Multi-level prediction of substance use: Interaction of white matter integrity, resting-state connectivity and inhibitory control measured repeatedly in every-day life

Substance use disorders are characterized by inhibition deficits related to disrupted connectivity in white matter pathways, leading via interaction to difficulties in resisting substance use. By combining neuroimaging with smartphone-based ecological momentary assessment (EMA), we questioned how biomarkers moderate inhibition deficits to predict use. Thus, we aimed to assess white matter integrity interaction with everyday inhibition deficits and related resting-state network connectivity to identify multi-dimensional predictors of substance use. Thirty-eight patients treated for alcohol, cannabis or tobacco use disorder completed 1 week of EMA to report substance use five times and complete Stroop inhibition testing twice daily. Before EMA tracking, participants underwent resting state functional MRI and diffusion tensor imaging (DTI) scanning. Regression analyses were conducted between mean Stroop performances and whole-brain fractional anisotropy (FA) in white matter. Moderation testing was conducted between mean FA within significant clusters as moderator and the link between momentary Stroop performance and use as outcome. Predictions between FA and resting-state connectivity strength in known inhibition-related networks were assessed using mixed modelling. Higher FA values in the anterior corpus callosum and bilateral anterior corona radiata predicted higher mean Stroop performance during the EMA week and stronger functional connectivity in occipital-frontal-cerebellar regions. Integrity in these regions moderated the link between inhibitory control and substance use, whereby stronger inhibition was predictive of the lowest probability of use for the highest FA values. In conclusion, compromised white matter structural integrity in anterior brain systems appears to underlie impairment in inhibitory control functional networks and compromised ability to refrain from substance use.

Contributions of Cerebral White Matter Hyperintensities to Postural Instability in Aging with and without Alcohol Use Disorder

BACKGROUND

Postural instability and brain white matter hyperintensities (WMH) are both noted markers of normal aging and alcohol use disorder (AUD). Here, we questioned what variables contribute to sway path/WMH relations in individuals with AUD and healthy control participants.

METHOD

The data comprised 404 balance platform sessions, yielding sway path length and MRI acquired cross-sectionally or longitudinally, in 102 control and 158 AUD participants, ages 25-80 years. Balance sessions were typically conducted on the same day as MRI FLAIR acquisitions, permitting WMH volume quantification. Factors considered in multiple regression analyses as potential contributors to relations between WMH volumes and postural instability were age, sex, socioeconomic status, education, pedal 2-point discrimination, systolic and diastolic blood pressure, body mass index, depressive symptoms, total alcohol consumed in the past year, and race.

RESULTS

Initial analysis identified diagnosis, age, sex, and race as significant contributors to observed sway path/WMH relations. Inclusion of these factors as predictors in multiple regression analysis substantially attenuated the sway/WMH relations in both AUD and healthy control groups. Women, irrespective of diagnosis or race, had shorter sway paths than men. Black participants, irrespective of diagnosis or sex, had shorter sway paths than non-Black participants despite having modestly larger WMH volumes than non-Black participants, possibly a reflection of the younger age of the Black sample.

DISCUSSION

Longer sway paths were related to larger WMH volumes in healthy men and women, with and without AUD. Critically, however, age nearly fully accounted for these relations.

Contributions of cerebral white matter hyperintensities, age, and pedal perception to postural sway in people living with HIV

OBJECTIVE

With aging, people living with HIV (PLWH) have diminishing postural stability that increases liability for falls. Factors and neuromechanisms contributing to instability are incompletely known. Brain white matter abnormalities seen as hyperintense (WMH) signals have been considered to underlie instability in normal aging and PLWH. We questioned whether sway-WMH relations endured after accounting for potentially relevant demographic, physiological, and HIV-related variables.

DESIGN

Mixed cross-sectional/longitudinal data acquired over 15 years in 141 PLWH and 102 age-range matched controls, 25-80 years old.

METHODS

Multimodal structural MRI data were quantified for 7 total and regional WMH volumes. Static posturography acquired with a force platform measured sway path length separately with eyes closed and eyes open. Statistical analyses used multiple regression with mixed modeling to test contributions from non-MRI and non-path data on sway path-WMH relations.

RESULTS

In simple correlations, longer sway paths were associated with larger WMH volumes in PWLH and controls. When demographic, physiological, and HIV-related variables were entered into multiple regressions, the sway-WMH relations under both vision conditions in the controls were attenuated when accounting for age and 2-point pedal discrimination. Although the sway-WMH relations in PLWH were influenced by age, 2-point pedal discrimination, and years with HIV infection, the sway-WMH relations endured for 5 of the 7 regions in the eyes-open condition.

CONCLUSIONS

The constellation of age-related increasing instability while standing, degradation of brain white matter integrity, and peripheral pedal neuropathy is indicative of advancing fraility and liability for falls as people age with HIV infection.

Federated learning with knowledge distillation for multi-organ segmentation with partially labeled datasets

The state-of-the-art multi-organ CT segmentation relies on deep learning models, which only generalize when trained on large samples of carefully curated data. However, it is challenging to train a single model that can segment all organs and types of tumors since most large datasets are partially labeled or are acquired across multiple institutes that may differ in their acquisitions. A possible solution is Federated learning, which is often used to train models on multi-institutional datasets where the data is not shared across sites. However, predictions of federated learning can be unreliable after the model is locally updated at sites due to 'catastrophic forgetting'. Here, we address this issue by using knowledge distillation (KD) so that the local training is regularized with the knowledge of a global model and pre-trained organ-specific segmentation models. We implement the models in a multi-head U-Net architecture that learns a shared embedding space for different organ segmentation, thereby obtaining multi-organ predictions without repeated processes. We evaluate the proposed method using 8 publicly available abdominal CT datasets of 7 different organs. Of those datasets, 889 CTs were used for training, 233 for internal testing, and 30 volumes for external testing. Experimental results verified that our proposed method substantially outperforms other state-of-the-art methods in terms of accuracy, inference time, and the number of parameters.

Frontal cortical volume deficits as enduring evidence of childhood abuse in community adults with AUD and HIV infection comorbidity

Background

Childhood abuse is an underappreciated source of stress, associated with adverse mental and physical health consequences. Childhood abuse has been directly associated with risky behavior thereby increasing the likelihood of alcohol misuse and risk of HIV infection, conditions associated with brain structural and functional deficits. Here, we examined the neural and behavioral correlates of childhood trauma history in alcohol use disorder (AUD), HIV infection (HIV), and their comorbidity (AUD+HIV).

Methods

Occurrence of childhood trauma was evaluated by retrospective interview. Cortical (frontal, temporal, parietal, and occipital), subcortical (hippocampus, amygdala), and regional frontal volumes were derived from structural MRI, adjusted for intracranial volume and age. Test scores of executive functioning, attention/working memory, verbal/visual learning, verbal/visual memory, and motor speed functional domains were standardized on age and education of a laboratory control group.

Results

History of childhood abuse was associated with smaller frontal lobe volumes regardless of diagnosis. For frontal subregional volumes, history of childhood abuse was selectively associated with smaller orbitofrontal and supplementary motor volumes. In participants with a child abuse history, poorer verbal/visual memory performance was associated with smaller orbitofrontal and frontal middle volumes, whereas in those without childhood abuse, poorer verbal/visual memory performance was associated with smaller orbitofrontal, frontal superior, and supplemental motor volumes.

Conclusions

Taken together, these results comport with and extend the findings that childhood abuse is associated with brain and behavioral sequelae in AUD, HIV, and AUD+HIV comorbidity. Further, these findings suggest that sequelae of abuse in childhood may be best conceptualized as a spectrum disorder as significant deficits may be present in those who may not meet criteria for a formal trauma-related diagnosis yet may be suffering enduring stress effects on brain structural and functional health.

Age-Accelerated Increase of White Matter Hyperintensity Volumes Is Exacerbated by Heavy Alcohol Use in People Living With HIV

BACKGROUND

Antiretroviral treatment has enabled people living with HIV infection to have a near-normal life span. With longevity comes opportunities for engaging in risky behavior, including initiation of excessive drinking. Given that both HIV infection and alcohol use disorder (AUD) can disrupt brain white matter integrity, we questioned whether HIV infection, even if successfully treated, or AUD alone results in signs of accelerated white matter aging and whether HIV+AUD comorbidity further accelerates brain aging.

METHODS

Longitudinal magnetic resonance imaging-FLAIR data were acquired over a 15-year period from 179 control individuals, 204 participants with AUD, 70 participants with HIV, and 75 participants with comorbid HIV+AUD. White matter hyperintensity (WMH) volumes were quantified and localized, and their functional relevance was examined with cognitive and motor testing.

RESULTS

The 3 diagnostic groups each had larger WMH volumes than the control group. Although all 4 groups exhibited accelerating volume increases with aging, only the HIV groups showed faster WMH enlargement than control individuals; the comorbid group showed faster acceleration than the HIV-only group. Sex and HIV infection length, but not viral suppression status, moderated acceleration. Correlations emerged between WMH volumes and attention/working memory and executive function scores of the AUD and HIV groups and between WMH volumes and motor skills in the 3 diagnostic groups.

