Prediction of brain age suggests accelerated atrophy after traumatic brain injury

Sustained Axonal Degeneration in Prolonged Disorders of Consciousness

(1) Background: Sustained axonal degeneration may play a critical role in prolonged disorder of consciousness (DOCs) pathophysiology. We evaluated levels of neurofilament light chain (NFL), an axonal injury marker, in patients with unresponsive wakefulness syndrome (UWS) and in the minimally conscious state (MCS) after traumatic brain injury (TBI) and hypoxic-ischemic brain injury (HIBI). (2) Methods: This prospective multicenter blinded study involved 70 patients with prolonged DOC and 70 sex-/age-matched healthy controls. Serum NFL levels were evaluated at 1-3 and 6 months post-injury and compared with those of controls. NFL levels were compared by DOC severity (UWS vs. MCS) and etiology (TBI vs. HIBI). (3) Results: Patients' serum NFL levels were significantly higher than those of controls at 1-3 and 6 months post-injury (medians, 1729 and 426 vs. 90 pg/mL; both p < 0.0001). NFL levels were higher in patients with UWS than in those in MCS at 1-3 months post-injury (p = 0.008) and in patients with HIBI than in those with TBI at 6 months post-injury (p = 0.037). (4) Conclusions: Patients with prolonged DOC present sustained axonal degeneration that is affected differently over time by brain injury severity and etiology.

Factors associated with brain ageing - a systematic review

Background

Brain age is a biomarker that predicts chronological age using neuroimaging features. Deviations of this predicted age from chronological age is considered a sign of age-related brain changes, or commonly referred to as brain ageing. The aim of this systematic review is to identify and synthesize the evidence for an association between lifestyle, health factors and diseases in adult populations, with brain ageing.

Methods

This systematic review was undertaken in accordance with the PRISMA guidelines. A systematic search of Embase and Medline was conducted to identify relevant articles using search terms relating to the prediction of age from neuroimaging data or brain ageing. The tables of two recent review papers on brain ageing were also examined to identify additional articles. Studies were limited to adult humans (aged 18 years and above), from clinical or general populations. Exposures and study design of all types were also considered eligible.

Results

A systematic search identified 52 studies, which examined brain ageing in clinical and community dwelling adults (mean age between 21 to 78 years, ~ 37% were female). Most research came from studies of individuals diagnosed with schizophrenia or Alzheimer’s disease, or healthy populations that were assessed cognitively. From these studies, psychiatric and neurologic diseases were most commonly associated with accelerated brain ageing, though not all studies drew the same conclusions. Evidence for all other exposures is nascent, and relatively inconsistent. Heterogenous methodologies, or methods of outcome ascertainment, were partly accountable.

Conclusion

This systematic review summarised the current evidence for an association between genetic, lifestyle, health, or diseases and brain ageing. Overall there is good evidence to suggest schizophrenia and Alzheimer’s disease are associated with accelerated brain ageing. Evidence for all other exposures was mixed or limited. This was mostly due to a lack of independent replication, and inconsistency across studies that were primarily cross sectional in nature. Future research efforts should focus on replicating current findings, using prospective datasets.

Trial registration

A copy of the review protocol can be accessed through PROSPERO, registration number CRD42020142817.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12883-021-02331-4.

Imaging biomarkers of vascular and axonal injury are spatially distinct in chronic traumatic brain injury

Traumatic Brain Injury (TBI) is associated with both diffuse axonal injury (DAI) and diffuse vascular injury (DVI), which result from inertial shearing forces. These terms are often used interchangeably, but the spatial relationships between DAI and DVI have not been carefully studied. Multimodal magnetic resonance imaging (MRI) can help distinguish these injury mechanisms: diffusion tensor imaging (DTI) provides information about axonal integrity, while arterial spin labeling (ASL) can be used to measure cerebral blood flow (CBF), and the reactivity of the Blood Oxygen Level Dependent (BOLD) signal to a hypercapnia challenge reflects cerebrovascular reactivity (CVR). Subjects with chronic TBI (n = 27) and healthy controls (n = 14) were studied with multimodal MRI. Mean values of mean diffusivity (MD), fractional anisotropy (FA), CBF, and CVR were extracted for pre-determined regions of interest (ROIs). Normalized z-score maps were generated from the pool of healthy controls. Abnormal ROIs in one modality were not predictive of abnormalities in another. Approximately 9-10% of abnormal voxels for CVR and CBF also showed an abnormal voxel value for MD, while only 1% of abnormal CVR and CBF voxels show a concomitant abnormal FA value. These data indicate that DAI and DVI represent two distinct TBI endophenotypes that are spatially independent.

