study ®.

Multimodal neuroimaging assessments were utilized to identify generalizable brain correlates of current body mass index (BMI) and predictors of pathological weight gain (i.e., beyond normative development) one year later. Multimodal data from children enrolled in the Adolescent Brain Cognitive Development Study® at 9-to-10-years-old, consisted of structural magnetic resonance imaging (MRI), diffusion tensor imaging (DTI), resting state (rs), and three task-based functional (f) MRI scans assessing reward processing, inhibitory control, and working memory. Cross-validated elastic-net regression revealed widespread structural associations with BMI (e.g., cortical thickness, surface area, subcortical volume, and DTI), which explained 35% of the variance in the training set and generalized well to the test set (R2 = 0.27). Widespread rsfMRI inter- and intra-network correlations were related to BMI (R2train = 0.21; R2test = 0.14), as were regional activations on the working memory task (R2train = 0.20; (R2test = 0.16). However, reward and inhibitory control tasks were unrelated to BMI. Further, pathological weight gain was predicted by structural features (Area Under the Curve (AUC)train = 0.83; AUCtest = 0.83, p < 0.001), but not by fMRI nor rsfMRI. These results establish generalizable brain correlates of current weight and future pathological weight gain. These results also suggest that sMRI may have particular value for identifying children at risk for pathological weight gain.

Examination of the association between exposure to childhood maltreatment and brain structure in young adults: a machine learning analysis.

Exposure to maltreatment during childhood is associated with structural changes throughout the brain. However, the structural differences that are most strongly associated with maltreatment remain unclear given the limited number of whole-brain studies. The present study used machine learning to identify if and how brain structure distinguished young adults with and without a history of maltreatment. Young adults (ages 18-21, n = 384) completed an assessment of childhood trauma exposure and a structural MRI as part of the IMAGEN study. Elastic net regularized regression was used to identify the structural features that identified those with a history of maltreatment. A generalizable model that included 7 cortical thicknesses, 15 surface areas, and 5 subcortical volumes was identified (area under the receiver operating characteristic curve = 0.71, p < 0.001). Those with a maltreatment history had reduced surface areas and cortical thicknesses primarily in fronto-temporal regions. This group also had larger cortical thicknesses in occipital regions and surface areas in frontal regions. The results suggest childhood maltreatment is associated with multiple measures of structure throughout the brain. The use of a large sample without exposure to adulthood trauma provides further evidence for the unique contribution of childhood trauma to brain structure. The identified regions overlapped with regions associated with psychopathology in adults with maltreatment histories, which offers insights as to how these disorders manifest.

Multimethod investigation of the neurobiological basis of ADHD symptomatology in children aged 9-10: baseline data from the ABCD study.

Attention deficit/hyperactivity disorder is associated with numerous neurocognitive deficits, including poor working memory and difficulty inhibiting undesirable behaviors that cause academic and behavioral problems in children. Prior work has attempted to determine how these differences are instantiated in the structure and function of the brain, but much of that work has been done in small samples, focused on older adolescents or adults, and used statistical approaches that were not robust to model overfitting. The current study used cross-validated elastic net regression to predict a continuous measure of ADHD symptomatology using brain morphometry and activation during tasks of working memory, inhibitory control, and reward processing, with separate models for each MRI measure. The best model using activation during the working memory task to predict ADHD symptomatology had an out-of-sample R2 = 2% and was robust to residualizing the effects of age, sex, race, parental income and education, handedness, pubertal status, and internalizing symptoms from ADHD symptomatology. This model used reduced activation in task positive regions and reduced deactivation in task negative regions to predict ADHD symptomatology. The best model with morphometry alone predicted ADHD symptomatology with an R2 = 1% but this effect dissipated when including covariates. The inhibitory control and reward tasks did not yield generalizable models. In summary, these analyses show, with a large and well-characterized sample, that the brain correlates of ADHD symptomatology are modest in effect size and captured best by brain morphometry and activation during a working memory task.

Brain Predictability toolbox: a Python library for neuroimaging-based machine learning.

SUMMARY: Brain Predictability toolbox (BPt) represents a unified framework of machine learning (ML) tools designed to work with both tabulated data (e.g. brain derived, psychiatric, behavioral and physiological variables) and neuroimaging specific data (e.g. brain volumes and surfaces). This package is suitable for investigating a wide range of different neuroimaging-based ML questions, in particular, those queried from large human datasets. AVAILABILITY AND IMPLEMENTATION: BPt has been developed as an open-source Python 3.6+ package hosted at https://github.com/sahahn/BPt under MIT License, with documentation provided at https://bpt.readthedocs.io/en/latest/, and continues to be actively developed. The project can be downloaded through the github link provided. A web GUI interface based on the same code is currently under development and can be set up through docker with instructions at https://github.com/sahahn/BPt_app.

Neuroanatomical correlates of impulsive traits in children aged 9 to 10.