CONCLUSIONS

Even treated HIV can show accelerated aging, possibly from treatment sequelae or legacy effects, and notably from AUD comorbidity. WMH volumes may be especially relevant for tracking HIV and AUD brain health because each condition is associated with liability for hypertensive processes, for which WMHs are considered a marker.

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.

Brain Volume in Fetal Alcohol Spectrum Disorders Over a 20-Year Span

Importance

Anomalous brain development and mental health problems are prevalent in fetal alcohol spectrum disorders (FASD), but there is a paucity of longitudinal brain imaging research into adulthood. This study presents long-term follow-up of brain volumetrics in a cohort of participants with FASD.

Objective

To test whether brain tissue declines faster with aging in individuals with FASD compared with control participants.

Design, Setting, and Participants

This cohort study used magnetic resonance imaging (MRI) data collected from individuals with FASD and control individuals (age 13-37 years at first magnetic resonance imaging [MRI1] acquired 1997-2000) compared with data collected 20 years later (MRI2; 2018-2021). Participants were recruited for MRI1 through the University of Washington Fetal Alcohol Syndrome (FAS) Follow-Up Study. For MRI2, former participants were recruited by the University of Washington Fetal Alcohol and Drug Unit. Data were analyzed from October 2022 to August 2023.

Main Outcomes and Measures

Intracranial volume (ICV) and regional cortical and cerebellar gray matter, white matter, and cerebrospinal fluid volumes were quantified automatically and analyzed, with group and sex as between-participant factors and age as a within-participant variable.

Results

Of 174 individuals with MRI1 data, 48 refused participation, 36 were unavailable, and 24 could not be located. The remaining 66 individuals (37.9%) were rescanned for MRI2, including 26 controls, 18 individuals with nondysmorphic heavily exposed fetal alcohol effects (FAE; diagnosed prior to MRI1), and 22 individuals with FAS. Mean (SD) age was 22.9 (5.6) years at MRI1 and 44.7 (6.5) years at MRI2, and 35 participants (53%) were male. The FAE and FAS groups exhibited enduring stepped volume deficits at MRI1 and MRI2; volumes among control participants were greater than among participants with FAE, which were greater than volumes among participants with FAS (eg, mean [SD] ICV: control, 1462.3 [119.3] cc at MRI1 and 1465.4 [129.4] cc at MRI2; FAE, 1375.6 [134.1] cc at MRI1 and 1371.7 [120.3] cc at MRI2; FAS, 1297.3 [163.0] cc at MRI1 and 1292.7 [172.1] cc at MRI2), without diagnosis-by-age interactions. Despite these persistent volume deficits, the FAE participants and FAS participants showed patterns of neurodevelopment within reference ranges: increase in white matter and decrease in gray matter of the cortex and decrease in white matter and increase in gray matter of the cerebellum.

Conclusions and Relevance

The findings of this cohort study support a nonaccelerating enduring, brain structural dysmorphic spectrum following prenatal alcohol exposure and a diagnostic distinction based on the degree of dysmorphia. FASD was not a progressive brain structural disorder by middle age, but whether accelerated decline occurs in later years remains to be determined.

One-shot Federated Learning on Medical Data using Knowledge Distillation with Image Synthesis and Client Model Adaptation

One-shot federated learning (FL) has emerged as a promising solution in scenarios where multiple communication rounds are not practical. Notably, as feature distributions in medical data are less discriminative than those of natural images, robust global model training with FL is non-trivial and can lead to overfitting. To address this issue, we propose a novel one-shot FL framework leveraging Image Synthesis and Client model Adaptation (FedISCA) with knowledge distillation (KD). To prevent overfitting, we generate diverse synthetic images ranging from random noise to realistic images. This approach (i) alleviates data privacy concerns and (ii) facilitates robust global model training using KD with decentralized client models. To mitigate domain disparity in the early stages of synthesis, we design noise-adapted client models where batch normalization statistics on random noise (synthetic images) are updated to enhance KD. Lastly, the global model is trained with both the original and noise-adapted client models via KD and synthetic images. This process is repeated till global model convergence. Extensive evaluation of this design on five small- and three large-scale medical image classification datasets reveals superior accuracy over prior methods. Code is available at https://github.com/myeongkyunkang/FedISCA.

Generating Realistic Brain MRIs via a Conditional Diffusion Probabilistic Model

As acquiring MRIs is expensive, neuroscience studies struggle to attain a sufficient number of them for properly training deep learning models. This challenge could be reduced by MRI synthesis, for which Generative Adversarial Networks (GANs) are popular. GANs, however, are commonly unstable and struggle with creating diverse and high-quality data. A more stable alternative is Diffusion Probabilistic Models (DPMs) with a fine-grained training strategy. To overcome their need for extensive computational resources, we propose a conditional DPM (cDPM) with a memory-efficient process that generates realistic-looking brain MRIs. To this end, we train a 2D cDPM to generate an MRI subvolume conditioned on another subset of slices from the same MRI. By generating slices using arbitrary combinations between condition and target slices, the model only requires limited computational resources to learn interdependencies between slices even if they are spatially far apart. After having learned these dependencies via an attention network, a new anatomy-consistent 3D brain MRI is generated by repeatedly applying the cDPM. Our experiments demonstrate that our method can generate high-quality 3D MRIs that share a similar distribution to real MRIs while still diversifying the training set. The code is available at https://github.com/xiaoiker/mask3DMRI_diffusion and also will be released as part of MONAI, at https://github.com/Project-MONAI/GenerativeModels.

An Explainable Geometric-Weighted Graph Attention Network for Identifying Functional Networks Associated with Gait Impairment

One of the hallmark symptoms of Parkinson's Disease (PD) is the progressive loss of postural reflexes, which eventually leads to gait difficulties and balance problems. Identifying disruptions in brain function associated with gait impairment could be crucial in better understanding PD motor progression, thus advancing the development of more effective and personalized therapeutics. In this work, we present an explainable, geometric, weighted-graph attention neural network (xGW-GAT) to identify functional networks predictive of the progression of gait difficulties in individuals with PD. xGW-GAT predicts the multi-class gait impairment on the MDS-Unified PD Rating Scale (MDS-UPDRS). Our computational- and data-efficient model represents functional connectomes as symmetric positive definite (SPD) matrices on a Riemannian manifold to explicitly encode pairwise interactions of entire connectomes, based on which we learn an attention mask yielding individual- and group-level explainability. Applied to our resting-state functional MRI (rs-fMRI) dataset of individuals with PD, xGW-GAT identifies functional connectivity patterns associated with gait impairment in PD and offers interpretable explanations of functional subnetworks associated with motor impairment. Our model successfully outperforms several existing methods while simultaneously revealing clinically-relevant connectivity patterns. The source code is available at https://github.com/favour-nerrise/xGW-GAT.

LSOR: Longitudinally-Consistent Self-Organized Representation Learning

Interpretability is a key issue when applying deep learning models to longitudinal brain MRIs. One way to address this issue is by visualizing the high-dimensional latent spaces generated by deep learning via self-organizing maps (SOM). SOM separates the latent space into clusters and then maps the cluster centers to a discrete (typically 2D) grid preserving the high-dimensional relationship between clusters. However, learning SOM in a high-dimensional latent space tends to be unstable, especially in a self-supervision setting. Furthermore, the learned SOM grid does not necessarily capture clinically interesting information, such as brain age. To resolve these issues, we propose the first self-supervised SOM approach that derives a high-dimensional, interpretable representation stratified by brain age solely based on longitudinal brain MRIs (i.e., without demographic or cognitive information). Called Longitudinally-consistent Self-Organized Representation learning (LSOR), the method is stable during training as it relies on soft clustering (vs. the hard cluster assignments used by existing SOM). Furthermore, our approach generates a latent space stratified according to brain age by aligning trajectories inferred from longitudinal MRIs to the reference vector associated with the corresponding SOM cluster. When applied to longitudinal MRIs of the Alzheimer's Disease Neuroimaging Initiative (ADNI, N = 632 ), LSOR generates an interpretable latent space and achieves comparable or higher accuracy than the state-of-the-art representations with respect to the downstream tasks of classification (static vs. progressive mild cognitive impairment) and regression (determining ADAS-Cog score of all subjects). The code is available at https://github.com/ouyangjiahong/longitudinal-som-single-modality.

White matter microstructural integrity continues to develop from adolescence to young adulthood in mice and humans: Same phenotype, different mechanism

As direct evaluation of a mouse model of human neurodevelopment, adolescent and young adult mice and humans underwent MR diffusion tensor imaging to quantify age-related differences in microstructural integrity of brain white matter fibers. Fractional anisotropy (FA) was greater in older than younger mice and humans. Despite the cross-species commonality, the underlying developmental mechanism differed: whereas evidence for greater axonal extension contributed to higher FA in older mice, evidence for continuing myelination contributed to higher FA in human adolescent development. These differences occurred in the context of species distinctions in overall brain growth: whereas the continued growth of the brain and skull in the murine model can accommodate volume expansion into adulthood, human white matter volume and myelination continue growth into adulthood within a fixed intracranial volume. Appreciation of the similarities and differences in developmental mechanism can enhance the utility of animal models of brain white matter structure, function, and response to exogenous manipulation.