Multi-channel attention-fusion neural network for brain age estimation: Accuracy, generality, and interpretation with 16,705 healthy MRIs across lifespan

Brain age estimated by machine learning from T1-weighted magnetic resonance images (T1w MRIs) can reveal how brain disorders alter brain aging and can help in the early detection of such disorders. A fundamental step is to build an accurate age estimator from healthy brain MRIs. We focus on this step, and propose a framework to improve the accuracy, generality, and interpretation of age estimation in healthy brain MRIs. For accuracy, we used one of the largest sample sizes (N = 16,705). For each subject, our proposed algorithm first explicitly splits the T1w image, which has been commonly treated as a single-channel 3D image in other studies, into two 3D image channels representing contrast and morphometry information. We further proposed a "fusion-with-attention" deep learning convolutional neural network (FiA-Net) to learn how to best fuse the contrast and morphometry image channels. FiA-Net recognizes varying contributions across image channels at different brain anatomy and different feature layers. In contrast, multi-channel fusion does not exist for brain age estimation, and is mostly attention-free in other medical image analysis tasks (e.g., image synthesis, or segmentation), where treating channels equally may not be optimal. For generality, we used lifespan data 0-97 years of age for real-world utility; and we thoroughly tested FiA-Net for multi-site and multi-scanner generality by two phases of cross-validations in discovery and replication data, compared to most other studies with only one phase of cross-validation. For interpretation, we directly measured each artificial neuron's correlation with the chronological age, compared to other studies looking at the saliency of features where salient features may or may not predict age. Overall, FiA-Net achieved a mean absolute error (MAE) of 3.00 years and Pearson correlation r=0.9840 with known chronological ages in healthy brain MRIs 0-97 years of age, comparing favorably with state-of-the-art algorithms and studies for accuracy and generality across sites and datasets. We also provided interpretations on how different artificial neurons and real neuroanatomy contribute to the age estimation.

Synergistic effects of brain injury and aging: common mechanisms of proteostatic dysfunction

The aftermath of TBI is associated with an acute stress response and the accumulation of insoluble protein aggregates. Even after the symptoms of TBI are resolved, insidious molecular processes continue to develop, which often ultimately result in the development of age-associated neurodegenerative disorders. The precise molecular cascades that drive unhealthy brain aging are still largely unknown. In this review, we discuss proteostatic dysfunction as a converging mechanism contributing to accelerated brain aging after TBI. We examine evidence from human tissue and in vivo animal models, spanning both the aging and injury contexts. We conclude that TBI has a sustained debilitating effect on the proteostatic machinery, which may contribute to the accelerated pathological and cognitive hallmarks of aging that are observed following injury.

Learning to synthesise the ageing brain without longitudinal data

How will my face look when I get older? Or, for a more challenging question: How will my brain look when I get older? To answer this question one must devise (and learn from data) a multivariate auto-regressive function which given an image and a desired target age generates an output image. While collecting data for faces may be easier, collecting longitudinal brain data is not trivial. We propose a deep learning-based method that learns to simulate subject-specific brain ageing trajectories without relying on longitudinal data. Our method synthesises images conditioned on two factors: age (a continuous variable), and status of Alzheimer's Disease (AD, an ordinal variable). With an adversarial formulation we learn the joint distribution of brain appearance, age and AD status, and define reconstruction losses to address the challenging problem of preserving subject identity. We compare with several benchmarks using two widely used datasets. We evaluate the quality and realism of synthesised images using ground-truth longitudinal data and a pre-trained age predictor. We show that, despite the use of cross-sectional data, our model learns patterns of gray matter atrophy in the middle temporal gyrus in patients with AD. To demonstrate generalisation ability, we train on one dataset and evaluate predictions on the other. In conclusion, our model shows an ability to separate age, disease influence and anatomy using only 2D cross-sectional data that should be useful in large studies into neurodegenerative disease, that aim to combine several data sources. To facilitate such future studies by the community at large our code is made available at https://github.com/xiat0616/BrainAgeing.