Impulsivity refers to a set of traits that are generally negatively related to critical domains of adaptive functioning and are core features of numerous psychiatric disorders. The current study examined the gray and white matter correlates of five impulsive traits measured using an abbreviated version of the UPPS-P (Urgency, (lack of) Premeditation, (lack of) Perseverance, Sensation-Seeking, Positive Urgency) impulsivity scale in children aged 9 to 10 (N = 11,052) from the Adolescent Brain and Cognitive Development (ABCD) study. Linear mixed effect models and elastic net regression were used to examine features of regional gray matter and white matter tractography most associated with each UPPS-P scale; intraclass correlations were computed to examine the similarity of the neuroanatomical correlates among the scales. Positive Urgency showed the most robust association with neuroanatomy, with similar but less robust associations found for Negative Urgency. Perseverance showed little association with neuroanatomy. Premeditation and Sensation Seeking showed intermediate associations with neuroanatomy. Critical regions across measures include the dorsolateral prefrontal cortex, lateral temporal cortex, and orbitofrontal cortex; critical tracts included the superior longitudinal fasciculus and inferior fronto-occipital fasciculus. Negative Urgency and Positive Urgency showed the greatest neuroanatomical similarity. Some UPPS-P traits share neuroanatomical correlates, while others have distinct correlates or essentially no relation to neuroanatomy. Neuroanatomy tended to account for relatively little variance in UPPS-P traits (i.e., Model R2 < 1%) and effects were spread throughout the brain, highlighting the importance of well powered samples. (PsycInfo Database Record (c) 2020 APA, all rights reserved).

Investigation of Psychiatric and Neuropsychological Correlates of Default Mode Network and Dorsal Attention Network Anticorrelation in Children.

The default mode network (DMN) and dorsal attention network (DAN) demonstrate an intrinsic "anticorrelation" in healthy adults, which is thought to represent the functional segregation between internally and externally directed thought. Reduced segregation of these networks has been proposed as a mechanism for cognitive deficits that occurs in many psychiatric disorders, but this association has rarely been tested in pre-adolescent children. The current analysis used data from the Adolescent Brain Cognitive Development study to examine the relationship between the strength of DMN/DAN anticorrelation and psychiatric symptoms in the largest sample to date of 9- to 10-year-old children (N = 6543). The relationship of DMN/DAN anticorrelation to a battery of neuropsychological tests was also assessed. DMN/DAN anticorrelation was robustly linked to attention problems, as well as age, sex, and socioeconomic factors. Other psychiatric correlates identified in prior reports were not robustly linked to DMN/DAN anticorrelation after controlling for demographic covariates. Among neuropsychological measures, the clearest correlates of DMN/DAN anticorrelation were the Card Sort task of executive function and cognitive flexibility and the NIH Toolbox Total Cognitive Score, although these did not survive correction for socioeconomic factors. These findings indicate a complicated relationship between DMN/DAN anticorrelation and demographics, neuropsychological function, and psychiatric problems.

Machine deep learning accurately detects endoleak after endovascular abdominal aortic aneurysm repair.

OBJECTIVE: The objective of this study was to develop a machine deep learning algorithm for endoleak detection and measurement of aneurysm diameter, area, and volume from computed tomography angiography (CTA). METHODS: Digital Imaging and Communications in Medicine files representing three-phase postoperative CTA images (N = 334) of 191 unique patients undergoing endovascular aneurysm repair for infrarenal abdominal aortic aneurysm (AAA) with a variety of commercial devices were used to train a deep learning pipeline across four tasks. The RetinaNet object-detection convolutional neural network (CNN) architecture was trained to predict bounding boxes around the axial CTA slices that were then stitched together in two dimensions into a smaller region containing the aneurysm. Multiclass endoleak detection and segmentation of the AAA, endograft, and endoleak were performed on this smaller region. Segmentations on a single randomly selected contrast from each scan included 33 full and 68 partial segmentations for endograft and AAA and 99 full segmentations for endoleak. A modified version of ResNet-50 CNN was used to detect endoleak on individual axial slices. A three-dimensional U-Net CNN model was trained on the task of dense three-dimensional segmentation and used to measure diameter and volume with a specially designed loss function. We made use of fivefold cross-validation to evaluate model performance for each step, splitting training and testing data at each fold, such that multiple scans from the same patient were preserved with the same fold. Algorithm predictions for endoleak were compared with the radiology report and with a subset of CTA images independently read by two vascular specialists. RESULTS: The localization portion of the network accurately predicted a region of interest containing the AAA in 99% of cases. The best model of binary endoleak detection obtained an area under the receiver operating characteristic curve of 0.94 ± 0.03 with an optimized accuracy of 0.89 ± 0.03 on a balanced data set. An introduced postprocessing algorithm for determining maximum diameter was used on both the predicted AAA segmentation and ground truth segmentation, predicting on average an absolute diameter error of 2.3 ± 2.0 mm by 1.4 ± 1.7 mm for each measurement, respectively. The algorithm measured AAA and endograft volume accurately (Dice coefficient, 0.95 ± 0.2) with an absolute volume error of 10.1 ± 9.1 mL. The algorithm measured endoleak volume less accurately, with a Dice score of 0.53 ± 0.21 and an average absolute volume error of 1.2 ± 1.9 mL. CONCLUSIONS: This machine learning algorithm shows promise in augmenting a human's ability to interpret postoperative CTA images and may help improve surveillance after endovascular aneurysm repair. External validation on larger data sets and prospective study are required before the algorithm can be clinically applicable.