An Explainable Geometric-Weighted Graph Attention Network for Identifying Functional Networks Associated with Gait Impairment

One of the hallmark symptoms of Parkinson's Disease (PD) is the progressive loss of postural reflexes, which eventually leads to gait difficulties and balance problems. Identifying disruptions in brain function associated with gait impairment could be crucial in better understanding PD motor progression, thus advancing the development of more effective and personalized therapeutics. In this work, we present an explainable, geometric, weighted-graph attention neural network (xGW-GAT) to identify functional networks predictive of the progression of gait difficulties in individuals with PD. xGW-GAT predicts the multi-class gait impairment on the MDS-Unified PD Rating Scale (MDS-UPDRS). Our computational- and data-efficient model represents functional connectomes as symmetric positive definite (SPD) matrices on a Riemannian manifold to explicitly encode pairwise interactions of entire connectomes, based on which we learn an attention mask yielding individual- and group-level explain-ability. Applied to our resting-state functional MRI (rs-fMRI) dataset of individuals with PD, xGW-GAT identifies functional connectivity patterns associated with gait impairment in PD and offers interpretable explanations of functional subnetworks associated with motor impairment. Our model successfully outperforms several existing methods while simultaneously revealing clinically-relevant connectivity patterns. The source code is available at https://github.com/favour-nerrise/xGW-GAT.

Postural instability in HIV infection: relation to central and peripheral nervous system markers

OBJECTIVES

Determine the independent contributions of central nervous system (CNS) and peripheral nervous system (PNS) metrics to balance instability in people with HIV (PWH) compared with people without HIV (PWoH).

METHODS

Volumetric MRI (CNS) and two-point pedal discrimination (PNS) were tested as substrates of stance instability measured with balance platform posturography.

DESIGN

125 PWH and 88 PWoH underwent balance testing and brain MRI.

RESULTS

The PWH exhibited stability deficits that were disproportionately greater with eyes closed than eyes open compared with PWoH. Further analyses revealed that greater postural imbalance measured as longer sway paths correlated with smaller cortical and cerebellar lobular brain volumes known to serve sensory integration; identified brain/sway path relations endured after accounting for contributions from physiological and disease factors as potential moderators; and multiple regression identified PNS and CNS metrics as independent predictors of postural instability in PWH that differed with the use of visual information to stabilize balance. With eyes closed, temporal volumes and two-point pedal discrimination were significant independent predictors of sway; with eyes open, occipital volume was an additional predictor of sway. These relations were selective to PWH and were not detected in PWoH.

CONCLUSION

CNS and PNS factors were independent contributors to postural instability in PWH. Recognizing that myriad inputs must be detected by peripheral systems and brain networks to integrate sensory and musculoskeletal information for maintenance of postural stability, age- or disease-related degradation of either or both nervous systems may contribute to imbalance and liability for falls.

Brain volumetrics differ by Fiebig stage in acute HIV infection

OBJECTIVE

People with chronic HIV exhibit lower regional brain volumes compared to people without HIV (PWOH). Whether imaging alterations observed in chronic infection occur in acute HIV infection (AHI) remains unknown.

DESIGN

Cross-sectional study of Thai participants with AHI.

METHODS

One hundred and twelve Thai males with AHI (age 20-46) and 18 male Thai PWOH (age 18-40) were included. Individuals with AHI were stratified into early (Fiebig I-II; n  = 32) and late (Fiebig III-V; n  = 80) stages of acute infection using validated assays. T1-weighted scans were acquired using a 3 T MRI performed within five days of antiretroviral therapy (ART) initiation. Volumes for the amygdala, caudate nucleus, hippocampus, nucleus accumbens, pallidum, putamen, and thalamus were compared across groups.

RESULTS

Participants in late Fiebig stages exhibited larger volumes in the nucleus accumbens (8% larger; P  = 0.049) and putamen (19%; P  < 0.001) when compared to participants in the early Fiebig. Compared to PWOH, participants in late Fiebig exhibited larger volumes of the amygdala (9% larger; P  = 0.002), caudate nucleus (11%; P  = 0.005), nucleus accumbens (15%; P  = 0.004), pallidum (19%; P  = 0.001), and putamen (31%; P  < 0.001). Brain volumes in the nucleus accumbens, pallidum, and putamen correlated modestly with stimulant use over the past four months among late Fiebig individuals ( P s < 0.05).

CONCLUSIONS

Findings indicate that brain volume alterations occur in acute infection, with the most prominent differences evident in the later stages of AHI. Additional studies are needed to evaluate mechanisms for possible brain disruption following ART, including viral factors and markers of neuroinflammation.

Episodic memory deficit in HIV infection: common phenotype with Parkinson's disease, different neural substrates

Episodic memory deficits occur in people living with HIV (PLWH) and individuals with Parkinson's disease (PD). Given known effects of HIV and PD on frontolimbic systems, episodic memory deficits are often attributed to executive dysfunction. Although executive dysfunction, evidenced as retrieval deficits, is relevant to mnemonic deficits, learning deficits may also contribute. Here, the California Verbal Learning Test-II, administered to 42 PLWH, 41 PD participants, and 37 controls, assessed learning and retrieval using measures of free recall, cued recall, and recognition. Executive function was assessed with a composite score comprising Stroop Color-Word Reading and Backward Digit Spans. Neurostructural correlates were examined with MRI of frontal (precentral, superior, orbital, middle, inferior, supplemental motor, medial) and limbic (hippocampus, thalamus) volumes. HIV and PD groups were impaired relative to controls on learning and free and cued recall trials but did not differ on recognition or retention of learned material. In no case did executive functioning solely account for the observed mnemonic deficits or brain-performance relations. Critically, the shared learning and retrieval deficits in HIV and PD were related to different substrates of frontolimbic mnemonic neurocircuitry. Specifically, diminished learning and poorer free and cued recall were related to smaller orbitofrontal volume in PLWH but not PD, whereas diminished learning in PD but not PLWH was related to smaller frontal superior volume. In PD, poorer recognition correlated with smaller thalamic volume and poorer retention to hippocampal volume. Although memory deficits were similar, the neural correlates in HIV and PD suggest different pathogenic mechanisms.

Risk for depression tripled during the COVID-19 pandemic in emerging adults followed for the last 8 years

BACKGROUND

The coronavirus disease 2019 (COVID-19) pandemic has significantly increased depression rates, particularly in emerging adults. The aim of this study was to examine longitudinal changes in depression risk before and during COVID-19 in a cohort of emerging adults in the U.S. and to determine whether prior drinking or sleep habits could predict the severity of depressive symptoms during the pandemic.

METHODS

Participants were 525 emerging adults from the National Consortium on Alcohol and NeuroDevelopment in Adolescence (NCANDA), a five-site community sample including moderate-to-heavy drinkers. Poisson mixed-effect models evaluated changes in the Center for Epidemiological Studies Depression Scale (CES-D-10) from before to during COVID-19, also testing for sex and age interactions. Additional analyses examined whether alcohol use frequency or sleep duration measured in the last pre-COVID assessment predicted pandemic-related increase in depressive symptoms.

RESULTS

The prevalence of risk for clinical depression tripled due to a substantial and sustained increase in depressive symptoms during COVID-19 relative to pre-COVID years. Effects were strongest for younger women. Frequent alcohol use and short sleep duration during the closest pre-COVID visit predicted a greater increase in COVID-19 depressive symptoms.

CONCLUSIONS

The sharp increase in depression risk among emerging adults heralds a public health crisis with alarming implications for their social and emotional functioning as this generation matures. In addition to the heightened risk for younger women, the role of alcohol use and sleep behavior should be tracked through preventive care aiming to mitigate this looming mental health crisis.

Machine Learning Approaches to Understand Cognitive Phenotypes in People With HIV

Cognitive disorders are prevalent in people with HIV (PWH) despite antiretroviral therapy. Given the heterogeneity of cognitive disorders in PWH in the current era and evidence that these disorders have different etiologies and risk factors, scientific rationale is growing for using data-driven models to identify biologically defined subtypes (biotypes) of these disorders. Here, we discuss the state of science using machine learning to understand cognitive phenotypes in PWH and their associated comorbidities, biological mechanisms, and risk factors. We also discuss methods, example applications, challenges, and what will be required from the field to successfully incorporate machine learning in research on cognitive disorders in PWH. These topics were discussed at the National Institute of Mental Health meeting on "Biotypes of CNS Complications in People Living with HIV" held in October 2021. These ongoing research initiatives seek to explain the heterogeneity of cognitive phenotypes in PWH and their associated biological mechanisms to facilitate clinical management and tailored interventions.