Glial AP1 is activated with aging and accelerated by traumatic brain injury

The emergence of degenerative disease after traumatic brain injury is often described as an acceleration of normal age-related processes. Whether similar molecular processes occur after injury and in age is unclear. Here we identify a functionally dynamic and lasting transcriptional response in glia, mediated by the conserved transcription factor AP1. In the early post-TBI period, glial AP1 is essential for recovery, ensuring brain integrity and animal survival. In sharp contrast, chronic AP1 activation promotes human tau pathology, tissue loss, and mortality. We show a similar process activates in healthy fly brains with age. In humans, AP1 activity is detected after moderate TBI and correlates with microglial activation and tau pathology. Our data provide key molecular insight into glia, highlighting that the same molecular process drives dynamic and contradictory glia behavior in TBI, and possibly age, first acting to protect but chronically promoting disease.

Age-Net: An MRI-Based Iterative Framework for Brain Biological Age Estimation

The concept of biological age (BA) - although important in clinical practice - is hard to grasp mainly due to the lack of a clearly defined reference standard. For specific applications, especially in pediatrics, medical image data are used for BA estimation in a routine clinical context. Beyond this young age group, BA estimation is mostly restricted to whole-body assessment using non-imaging indicators such as blood biomarkers, genetic and cellular data. However, various organ systems may exhibit different aging characteristics due to lifestyle and genetic factors. Thus, a whole-body assessment of the BA does not reflect the deviations of aging behavior between organs. To this end, we propose a new imaging-based framework for organ-specific BA estimation. In this initial study we focus mainly on brain MRI. As a first step, we introduce a chronological age (CA) estimation framework using deep convolutional neural networks (Age-Net). We quantitatively assess the performance of this framework in comparison to existing state-of-the-art CA estimation approaches. Furthermore, we expand upon Age-Net with a novel iterative data-cleaning algorithm to segregate atypical-aging patients (BA [Formula: see text] CA) from the given population. We hypothesize that the remaining population should approximate the true BA behavior. We apply the proposed methodology on a brain magnetic resonance image (MRI) dataset containing healthy individuals as well as Alzheimer's patients with different dementia ratings. We demonstrate the correlation between the predicted BAs and the expected cognitive deterioration in Alzheimer's patients. A statistical and visualization-based analysis has provided evidence regarding the potential and current challenges of the proposed methodology.

In vivo biomarkers of structural and functional brain development and aging in humans

Brain aging is a major determinant of aging. Along with the aging population, prevalence of neurodegenerative diseases is increasing, therewith placing economic and social burden on individuals and society. Individual rates of brain aging are shaped by genetics, epigenetics, and prenatal environmental. Biomarkers of biological brain aging are needed to predict individual trajectories of aging and the risk for age-associated neurological impairments for developing early preventive and interventional measures. We review current advances of in vivo biomarkers predicting individual brain age. Telomere length and epigenetic clock, two important biomarkers that are closely related to the mechanistic aging process, have only poor deterministic and predictive accuracy regarding individual brain aging due to their high intra- and interindividual variability. Phenotype-related biomarkers of global cognitive function and brain structure provide a much closer correlation to age at the individual level. During fetal and perinatal life, autonomic activity is a unique functional marker of brain development. The cognitive and structural biomarkers also boast high diagnostic specificity for determining individual risks for neurodegenerative diseases.

Progressive Neurodegeneration Across Chronic Stages of Severe Traumatic Brain Injury

OBJECTIVE

To examine the trajectory of structural gray matter changes across 2 chronic periods of recovery in individuals who have sustained severe traumatic brain injury (TBI), adding to the growing literature indicating that neurodegenerative processes occur in the months to years postinjury.

PARTICIPANTS

Patients who experienced posttraumatic amnesia of 1 hour or more, and/or scored 12 or less on the Glasgow Coma Scale at the emergency department or the scene of the accident, and/or had positive brain imaging findings were recruited while receiving inpatient care, resulting in 51 patients with severe TBI.

METHODS

Secondary analyses of gray matter changes across approximately 5 months, 1 year, and 2.5 years postinjury were undertaken, using an automated segmentation protocol with improved accuracy in populations with morphological anomalies. We compared patients and matched controls on regions implicated in poorer long-term clinical outcome (accumbens, amygdala, brainstem, hippocampus, thalamus). To model brain-wide patterns of change, we then conducted an exploratory principal component analysis (PCA) on the linear slopes of all regional volumes across the 3 time points. Finally, we assessed nonlinear trends across earlier (5 months-1 year) versus later (1-2.5 years) time-windows with PCA to compare degeneration rates across time. Chronic degeneration was predicted cortically and subcortically brain-wide, and within specific regions of interest.