The distortions of the free water model for diffusion MRI data when assuming single compartment relaxometry and proton density

Objective.To document the bias of thesimplifiedfree water model of diffusion MRI (dMRI) signal vis-à-vis aspecificmodel which, in addition to diffusion, incorporates compartment-specific proton density (PD), T1 recovery during repetition time (TR), and T2 decay during echo time (TE).Approach.Both models assume that volume fractionfof the total signal in any voxel arises from the free water compartment (fw) such as cerebrospinal fluid or edema, and the remainder (1-f) from hindered water (hw) which is constrained by cellular structures such as white matter (WM). Thespecificandsimplifiedmodels are compared on a synthetic dataset, using a range of PD, T1 and T2 values. We then fit the models to anin vivohealthy brain dMRI dataset. For bothsyntheticandin vivodata we use experimentally feasible TR, TE, signal-to-noise ratio (SNR) and physiologically plausible diffusion profiles.Main results.From the simulations we see that the difference between the estimatedsimplified fandspecific fis largest for mid-range ground-truthf, and it increases as SNR increases. The estimation of volume fractionfis sensitive to the choice of model,simplifiedorspecific, but the estimated diffusion parameters are robust to small perturbations in the simulation.Specific fis more accurate and precise thansimplified f. In the white matter (WM) regions of thein vivoimages,specific fis lower thansimplified f.Significance.In dMRI models for free water, accounting for compartment specific PD, T1 and T2, in addition to diffusion, improves the estimation of model parameters. This extra model specification attenuates the estimation bias of compartmental volume fraction without affecting the estimation of other diffusion parameters.

Imputing Brain Measurements Across Data Sets via Graph Neural Networks

Publicly available data sets of structural MRIs might not contain specific measurements of brain Regions of Interests (ROIs) that are important for training machine learning models. For example, the curvature scores computed by Freesurfer are not released by the Adolescent Brain Cognitive Development (ABCD) Study. One can address this issue by simply reapplying Freesurfer to the data set. However, this approach is generally computationally and labor intensive (e.g., requiring quality control). An alternative is to impute the missing measurements via a deep learning approach. However, the state-of-the-art is designed to estimate randomly missing values rather than entire measurements. We therefore propose to re-frame the imputation problem as a prediction task on another (public) data set that contains the missing measurements and shares some ROI measurements with the data sets of interest. A deep learning model is then trained to predict the missing measurements from the shared ones and afterwards is applied to the other data sets. Our proposed algorithm models the dependencies between ROI measurements via a graph neural network (GNN) and accounts for demographic differences in brain measurements (e.g. sex) by feeding the graph encoding into a parallel architecture. The architecture simultaneously optimizes a graph decoder to impute values and a classifier in predicting demographic factors. We test the approach, called Demographic Aware Graph-based Imputation (DAGI), on imputing those missing Freesurfer measurements of ABCD (N=3760; minimum age 12 years) by training the predictor on those publicly released by the National Consortium on Alcohol and Neurodevelopment in Adolescence (NCANDA, N=540). 5-fold cross-validation on NCANDA reveals that the imputed scores are more accurate than those generated by linear regressors and deep learning models. Adding them also to a classifier trained in identifying sex results in higher accuracy than only using those Freesurfer scores provided by ABCD.

Alcohol Use Disorder and Its Comorbidity With HIV Infection Disrupts Anterior Cingulate Cortex Functional Connectivity

BACKGROUND

Individuals with alcohol use disorder (AUD) have a heightened risk of contracting HIV infection. The effects of these two diseases and their comorbidity on brain structure have been well described, but their effects on brain function have never been investigated at the scale of whole-brain connectomes.

METHODS

In contrast with prior studies that restricted analyses to specific brain networks or examined relatively small groups of participants, our analyses are based on whole-brain functional connectomes of 292 participants.

RESULTS

Relative to participants without AUD, the functional connectivity between the anterior cingulate cortex and orbitofrontal cortex was lower for participants with AUD. Compared with participants without AUD+HIV comorbidity, the functional connectivity between the anterior cingulate cortex and hippocampus was lower for the AUD+HIV participants. Compromised connectivity between these pairs was significantly correlated with greater total lifetime alcohol consumption; the effects of total lifetime alcohol consumption on executive functioning were significantly mediated by the functional connectivity between the pairs.

CONCLUSIONS

Taken together, our results suggest that the functional connectivity of the anterior cingulate cortex is disrupted in individuals with AUD alone and AUD with HIV infection comorbidity. Moreover, the affected connections are associated with deficits in executive functioning, including heightened impulsiveness.

Disentangling Normal Aging From Severity of Disease via Weak Supervision on Longitudinal MRI

The continuous progression of neurological diseases are often categorized into conditions according to their severity. To relate the severity to changes in brain morphometry, there is a growing interest in replacing these categories with a continuous severity scale that longitudinal MRIs are mapped onto via deep learning algorithms. However, existing methods based on supervised learning require large numbers of samples and those that do not, such as self-supervised models, fail to clearly separate the disease effect from normal aging. Here, we propose to explicitly disentangle those two factors via weak-supervision. In other words, training is based on longitudinal MRIs being labelled either normal or diseased so that the training data can be augmented with samples from disease categories that are not of primary interest to the analysis. We do so by encouraging trajectories of controls to be fully encoded by the direction associated with brain aging. Furthermore, an orthogonal direction linked to disease severity captures the residual component from normal aging in the diseased cohort. Hence, the proposed method quantifies disease severity and its progression speed in individuals without knowing their condition. We apply the proposed method on data from the Alzheimer's Disease Neuroimaging Initiative (ADNI, N =632 ). We then show that the model properly disentangled normal aging from the severity of cognitive impairment by plotting the resulting disentangled factors of each subject and generating simulated MRIs for a given chronological age and condition. Moreover, our representation obtains higher balanced accuracy when used for two downstream classification tasks compared to other pre-training approaches. The code for our weak-supervised approach is available at https://github.com/ouyangjiahong/longitudinal-direction-disentangle.

Multi-atlas thalamic nuclei segmentation on standard T1-weighed MRI with application to normal aging

Specific thalamic nuclei are implicated in healthy aging and age-related neurodegenerative diseases. However, few methods are available for robust automated segmentation of thalamic nuclei. The threefold aims of this study were to validate the use of a modified thalamic nuclei segmentation method on standard T1 MRI data, to apply this method to quantify age-related volume declines, and to test functional meaningfulness by predicting performance on motor testing. A modified version of THalamus Optimized Multi-Atlas Segmentation (THOMAS) generated 22 unilateral thalamic nuclei. For validation, we compared nuclear volumes obtained from THOMAS parcellation of white-matter-nulled (WMn) MRI data to T1 MRI data in 45 participants. To examine the effects of age/sex on thalamic nuclear volumes, T1 MRI available from a second data set of 121 men and 117 women, ages 20-86 years, were segmented using THOMAS. To test for functional ramifications, composite regions and constituent nuclei were correlated with Grooved Pegboard test scores. THOMAS on standard T1 data showed significant quantitative agreement with THOMAS from WMn data, especially for larger nuclei. Sex differences revealing larger volumes in men than women were accounted for by adjustment with supratentorial intracranial volume (sICV). Significant sICV-adjusted correlations between age and thalamic nuclear volumes were detected in 20 of the 22 unilateral nuclei and whole thalamus. Composite Posterior and Ventral regions and Ventral Anterior/Pulvinar nuclei correlated selectively with higher scores from the eye-hand coordination task. These results support the use of THOMAS for standard T1-weighted data as adequately robust for thalamic nuclear parcellation.

Bridging the Gap between Deep Learning and Hypothesis-Driven Analysis via Permutation Testing

A fundamental approach in neuroscience research is to test hypotheses based on neuropsychological and behavioral measures, i.e., whether certain factors (e.g., related to life events) are associated with an outcome (e.g., depression). In recent years, deep learning has become a potential alternative approach for conducting such analyses by predicting an outcome from a collection of factors and identifying the most "informative" ones driving the prediction. However, this approach has had limited impact as its findings are not linked to statistical significance of factors supporting hypotheses. In this article, we proposed a flexible and scalable approach based on the concept of permutation testing that integrates hypothesis testing into the data-driven deep learning analysis. We apply our approach to the yearly self-reported assessments of 621 adolescent participants of the National Consortium of Alcohol and Neurodevelopment in Adolescence (NCANDA) to predict negative valence, a symptom of major depressive disorder according to the NIMH Research Domain Criteria (RDoC). Our method successfully identifies categories of risk factors that further explain the symptom.

GaitForeMer: Self-Supervised Pre-Training of Transformers via Human Motion Forecasting for Few-Shot Gait Impairment Severity Estimation

Parkinson's disease (PD) is a neurological disorder that has a variety of observable motor-related symptoms such as slow movement, tremor, muscular rigidity, and impaired posture. PD is typically diagnosed by evaluating the severity of motor impairments according to scoring systems such as the Movement Disorder Society Unified Parkinson's Disease Rating Scale (MDS-UPDRS). Automated severity prediction using video recordings of individuals provides a promising route for non-intrusive monitoring of motor impairments. However, the limited size of PD gait data hinders model ability and clinical potential. Because of this clinical data scarcity and inspired by the recent advances in self-supervised large-scale language models like GPT-3, we use human motion forecasting as an effective self-supervised pre-training task for the estimation of motor impairment severity. We introduce GaitForeMer, Gait Forecasting and impairment estimation transforMer, which is first pre-trained on public datasets to forecast gait movements and then applied to clinical data to predict MDS-UPDRS gait impairment severity. Our method outperforms previous approaches that rely solely on clinical data by a large margin, achieving an F1 score of 0.76, precision of 0.79, and recall of 0.75. Using GaitForeMer, we show how public human movement data repositories can assist clinical use cases through learning universal motion representations. The code is available at https://github.com/markendo/GaitForeMer.

Joint Graph Convolution for Analyzing Brain Structural and Functional Connectome

The white-matter (micro-)structural architecture of the brain promotes synchrony among neuronal populations, giving rise to richly patterned functional connections. A fundamental problem for systems neuroscience is determining the best way to relate structural and functional networks quantified by diffusion tensor imaging and resting-state functional MRI. As one of the state-of-the-art approaches for network analysis, graph convolutional networks (GCN) have been separately used to analyze functional and structural networks, but have not been applied to explore inter-network relationships. In this work, we propose to couple the two networks of an individual by adding inter-network edges between corresponding brain regions, so that the joint structure-function graph can be directly analyzed by a single GCN. The weights of inter-network edges are learnable, reflecting non-uniform structure-function coupling strength across the brain. We apply our Joint-GCN to predict age and sex of 662 participants from the public dataset of the National Consortium on Alcohol and Neurodevelopment in Adolescence (NCANDA) based on their functional and micro-structural white-matter networks. Our results support that the proposed Joint-GCN outperforms existing multi-modal graph learning approaches for analyzing structural and functional networks.

Multiple Instance Neuroimage Transformer

For the first time, we propose using a multiple instance learning based convolution-free transformer model, called Multiple Instance Neuroimage Transformer (MINiT), for the classification of T1-weighted (T1w) MRIs. We first present several variants of transformer models adopted for neuroimages. These models extract non-overlapping 3D blocks from the input volume and perform multi-headed self-attention on a sequence of their linear projections. MINiT, on the other hand, treats each of the non-overlapping 3D blocks of the input MRI as its own instance, splitting it further into non-overlapping 3D patches, on which multi-headed self-attention is computed. As a proof-of-concept, we evaluate the efficacy of our model by training it to identify sex from T1w-MRIs of two public datasets: Adolescent Brain Cognitive Development (ABCD) and the National Consortium on Alcohol and Neurodevelopment in Adolescence (NCANDA). The learned attention maps highlight voxels contributing to identifying sex differences in brain morphometry. The code is available at https://github.com/singlaayush/MINIT.

Earlier Bedtime and Effective Coping Skills Predict a Return to Low-Risk of Depression in Young Adults during the COVID-19 Pandemic

To determine the persistent effects of the pandemic on mental health in young adults, we categorized depressive symptom trajectories and sought factors that promoted a reduction in depressive symptoms in high-risk individuals. Specifically, longitudinal analysis investigated changes in the risk for depression before and during the pandemic until December 2021 in 399 young adults (57% female; age range: 22.8 ± 2.6 years) in the United States (U.S.) participating in the National Consortium on Alcohol and NeuroDevelopment in Adolescence (NCANDA) study. The Center for Epidemiologic Studies Depression Scale (CES-D-10) was administered multiple times before and during the pandemic. A score ≥10 identified individuals at high-risk for depression. Self-reported sleep behavior, substance use, and coping skills at the start of the pandemic were assessed as predictors for returning to low-risk levels while controlling for demographic factors. The analysis identified four trajectory groups regarding depression risk, with 38% being at low-risk pre-pandemic through 2021, 14% showing persistent high-risk pre-pandemic through 2021, and the remainder converting to high-risk either in June 2020 (30%) or later (18%). Of those who became high-risk in June 2020, 51% were no longer at high-risk in 2021. Logistic regression revealed that earlier bedtime and, for the older participants (mid to late twenties), better coping skills were associated with this declining risk. Results indicate divergence in trajectories of depressive symptoms, with a considerable number of young adults developing persistent depressive symptoms. Healthy sleep behavior and specific coping skills have the potential to promote remittance from depressive symptoms in the context of the pandemic.

Did the acute impact of the COVID-19 pandemic on drinking or nicotine use persist? Evidence from a cohort of emerging adults followed for up to nine years

OBJECTIVE

This study examined the impact of the COVID-19 pandemic on drinking and nicotine use through June of 2021 in a community-based sample of young adults.

METHOD

Data were from 348 individuals (49% female) enrolled in a long-term longitudinal study with an accelerated longitudinal design: the National Consortium on Alcohol and Neurodevelopment in Adolescence (NCANDA) Study. Individuals completed pre-pandemic assessments biannually from 2016 to early 2020, then completed up to three web-based, during-pandemic surveys in June 2020, December 2020, and June 2021. Assessments when individuals were 18.8-22.4 years old (N = 1,458) were used to compare drinking and nicotine use pre-pandemic vs. at each of the three during-pandemic timepoints, adjusting for the age-related increases expected over time.

RESULTS

Compared to pre-pandemic, participants were less likely to report past-month drinking in June or December 2020, but there was an increase in drinking days among drinkers in June 2020. By June 2021, both the prevalence of past-month drinking and number of drinking days among drinks were similar to pre-pandemic levels. On average, there were no statistically significant differences between pre-pandemic and during-pandemic time points for binge drinking, typical drinking quantity, or nicotine use. Young adults who reported an adverse financial impact of the pandemic showed increased nicotine use while their peers showed stable or decreased nicotine use.

CONCLUSION

Initial effects of the pandemic on alcohol use faded by June 2021, and on average there was little effect of the pandemic on nicotine use.

Self-supervised learning of neighborhood embedding for longitudinal MRI

In recent years, several deep learning models recommend first to represent Magnetic Resonance Imaging (MRI) as latent features before performing a downstream task of interest (such as classification or regression). The performance of the downstream task generally improves when these latent representations are explicitly associated with factors of interest. For example, we derived such a representation for capturing brain aging by applying self-supervised learning to longitudinal MRIs and then used the resulting encoding to automatically identify diseases accelerating the aging of the brain. We now propose a refinement of this representation by replacing the linear modeling of brain aging with one that is consistent in local neighborhoods in the latent space. Called Longitudinal Neighborhood Embedding (LNE), we derive an encoding so that neighborhoods are age-consistent (i.e., brain MRIs of different subjects with similar brain ages are in close proximity of each other) and progression-consistent, i.e., the latent space is defined by a smooth trajectory field where each trajectory captures changes in brain ages between a pair of MRIs extracted from a longitudinal sequence. To make the problem computationally tractable, we further propose a strategy for mini-batch sampling so that the resulting local neighborhoods accurately approximate the ones that would be defined based on the whole cohort. We evaluate LNE on three different downstream tasks: (1) to predict chronological age from T1-w MRI of 274 healthy subjects participating in a study at SRI International; (2) to distinguish Normal Control (NC) from Alzheimer's Disease (AD) and stable Mild Cognitive Impairment (sMCI) from progressive Mild Cognitive Impairment (pMCI) based on T1-w MRI of 632 participants of the Alzheimer's Disease Neuroimaging Initiative (ADNI); and (3) to distinguish no-to-low from moderate-to-heavy alcohol drinkers based on fractional anisotropy derived from diffusion tensor MRIs of 764 adolescents recruited by the National Consortium on Alcohol and NeuroDevelopment in Adolescence (NCANDA). Across the three data sets, the visualization of the smooth trajectory vector fields and superior accuracy on downstream tasks demonstrate the strength of the proposed method over existing self-supervised methods in extracting information related to brain aging, which could help study the impact of substance use and neurodegenerative disorders. The code is available at https://github.com/ouyangjiahong/longitudinal-neighbourhood-embedding.

Prior test experience confounds longitudinal tracking of adolescent cognitive and motor development

Background

Accurate measurement of trajectories in longitudinal studies, considered the gold standard method for tracking functional growth during adolescence, decline in aging, and change after head injury, is subject to confounding by testing experience.

Methods

We measured change in cognitive and motor abilities over four test sessions (baseline and three annual assessments) in 154 male and 165 female participants (baseline age 12–21 years) from the National Consortium on Alcohol and NeuroDevelopment in Adolescence (NCANDA) study. At each of the four test sessions, these participants were given a test battery using computerized administration and traditional pencil and paper tests that yielded accuracy and speed measures for multiple component cognitive (Abstraction, Attention, Emotion, Episodic memory, Working memory, and General Ability) and motor (Ataxia and Speed) functions. The analysis aim was to dissociate neurodevelopment from testing experience by using an adaptation of the twice-minus-once tested method, which calculated the difference between longitudinal change (comprising developmental plus practice effects) and practice-free initial cross-sectional performance for each consecutive pairs of test sessions. Accordingly, the first set of analyses quantified the effects of learning (i.e., prior test experience) on accuracy and after speed domain scores. Then developmental effects were  determined for each domain for accuracy and speed having removed the measured learning effects.