RESULTS

(1) From 5 months to 1 year, patients showed significant degeneration in the accumbens, and marginal degeneration in the amygdala, brainstem, thalamus, and the left hippocampus when examined unilaterally, compared with controls. (2) PCA components representing subcortical and temporal regions, and regions from the basal ganglia, significantly differed from controls in the first time-window. (3) Progression occurred at the same rate across both time-windows, suggesting neither escalation nor attenuation of degeneration across time.

CONCLUSION

Localized yet progressive decline emphasizes the necessity of developing interventions to offset degeneration and improve long-term functioning.

Cognitive Reserve in Individuals Aging With Traumatic Brain Injury: Independent and Interactive Effects on Cognitive Functioning

OBJECTIVE

To examine the influence of 2 temporal factors-age and injury chronicity-on the relationship between cognitive reserve (CR) and cognitive functioning in older adults with chronic traumatic brain injury (TBI).

SETTING

Outpatient research laboratory.

PARTICIPANTS

Adults, 50 years or older, with a 1- to 45-year history of moderate or severe TBI (N = 108).

DESIGN

Cross-sectional observational study.

MAIN MEASURES

CR was estimated using demographically corrected performance on a word-reading test (an approximation of premorbid IQ). Injury chronicity was operationalized as number of years since the date of injury. Composite cognitive scores were computed from performances on neuropsychological tests of processing speed, executive functioning, and memory.

RESULTS

CR was positively and significantly related to all cognitive performances independent of age, injury chronicity, and injury severity. Greater injury chronicity significantly attenuated the effect of CR on processing speed such that individuals more distal from their injury date evidenced a weaker positive relationship between CR and performance.

CONCLUSION

Temporal factors may modify associations between CR and cognition. Findings suggest that the protective effects of CR are temporally delimited, potentially contending with declines in brain reserve. The prognostic value of traditional outcome determinants should be considered in the context of injury chronicity.

Explainable Deep Learning for Personalized Age Prediction With Brain Morphology

Predicting brain age has become one of the most attractive challenges in computational neuroscience due to the role of the predicted age as an effective biomarker for different brain diseases and conditions. A great variety of machine learning (ML) approaches and deep learning (DL) techniques have been proposed to predict age from brain magnetic resonance imaging scans. If on one hand, DL models could improve performance and reduce model bias compared to other less complex ML methods, on the other hand, they are typically black boxes as do not provide an in-depth understanding of the underlying mechanisms. Explainable Artificial Intelligence (XAI) methods have been recently introduced to provide interpretable decisions of ML and DL algorithms both at local and global level. In this work, we present an explainable DL framework to predict the age of a healthy cohort of subjects from ABIDE I database by using the morphological features extracted from their MRI scans. We embed the two local XAI methods SHAP and LIME to explain the outcomes of the DL models, determine the contribution of each brain morphological descriptor to the final predicted age of each subject and investigate the reliability of the two methods. Our findings indicate that the SHAP method can provide more reliable explanations for the morphological aging mechanisms and be exploited to identify personalized age-related imaging biomarker.

Predicting brain age using machine learning algorithms: A comprehensive evaluation

Machine learning (ML) algorithms play a vital role in brain age estimation frameworks. The impact of regression algorithms on prediction accuracy in the brain age estimation frameworks have not been comprehensively evaluated. Here, we sought to assess the efficiency of different regression algorithms on brain age estimation. To this end, we built a brain age estimation framework based on a large set of cognitively healthy (CH) individuals (N = 788) as a training set followed by different regression algorithms (18 different algorithms in total). We then quantified each regression-algorithm on independent test sets composed of 88 CH individuals, 70 mild cognitive impairment patients as well as 30 Alzheimers disease patients. The prediction accuracy in the independent test set (i.e., CH set) varied in regression algorithms (mean absolute error (MAE) from 4.63 to 7.14 yrs, R2 from 0.76 to 0.88). The highest and lowest prediction accuracies were achieved by Quadratic Support Vector Regression algorithm (MAE = 4.63 yrs, R2 = 0.88, 95% CI = [-1.26, 1.42]) and Binary Decision Tree algorithm (MAE = 7.14 yrs, R2 = 0.76, 95% CI = [-1.50, 2.62]), respectively. Our experimental results demonstrate that prediction accuracy in brain age frameworks is affected by regression algorithms, indicating that advanced machine learning algorithms can lead to more accurate brain age predictions in clinical settings.