Results

The greatest gains in performance occurred between the first and second sessions, especially in younger participants, regardless of sex, but practice gains continued to accrue thereafter for several functions. For all 8 accuracy composite scores, the developmental effect after accounting for learning was significant across age and was adequately described by linear fits. The learning-adjusted developmental effects for speed were adequately described by linear fits for Abstraction, Emotion, Episodic Memory, General Ability, and Motor scores, although a nonlinear fit was better for Attention, Working Memory, and Average Speed scores.

Conclusion

Thus, what appeared as accelerated cognitive and motor development was, in most cases, attributable to learning. Recognition of the substantial influence of prior testing experience is critical for accurate characterization of normal development and for developing norms for clinical neuropsychological investigations of conditions affecting the brain.

The Pandemic's Toll on Young Adolescents: Prevention and Intervention Targets to Preserve Their Mental Health

PURPOSE

Adolescence is characterized by dramatic physical, social, and emotional changes, making teens particularly vulnerable to the mental health effects of the COVID-19 pandemic. This longitudinal study identifies young adolescents who are most vulnerable to the psychological toll of the pandemic and provides insights to inform strategies to help adolescents cope better in times of crisis.

METHODS

A data-driven approach was applied to a longitudinal, demographically diverse cohort of more than 3,000 young adolescents (11-14 years) participating in the ongoing Adolescent Brain Cognitive Development Study in the United States, including multiple prepandemic visits and three assessments during the COVID-19 pandemic (May-August 2020). We fitted machine learning models and provided a comprehensive list of predictors of psychological distress in individuals.

RESULTS

Positive affect, stress, anxiety, and depressive symptoms were accurately detected with our classifiers. Female sex and prepandemic internalizing symptoms and sleep problems were strong predictors of psychological distress. Parent- and youth-reported pandemic-related psychosocial factors, including poorer quality and functioning of family relationships, more screen time, and witnessing discrimination in relation to the pandemic further predicted youth distress. However, better social support, regular physical activities, coping strategies, and healthy behaviors predicted better emotional well-being.

DISCUSSION

Findings highlight the importance of social connectedness and healthy behaviors, such as sleep and physical activity, as buffering factors against the deleterious effects of the pandemic on adolescents' mental health. They also point to the need for greater attention toward coping strategies that help the most vulnerable adolescents, particularly girls and those with prepandemic psychological problems.

Growth trajectories of cognitive and motor control in adolescence: How much is development and how much is practice?

OBJECTIVE

Executive control continues to develop throughout adolescence and is vulnerable to alcohol use. Although longitudinal assessment is ideal for tracking executive function development and onset of alcohol use, prior testing experience must be distinguished from developmental trajectories.

METHOD

We used the Stroop Match-to-Sample task to examine the improvement of processing speed and specific cognitive and motor control over 4 years in 445 adolescents. The twice-minus-once-tested method was used and expanded to four test sessions to delineate prior experience (i.e., learning) from development. A General Additive Model evaluated the predictive value of age and sex on executive function development and potential influences of alcohol use on development.

RESULTS

Results revealed strong learning between the first two assessments. Adolescents significantly improved their speed processing over 4 years. Compared with boys, girls enhanced ability to control cognitive interference and motor reactions. Finally, the influence of alcohol use initiation was tested over 4 years for development in 110 no/low, 110 moderate/heavy age- and sex-matched drinkers; alcohol effects were not detected in the matched groups.

CONCLUSIONS

Estimation of learning effects is crucial for examining developmental changes longitudinally. (PsycInfo Database Record (c) 2022 APA, all rights reserved).

Multi-label, multi-domain learning identifies compounding effects of HIV and cognitive impairment

Older individuals infected by Human Immunodeficiency Virus (HIV) are at risk for developing HIV-Associated Neurocognitive Disorder (HAND), i.e., from reduced cognitive functioning similar to HIV-negative individuals with Mild Cognitive Impairment (MCI) or to Alzheimer's Disease (AD) if more severely affected. Incompletely understood is how brain structure can serve to differentiate cognitive impairment (CI) in the HIV-positive (i.e., HAND) from the HIV-negative cohort (i.e., MCI and AD). To that end, we designed a multi-label classifier that labels the structural magnetic resonance images (MRI) of individuals by their HIV and CI status via two binary variables. Proper training of such an approach traditionally requires well-curated datasets containing large number of samples for each of the corresponding four cohorts (healthy controls, CI HIV-negative adults a.k.a. CI-only, HIV-positive patients without CI a.k.a. HIV-only, and HAND). Because of the rarity of such datasets, we proposed to improve training of the multi-label classifier via a multi-domain learning scheme that also incorporates domain-specific classifiers on auxiliary single-label datasets specific to either binary label. Specifically, we complement the training dataset of MRIs of the four cohorts (Control: 156, CI-only: 335, HIV-only: 37, HAND: 145) acquired by the Memory and Aging Center at the University of California - San Francisco with a CI-specific dataset only containing MRIs of HIV-negative subjects (Controls: 229, CI-only: 397) from the Alzheimer's Disease Neuroimaging Initiative and an HIV-specific dataset (Controls: 75, HIV-only: 75) provided by SRI International. Based on cross-validation on the UCSF dataset, the multi-domain and multi-label learning strategy leads to superior classification accuracy compared with one-domain or multi-class learning approaches, specifically for the undersampled HIV-only cohort. The 'prediction logits' of CI computed by the multi-label formulation also successfully stratify motor performance among the HIV-positive subjects (including HAND). Finally, brain patterns driving the subject-level predictions across all four cohorts characterize the independent and compounding effects of HIV and CI in the HAND cohort.

Adolescent Binge Drinking Is Associated With Accelerated Decline of Gray Matter Volume

The age- and time-dependent effects of binge drinking on adolescent brain development have not been well characterized even though binge drinking is a health crisis among adolescents. The impact of binge drinking on gray matter volume (GMV) development was examined using 5 waves of longitudinal data from the National Consortium on Alcohol and NeuroDevelopment in Adolescence study. Binge drinkers (n = 166) were compared with non-binge drinkers (n = 82 after matching on potential confounders). Number of binge drinking episodes in the past year was linked to decreased GMVs in bilateral Desikan-Killiany cortical parcellations (26 of 34 with P < 0.05/34) with the strongest effects observed in frontal regions. Interactions of binge drinking episodes and baseline age demonstrated stronger effects in younger participants. Statistical models sensitive to number of binge episodes and their temporal proximity to brain volumes provided the best fits. Consistent with prior research, results of this study highlight the negative effects of binge drinking on the developing brain. Our results present novel findings that cortical GMV decreases were greater in closer proximity to binge drinking episodes in a dose-response manner. This relation suggests a causal effect and raises the possibility that normal growth trajectories may be reinstated with alcohol abstinence.

Memory impairment in alcohol use disorder is associated with regional frontal brain volumes

BACKGROUND

Episodic memory deficits occur in alcohol use disorder (AUD), but their anatomical substrates remain in question. Although persistent memory impairment is classically associated with limbic circuitry disruption, learning and retrieval of new information also relies on frontal systems. Despite AUD vulnerability of frontal lobe integrity, relations between frontal regions and memory processes have been under-appreciated.

METHODS

Participants included 91 AUD (49 with a drug diagnosis history) and 36 controls. Verbal and visual episodic memory scores were age- and education-corrected. Structural magnetic resonance imaging (MRI) data yielded regional frontal lobe (precentral, superior, orbital, middle, inferior, supplemental motor, and medial) and total hippocampal volumes.

RESULTS

AUD were impaired on all memory scores and had smaller precentral frontal and hippocampal volumes than controls. Orbital, superior, and inferior frontal volumes and lifetime alcohol consumption were independent predictors of episodic memory in AUD. Selectivity was established with a double dissociation, where orbital frontal volume predicted verbal but not visual memory, whereas inferior frontal volumes predicted visual but not verbal memory. Further, superior frontal volumes predicted verbal memory in AUD alone, whereas orbital frontal volumes predicted verbal memory in AUD+drug abuse history.

CONCLUSIONS

Selective relations among frontal subregions and episodic memory processes highlight the relevance of extra-limbic regions in mnemonic processes in AUD. Memory deficits resulting from frontal dysfunction, unlike the episodic memory impairment associated with limbic dysfunction, may be more amenable to recovery with cessation or reduction of alcohol misuse and may partially explain the heterogeneity in episodic memory abilities in AUD.