Ranking Biomarkers of Aging by Citation Profiling and Effort Scoring

Aging affects most living organisms and includes the processes that reduce health and survival. The chronological and the biological age of individuals can differ remarkably, and there is a lack of reliable biomarkers to monitor the consequences of aging. In this review we give an overview of commonly mentioned and frequently used potential aging-related biomarkers. We were interested in biomarkers of aging in general and in biomarkers related to cellular senescence in particular. To answer the question whether a biological feature is relevant as a potential biomarker of aging or senescence in the scientific community we used the PICO strategy known from evidence-based medicine. We introduced two scoring systems, aimed at reflecting biomarker relevance and measurement effort, which can be used to support study designs in both clinical and research settings.

Genetic inactivation of SARM1 axon degeneration pathway improves outcome trajectory after experimental traumatic brain injury based on pathological, radiological, and functional measures

Traumatic brain injury (TBI) causes chronic symptoms and increased risk of neurodegeneration. Axons in white matter tracts, such as the corpus callosum (CC), are critical components of neural circuits and particularly vulnerable to TBI. Treatments are needed to protect axons from traumatic injury and mitigate post-traumatic neurodegeneration. SARM1 protein is a central driver of axon degeneration through a conserved molecular pathway. Sarm1−/− mice with knockout (KO) of the Sarm1 gene enable genetic proof-of-concept testing of the SARM1 pathway as a therapeutic target. We evaluated Sarm1 deletion effects after TBI using a concussive model that causes traumatic axonal injury and progresses to CC atrophy at 10 weeks, indicating post-traumatic neurodegeneration. Sarm1 wild-type (WT) mice developed significant CC atrophy that was reduced in Sarm1 KO mice. Ultrastructural classification of pathology of individual axons, using electron microscopy, demonstrated that Sarm1 KO preserved more intact axons and reduced damaged or demyelinated axons. Longitudinal MRI studies in live mice identified significantly reduced CC volume after TBI in Sarm1 WT mice that was attenuated in Sarm1 KO mice. MR diffusion tensor imaging detected reduced fractional anisotropy in both genotypes while axial diffusivity remained higher in Sarm1 KO mice. Immunohistochemistry revealed significant attenuation of CC atrophy, myelin loss, and neuroinflammation in Sarm1 KO mice after TBI. Functionally, Sarm1 KO mice exhibited beneficial effects in motor learning and sleep behavior. Based on these findings, Sarm1 inactivation can protect axons and white matter tracts to improve translational outcomes associated with CC atrophy and post-traumatic neurodegeneration.

Aging faster: worry and rumination in late life are associated with greater brain age

Older adults with anxiety have lower gray matter brain volume-a component of accelerated aging. We have previously validated a machine learning model to predict brain age, an estimate of an individual's age based on voxel-wise gray matter images. We investigated associations between brain age and anxiety, depression, stress, and emotion regulation. We recruited 78 participants (≥50 years) along a wide range of worry severity. We collected imaging data and computed voxel-wise gray matter images, which were input into an existing machine learning model to estimate brain age. We conducted a multivariable linear regression between brain age and age, sex, race, education, worry, anxiety, depression, rumination, neuroticism, stress, reappraisal, and suppression. We found that greater brain age was significantly associated with greater age, male sex, greater worry, greater rumination, and lower suppression. Male sex, worry, and rumination are associated with accelerated aging in late life and expressive suppression may have a protective effect. These results provide evidence for the transdiagnostic model of negative repetitive thoughts, which are associated with cognitive decline, amyloid, and tau.