Quantifying Parkinson's disease motor severity under uncertainty using MDS-UPDRS videos

Parkinson's disease (PD) is a brain disorder that primarily affects motor function, leading to slow movement, tremor, and stiffness, as well as postural instability and difficulty with walking/balance. The severity of PD motor impairments is clinically assessed by part III of the Movement Disorder Society Unified Parkinson's Disease Rating Scale (MDS-UPDRS), a universally-accepted rating scale. However, experts often disagree on the exact scoring of individuals. In the presence of label noise, training a machine learning model using only scores from a single rater may introduce bias, while training models with multiple noisy ratings is a challenging task due to the inter-rater variabilities. In this paper, we introduce an ordinal focal neural network to estimate the MDS-UPDRS scores from input videos, to leverage the ordinal nature of MDS-UPDRS scores and combat class imbalance. To handle multiple noisy labels per exam, the training of the network is regularized via rater confusion estimation (RCE), which encodes the rating habits and skills of raters via a confusion matrix. We apply our pipeline to estimate MDS-UPDRS test scores from their video recordings including gait (with multiple Raters, R=3) and finger tapping scores (single rater). On a sizable clinical dataset for the gait test (N=55), we obtained a classification accuracy of 72% with majority vote as ground-truth, and an accuracy of ∼84% of our model predicting at least one of the raters' scores. Our work demonstrates how computer-assisted technologies can be used to track patients and their motor impairments, even when there is uncertainty in the clinical ratings. The latest version of the code will be available at https://github.com/mlu355/PD-Motor-Severity-Estimation.

Adversarial Bayesian Optimization for Quantifying Motion Artifact Within MRI

Subject motion during an MRI sequence can cause ghosting effects or diffuse image noise in the phase-encoding direction and hence is likely to bias findings in neuroimaging studies. Detecting motion artifacts often relies on experts visually inspecting MRIs, which is subjective and expensive. To improve this detection, we develop a framework to automatically quantify the severity of motion artifact within a brain MRI. We formulate this task as a regression problem and train the regressor from a data set of MRIs with various amounts of motion artifacts. To resolve the issue of missing fine-grained ground-truth labels (level of artifacts), we propose Adversarial Bayesian Optimization (ABO) to infer the distribution of motion parameters (i.e., rotation and translation) underlying the acquired MRI data and then inject synthetic motion artifacts sampled from that estimated distribution into motion-free MRIs. After training the regressor on the synthetic data, we applied the model to quantify the motion level in 990 MRIs collected by the National Consortium on Alcohol and Neurodevelopment in Adolescence. Results show that the motion level derived by our approach is more reliable than the traditional metric based on Entropy Focus Criterion and manually defined binary labels.

Representation Learning with Statistical Independence to Mitigate Bias

Presence of bias (in datasets or tasks) is inarguably one of the most critical challenges in machine learning applications that has alluded to pivotal debates in recent years. Such challenges range from spurious associations between variables in medical studies to the bias of race in gender or face recognition systems. Controlling for all types of biases in the dataset curation stage is cumbersome and sometimes impossible. The alternative is to use the available data and build models incorporating fair representation learning. In this paper, we propose such a model based on adversarial training with two competing objectives to learn features that have (1) maximum discriminative power with respect to the task and (2) minimal statistical mean dependence with the protected (bias) variable(s). Our approach does so by incorporating a new adversarial loss function that encourages a vanished correlation between the bias and the learned features. We apply our method to synthetic data, medical images (containing task bias), and a dataset for gender classification (containing dataset bias). Our results show that the learned features by our method not only result in superior prediction performance but also are unbiased.

Longitudinal Correlation Analysis for Decoding Multi-modal Brain Development

Starting from childhood, the human brain restructures and rewires throughout life. Characterizing such complex brain development requires effective analysis of longitudinal and multi-modal neuroimaging data. Here, we propose such an analysis approach named Longitudinal Correlation Analysis (LCA). LCA couples the data of two modalities by first reducing the input from each modality to a latent representation based on autoencoders. A self-supervised strategy then relates the two latent spaces by jointly disentangling two directions, one in each space, such that the longitudinal changes in latent representations along those directions are maximally correlated between modalities. We applied LCA to analyze the longitudinal T1-weighted and diffusion-weighted MRIs of 679 youths from the National Consortium on Alcohol and Neurodevelopment in Adolescence. Unlike existing approaches that focus on either cross-sectional or single-modal modeling, LCA successfully unraveled coupled macrostructural and microstructural brain development from morphological and diffusivity features extracted from the data. A retesting of LCA on raw 3D image volumes of those subjects successfully replicated the findings from the feature-based analysis. Lastly, the developmental effects revealed by LCA were inline with the current understanding of maturational patterns of the adolescent brain.

Self-Supervised Longitudinal Neighbourhood Embedding

Longitudinal MRIs are often used to capture the gradual deterioration of brain structure and function caused by aging or neurological diseases. Analyzing this data via machine learning generally requires a large number of ground-truth labels, which are often missing or expensive to obtain. Reducing the need for labels, we propose a self-supervised strategy for representation learning named Longitudinal Neighborhood Embedding (LNE). Motivated by concepts in contrastive learning, LNE explicitly models the similarity between trajectory vectors across different subjects. We do so by building a graph in each training iteration defining neighborhoods in the latent space so that the progression direction of a subject follows the direction of its neighbors. This results in a smooth trajectory field that captures the global morphological change of the brain while maintaining the local continuity. We apply LNE to longitudinal T1w MRIs of two neuroimaging studies: a dataset composed of 274 healthy subjects, and Alzheimer's Disease Neuroimaging Initiative (ADNI, N = 632). The visualization of the smooth trajectory vector field and superior performance on downstream tasks demonstrate the strength of the proposed method over existing self-supervised methods in extracting information associated with normal aging and in revealing the impact of neurodegenerative disorders. The code is available at https://github.com/ouyangjiahong/longitudinal-neighbourhood-embedding.

Longitudinal self-supervised learning

Machine learning analysis of longitudinal neuroimaging data is typically based on supervised learning, which requires large number of ground-truth labels to be informative. As ground-truth labels are often missing or expensive to obtain in neuroscience, we avoid them in our analysis by combing factor disentanglement with self-supervised learning to identify changes and consistencies across the multiple MRIs acquired of each individual over time. Specifically, we propose a new definition of disentanglement by formulating a multivariate mapping between factors (e.g., brain age) associated with an MRI and a latent image representation. Then, factors that evolve across acquisitions of longitudinal sequences are disentangled from that mapping by self-supervised learning in such a way that changes in a single factor induce change along one direction in the representation space. We implement this model, named Longitudinal Self-Supervised Learning (LSSL), via a standard autoencoding structure with a cosine loss to disentangle brain age from the image representation. We apply LSSL to two longitudinal neuroimaging studies to highlight its strength in extracting the brain-age information from MRI and revealing informative characteristics associated with neurodegenerative and neuropsychological disorders. Moreover, the representations learned by LSSL facilitate supervised classification by recording faster convergence and higher (or similar) prediction accuracy compared to several other representation learning techniques.

Longitudinal Pooling & Consistency Regularization to Model Disease Progression From MRIs

Many neurological diseases are characterized by gradual deterioration of brain structure andfunction. Large longitudinal MRI datasets have revealed such deterioration, in part, by applying machine and deep learning to predict diagnosis. A popular approach is to apply Convolutional Neural Networks (CNN) to extract informative features from each visit of the longitudinal MRI and then use those features to classify each visit via Recurrent Neural Networks (RNNs). Such modeling neglects the progressive nature of the disease, which may result in clinically implausible classifications across visits. To avoid this issue, we propose to combine features across visits by coupling feature extraction with a novel longitudinal pooling layer and enforce consistency of the classification across visits in line with disease progression. We evaluate the proposed method on the longitudinal structural MRIs from three neuroimaging datasets: Alzheimer's Disease Neuroimaging Initiative (ADNI, N=404), a dataset composed of 274 normal controls and 329 patients with Alcohol Use Disorder (AUD), and 255 youths from the National Consortium on Alcohol and NeuroDevelopment in Adolescence (NCANDA). In allthree experiments our method is superior to other widely used approaches for longitudinal classification thus making a unique contribution towards more accurate tracking of the impact of conditions on the brain. The code is available at https://github.com/ouyangjiahong/longitudinal-pooling.

Going Beyond Saliency Maps: Training Deep Models to Interpret Deep Models

Interpretability is a critical factor in applying complex deep learning models to advance the understanding of brain disorders in neuroimaging studies. To interpret the decision process of a trained classifier, existing techniques typically rely on saliency maps to quantify the voxel-wise or feature-level importance for classification through partial derivatives. Despite providing some level of localization, these maps are not human-understandable from the neuroscience perspective as they often do not inform the specific type of morphological changes linked to the brain disorder. Inspired by the image-to-image translation scheme, we propose to train simulator networks to inject (or remove) patterns of the disease into a given MRI based on a warping operation, such that the classifier increases (or decreases) its confidence in labeling the simulated MRI as diseased. To increase the robustness of training, we propose to couple the two simulators into a unified model based on conditional convolution. We applied our approach to interpreting classifiers trained on a synthetic dataset and two neuroimaging datasets to visualize the effect of Alzheimer's disease and alcohol dependence. Compared to the saliency maps generated by baseline approaches, our simulations and visualizations based on the Jacobian determinants of the warping field reveal meaningful and understandable patterns related to the diseases.

Metadata Normalization

Batch Normalization (BN) and its variants have delivered tremendous success in combating the covariate shift induced by the training step of deep learning methods. While these techniques normalize feature distributions by standardizing with batch statistics, they do not correct the influence on features from extraneous variables or multiple distributions. Such extra variables, referred to as metadata here, may create bias or confounding effects (e.g., race when classifying gender from face images). We introduce the Metadata Normalization (MDN) layer, a new batch-level operation which can be used end-to-end within the training framework, to correct the influence of metadata on feature distributions. MDN adopts a regression analysis technique traditionally used for preprocessing to remove (regress out) the metadata effects on model features during training. We utilize a metric based on distance correlation to quantify the distribution bias from the metadata and demonstrate that our method successfully removes metadata effects on four diverse settings: one synthetic, one 2D image, one video, and one 3D medical image dataset.

Preliminary Evidence for a Relationship between Elevated Plasma TNFα and Smaller Subcortical White Matter Volume in HCV Infection Irrespective of HIV or AUD Comorbidity

Classical inflammation in response to bacterial, parasitic, or viral infections such as HIV includes local recruitment of neutrophils and macrophages and the production of proinflammatory cytokines and chemokines. Proposed biomarkers of organ integrity in Alcohol Use Disorders (AUD) include elevations in peripheral plasma levels of proinflammatory proteins. In testing this proposal, previous work included a group of human immunodeficiency virus (HIV)-infected individuals as positive controls and identified elevations in the soluble proteins TNFα and IP10; these cytokines were only elevated in AUD individuals seropositive for hepatitis C infection (HCV). The current observational, cross-sectional study evaluated whether higher levels of these proinflammatory cytokines would be associated with compromised brain integrity. Soluble protein levels were quantified in 86 healthy controls, 132 individuals with AUD, 54 individuals seropositive for HIV, and 49 individuals with AUD and HIV. Among the patient groups, HCV was present in 24 of the individuals with AUD, 13 individuals with HIV, and 20 of the individuals in the comorbid AUD and HIV group. Soluble protein levels were correlated to regional brain volumes as quantified with structural magnetic resonance imaging (MRI). In addition to higher levels of TNFα and IP10 in the 2 HIV groups and the HCV-seropositive AUD group, this study identified lower levels of IL1β in the 3 patient groups relative to the control group. Only TNFα, however, showed a relationship with brain integrity: in HCV or HIV infection, higher peripheral levels of TNFα correlated with smaller subcortical white matter volume. These preliminary results highlight the privileged status of TNFα on brain integrity in the context of infection.

Attenuated cerebral blood flow in frontolimbic and insular cortices in Alcohol Use Disorder: Relation to working memory

Chronic, excessive alcohol consumption is associated with cerebrovascular hypoperfusion, which has the potential to interfere with cognitive processes. Magnetic resonance pulsed continuous arterial spin labeling (PCASL) provides a noninvasive approach for measuring regional cerebral blood flow (CBF) and was used to study 24 men and women with Alcohol Use Disorder (AUD) and 20 age- and sex-matched controls. Two analysis approaches tested group differences: a data-driven, regionally-free method to test for group differences on a voxel-by-voxel basis and a region of interest (ROI) approach, which focused quantification on atlas-determined brain structures. Whole-brain, voxel-wise quantification identified low AUD-related cerebral perfusion in large volumes of medial frontal and cingulate cortices. The ROI analysis also identified lower CBF in the AUD group relative to the control group in medial frontal, anterior/middle cingulate, insular, and hippocampal/amygdala ROIs. Further, years of AUD diagnosis negatively correlated with temporal cortical CBF, and scores on an alcohol withdrawal scale negatively correlated with posterior cingulate and occipital gray matter CBF. Regional volume deficits did not account for AUD CBF deficits. Functional relevance of attenuated regional CBF in the AUD group emerged with positive correlations between episodic working memory test scores and anterior/middle cingulum, insula, and thalamus CBF. The frontolimbic and insular cortical neuroconstellation with dampened perfusion suggests a mechanism of dysfunction associated with these brain regions in AUD.

Association of Heavy Drinking With Deviant Fiber Tract Development in Frontal Brain Systems in Adolescents

IMPORTANCE

Maturation of white matter fiber systems subserves cognitive, behavioral, emotional, and motor development during adolescence. Hazardous drinking during this active neurodevelopmental period may alter the trajectory of white matter microstructural development, potentially increasing risk for developing alcohol-related dysfunction and alcohol use disorder in adulthood.

OBJECTIVE

To identify disrupted adolescent microstructural brain development linked to drinking onset and to assess whether the disruption is more pronounced in younger rather than older adolescents.

DESIGN, SETTING, AND PARTICIPANTS

This case-control study, conducted from January 13, 2013, to January 15, 2019, consisted of an analysis of 451 participants from the National Consortium on Alcohol and Neurodevelopment in Adolescence cohort. Participants were aged 12 to 21 years at baseline and had at least 2 usable magnetic resonance diffusion tensor imaging (DTI) scans and up to 5 examination visits spanning 4 years. Participants with a youth-adjusted Cahalan score of 0 were labeled as no-to-low drinkers; those with a score of greater than 1 for at least 2 consecutive visits were labeled as heavy drinkers. Exploratory analysis was conducted between no-to-low and heavy drinkers. A between-group analysis was conducted between age- and sex-matched youths, and a within-participant analysis was performed before and after drinking.

EXPOSURES

Self-reported alcohol consumption in the past year summarized by categorical drinking levels.

MAIN OUTCOMES AND MEASURES

Diffusion tensor imaging measurement of fractional anisotropy (FA) in the whole brain and fiber systems quantifying the developmental change of each participant as a slope.

RESULTS

Analysis of whole-brain FA of 451 adolescents included 291 (64.5%) no-to-low drinkers and 160 (35.5%) heavy drinkers who indicated the potential for a deleterious association of alcohol with microstructural development. Among the no-to-low drinkers, 142 (48.4%) were boys with mean (SD) age of 16.5 (2.2) years and 149 (51.2%) were girls with mean (SD) age of 16.5 (2.1) years and 192 (66.0%) were White participants. Among the heavy drinkers, 86 (53.8%) were boys with mean (SD) age of 20.1 (1.5) years and 74 (46.3%) were girls with mean (SD) age of 20.5 (2.0) years and 142 (88.8%) were White participants. A group analysis revealed FA reduction in heavy-drinking youth compared with age- and sex-matched controls (t154 = -2.7, P = .008). The slope of this reduction correlated with log of days of drinking since the baseline visit (r156 = -0.21, 2-tailed P = .008). A within-participant analysis contrasting developmental trajectories of youths before and after they initiated heavy drinking supported the prediction that drinking onset was associated with and potentially preceded disrupted white matter integrity. Age-alcohol interactions (t152 = 3.0, P = .004) observed for the FA slopes indicated that the alcohol-associated disruption was greater in younger than older adolescents and was most pronounced in the genu and body of the corpus callosum, regions known to continue developing throughout adolescence.

CONCLUSIONS AND RELEVANCE

This case-control study of adolescents found a deleterious association of alcohol use with white matter microstructural integrity. These findings support the concept of heightened vulnerability to environmental agents, including alcohol, associated with attenuated development of major white matter tracts in early adolescence.

Performance ramifications of abnormal functional connectivity of ventral posterior lateral thalamus with cerebellum in abstinent individuals with Alcohol Use Disorder

The extant literature supports the involvement of the thalamus in the cognitive and motor impairment associated with chronic alcohol consumption, but clear structure/function relationships remain elusive. Alcohol effects on specific nuclei rather than the entire thalamus may provide the basis for differential cognitive and motor decline in Alcohol Use Disorder (AUD). This functional MRI (fMRI) study was conducted in 23 abstinent individuals with AUD and 27 healthy controls to test the hypothesis that functional connectivity between anterior thalamus and hippocampus would be compromised in those with an AUD diagnosis and related to mnemonic deficits. Functional connectivity between 7 thalamic structures [5 thalamic nuclei: anterior ventral (AV), mediodorsal (MD), pulvinar (Pul), ventral lateral posterior (VLP), and ventral posterior lateral (VPL); ventral thalamus; the entire thalamus] and 14 "functional regions" was evaluated. Relative to controls, the AUD group exhibited different VPL-based functional connectivity: an anticorrelation between VPL and a bilateral middle temporal lobe region observed in controls became a positive correlation in the AUD group; an anticorrelation between the VPL and the cerebellum was stronger in the AUD than control group. AUD-associated altered connectivity between anterior thalamus and hippocampus as a substrate of memory compromise was not supported; instead, connectivity differences from controls selective to VPL and cerebellum demonstrated a relationship with impaired balance. These preliminary findings support substructure-level evaluation in future studies focused on discerning the role of the thalamus in AUD-associated cognitive and motor deficits.