Brain-predicted age difference score is related to specific cognitive functions: a multi-site replication analysis

Brain-predicted age difference scores are calculated by subtracting chronological age from 'brain' age, which is estimated using neuroimaging data. Positive scores reflect accelerated ageing and are associated with increased mortality risk and poorer physical function. To date, however, the relationship between brain-predicted age difference scores and specific cognitive functions has not been systematically examined using appropriate statistical methods. First, applying machine learning to 1359 T1-weighted MRI scans, we predicted the relationship between chronological age and voxel-wise grey matter data. This model was then applied to MRI data from three independent datasets, significantly predicting chronological age in each dataset: Dokuz Eylül University (n = 175), the Cognitive Reserve/Reference Ability Neural Network study (n = 380), and The Irish Longitudinal Study on Ageing (n = 487). Each independent dataset had rich neuropsychological data. Brain-predicted age difference scores were significantly negatively correlated with performance on measures of general cognitive status (two datasets); processing speed, visual attention, and cognitive flexibility (three datasets); visual attention and cognitive flexibility (two datasets); and semantic verbal fluency (two datasets). As such, there is firm evidence of correlations between increased brain-predicted age differences and reduced cognitive function in some domains that are implicated in cognitive ageing.

Abnormal dorsal attention network activation in memory impairment after traumatic brain injury

Memory impairment is a common, disabling effect of traumatic brain injury. In healthy individuals, successful memory encoding is associated with activation of the dorsal attention network as well as suppression of the default mode network. Here, in traumatic brain injury patients we examined whether: (i) impairments in memory encoding are associated with abnormal brain activation in these networks; (ii) whether changes in this brain activity predict subsequent memory retrieval; and (iii) whether abnormal white matter integrity underpinning functional networks is associated with impaired subsequent memory. Thirty-five patients with moderate-severe traumatic brain injury aged 23-65 years (74% males) in the post-acute/chronic phase after injury and 16 healthy control subjects underwent functional MRI during performance of an abstract image memory encoding task. Diffusion tensor imaging was used to assess structural abnormalities across patient groups compared to 28 age-matched healthy controls. Successful memory encoding across all participants was associated with activation of the dorsal attention network, the ventral visual stream and medial temporal lobes. Decreased activation was seen in the default mode network. Patients with preserved episodic memory demonstrated increased activation in areas of the dorsal attention network. Patients with impaired memory showed increased left anterior prefrontal activity. White matter microstructure underpinning connectivity between core nodes of the encoding networks was significantly reduced in patients with memory impairment. Our results show for the first time that patients with impaired episodic memory show abnormal activation of key nodes within the dorsal attention network and regions regulating default mode network activity during encoding. Successful encoding was associated with an opposite direction of signal change between patients with and without memory impairment, suggesting that memory encoding mechanisms could be fundamentally altered in this population. We demonstrate a clear relationship between functional networks activated during encoding and underlying abnormalities within the structural connectome in patients with memory impairment. We suggest that encoding failures in this group are likely due to failed control of goal-directed attentional resources.

Individual variation underlying brain age estimates in typical development

Typical brain development follows a protracted trajectory throughout childhood and adolescence. Deviations from typical growth trajectories have been implicated in neurodevelopmental and psychiatric disorders. Recently, the use of machine learning algorithms to model age as a function of structural or functional brain properties has been used to examine advanced or delayed brain maturation in healthy and clinical populations. Termed 'brain age', this approach often relies on complex, nonlinear models that can be difficult to interpret. In this study, we use model explanation methods to examine the cortical features that contribute to brain age modelling on an individual basis. In a large cohort of n = 768 typically-developing children (aged 3-21 years), we build models of brain development using three different machine learning approaches. We employ SHAP, a model-agnostic technique to identify sample-specific feature importance, to identify regional cortical metrics that explain errors in brain age prediction. We find that, on average, brain age prediction and the cortical features that explain model predictions are consistent across model types and reflect previously reported patterns of regions brain development. However, while several regions are found to contribute to brain age prediction error, we find little spatial correspondence between individual estimates of feature importance, even when matched for age, sex and brain age prediction error. We also find no association between brain age error and cognitive performance in this typically-developing sample. Overall, this study shows that, while brain age estimates based on cortical development are relatively robust and consistent across model types and preprocessing strategies, significant between-subject variation exists in the features that explain erroneous brain age predictions on an individual level.

Brain age prediction: A comparison between machine learning models using region- and voxel-based morphometric data

Brain morphology varies across the ageing trajectory and the prediction of a person's age using brain features can aid the detection of abnormalities in the ageing process. Existing studies on such “brain age prediction” vary widely in terms of their methods and type of data, so at present the most accurate and generalisable methodological approach is unclear. Therefore, we used the UK Biobank data set (N = 10,824, age range 47–73) to compare the performance of the machine learning models support vector regression, relevance vector regression and Gaussian process regression on whole‐brain region‐based or voxel‐based structural magnetic resonance imaging data with or without dimensionality reduction through principal component analysis. Performance was assessed in the validation set through cross‐validation as well as an independent test set. The models achieved mean absolute errors between 3.7 and 4.7 years, with those trained on voxel‐level data with principal component analysis performing best. Overall, we observed little difference in performance between models trained on the same data type, indicating that the type of input data had greater impact on performance than model choice. All code is provided online in the hope that this will aid future research.

A population-based study of head injury, cognitive function and pathological markers

Objective

To assess associations between head injury (HI) with loss of consciousness (LOC), ageing and markers of later‐life cerebral pathology; and to explore whether those effects may help explain subtle cognitive deficits in dementia‐free individuals.

Methods

Participants (n = 502, age = 69–71) from the 1946 British Birth Cohort underwent cognitive testing (subtests of Preclinical Alzheimer Cognitive Composite), ¹⁸F‐florbetapir Aβ‐PET and MR imaging. Measures include Aβ‐PET status, brain, hippocampal and white matter hyperintensity (WMH) volumes, normal appearing white matter (NAWM) microstructure, Alzheimer’s disease (AD)‐related cortical thickness, and serum neurofilament light chain (NFL). LOC HI metrics include HI occurring: (i) >15 years prior to the scan (ii) anytime up to age 71.

Results

Compared to those with no evidence of an LOC HI, only those reporting an LOC HI>15 years prior (16%, n = 80) performed worse on cognitive tests at age 69–71, taking into account premorbid cognition, particularly on the digit‐symbol substitution test (DSST). Smaller brain volume (BV) and adverse NAWM microstructural integrity explained 30% and 16% of the relationship between HI and DSST, respectively. We found no evidence that LOC HI was associated with Aβ load, hippocampal volume, WMH volume, AD‐related cortical thickness or NFL (all p > 0.01).

Interpretation

Having a LOC HI aged 50’s and younger was linked with lower later‐life cognitive function at age ~70 than expected. This may reflect a damaging but small impact of HI; explained in part by smaller BV and different microstructure pathways but not via pathology related to AD (amyloid, hippocampal volume, AD cortical thickness) or ongoing neurodegeneration (serum NFL).

Diffuse axonal injury predicts neurodegeneration after moderate-severe traumatic brain injury

Traumatic brain injury is associated with elevated rates of neurodegenerative diseases such as Alzheimer's disease and chronic traumatic encephalopathy. In experimental models, diffuse axonal injury triggers post-traumatic neurodegeneration, with axonal damage leading to Wallerian degeneration and toxic proteinopathies of amyloid and hyperphosphorylated tau. However, in humans the link between diffuse axonal injury and subsequent neurodegeneration has yet to be established. Here we test the hypothesis that the severity and location of diffuse axonal injury predicts the degree of progressive post-traumatic neurodegeneration. We investigated longitudinal changes in 55 patients in the chronic phase after moderate-severe traumatic brain injury and 19 healthy control subjects. Fractional anisotropy was calculated from diffusion tensor imaging as a measure of diffuse axonal injury. Jacobian determinant atrophy rates were calculated from serial volumetric T1 scans as a measure of measure post-traumatic neurodegeneration. We explored a range of potential predictors of longitudinal post-traumatic neurodegeneration and compared the variance in brain atrophy that they explained. Patients showed widespread evidence of diffuse axonal injury, with reductions of fractional anisotropy at baseline and follow-up in large parts of the white matter. No significant changes in fractional anisotropy over time were observed. In contrast, abnormally high rates of brain atrophy were seen in both the grey and white matter. The location and extent of diffuse axonal injury predicted the degree of brain atrophy: fractional anisotropy predicted progressive atrophy in both whole-brain and voxelwise analyses. The strongest relationships were seen in central white matter tracts, including the body of the corpus callosum, which are most commonly affected by diffuse axonal injury. Diffuse axonal injury predicted substantially more variability in white matter atrophy than other putative clinical or imaging measures, including baseline brain volume, age, clinical measures of injury severity and microbleeds (>50% for fractional anisotropy versus <5% for other measures). Grey matter atrophy was not predicted by diffuse axonal injury at baseline. In summary, diffusion MRI measures of diffuse axonal injury are a strong predictor of post-traumatic neurodegeneration. This supports a causal link between axonal injury and the progressive neurodegeneration that is commonly seen after moderate/severe traumatic brain injury but has been of uncertain aetiology. The assessment of diffuse axonal injury with diffusion MRI is likely to improve prognostic accuracy and help identify those at greatest neurodegenerative risk for inclusion in clinical treatment trials.

Chronic noncancer pain is not associated with accelerated brain aging as assessed by structural magnetic resonance imaging in patients treated in specialized outpatient clinics

Chronic pain is often associated with changes in brain structure and function, and also cognitive deficits. It has been noted that these chronic pain-related alterations may resemble changes found in healthy aging, and thus may represent accelerated or premature aging of the brain. Here, we test the hypothesis that patients with chronic noncancer pain demonstrate accelerated brain aging compared with healthy control subjects. The predicted brain age of 59 patients with chronic pain (mean chronological age ± SD: 53.0 ± 9.0 years; 43 women) and 60 pain-free healthy controls (52.6 ± 9.0 years; 44 women) was determined using the software brainageR. This software segments the individual T1-weighted structural MR images into gray and white matter and compares gray and white matter images with a large (n = 2001) training set of structural images, using machine learning. Finally, brain age delta, which is the predicted brain age minus chronological age, was calculated and compared across groups. This study provided no evidence for the hypothesis that chronic pain is associated with accelerated brain aging (Welch t test, P = 0.74, Cohen's d = 0.061). A Bayesian independent-samples t test indicated moderate evidence in favor of the null hypothesis (BF01 = 4.875, ie, group means were equal). Our results provide indirect support for recent models of pain-related changes of brain structure, brain function, and cognitive functions. These models postulate network-specific maladaptive plasticity, rather than widespread or global neural degeneration.

Estimating brain age from structural MRI and MEG data: Insights from dimensionality reduction techniques

Brain age prediction studies aim at reliably estimating the difference between the chronological age of an individual and their predicted age based on neuroimaging data, which has been proposed as an informative measure of disease and cognitive decline. As most previous studies relied exclusively on magnetic resonance imaging (MRI) data, we hereby investigate whether combining structural MRI with functional magnetoencephalography (MEG) information improves age prediction using a large cohort of healthy subjects (N = 613, age 18-88 years) from the Cam-CAN repository. To this end, we examined the performance of dimensionality reduction and multivariate associative techniques, namely Principal Component Analysis (PCA) and Canonical Correlation Analysis (CCA), to tackle the high dimensionality of neuroimaging data. Using MEG features (mean absolute error (MAE) of 9.60 years) yielded worse performance when compared to using MRI features (MAE of 5.33 years), but a stacking model combining both feature sets improved age prediction performance (MAE of 4.88 years). Furthermore, we found that PCA resulted in inferior performance, whereas CCA in conjunction with Gaussian process regression models yielded the best prediction performance. Notably, CCA allowed us to visualize the features that significantly contributed to brain age prediction. We found that MRI features from subcortical structures were more reliable age predictors than cortical features, and that spectral MEG measures were more reliable than connectivity metrics. Our results provide an insight into the underlying processes that are reflective of brain aging, yielding promise for the identification of reliable biomarkers of neurodegenerative diseases that emerge later during the lifespan.

Sex-specific differences in the association between body mass index and brain aging in young adults: Findings from the human connectome project

BACKGROUND

This report evaluated sex-specific differences in the association between brain aging and body mass index (BMI) in young adults using the publicly available data from the Human Connectome Project (HCP).

METHODS

Participants of HCP with available structural imaging and BMI data were included [n = 1112; mean age = 28.80 (SD = 3.70); mean BMI = 26.53 (SD = 5.20); males n = 507, females n = 605]. Predicted brain age was generated using raw T1-weighted MRI scan and a Gaussian Processes regression model. The difference (Δ aging) between brain age predicted by structural imaging and chronological age was computed. A linear regression model was used with Δ aging as the dependent variable, and sex, BMI, and BMI-by-sex interaction as independent variables of interest, and race, ethnicity, income, and education as covariates.

RESULTS

There was a significant BMI-by-sex interaction for Δ aging (p = 0.041). Higher BMI was associated with greater brain aging in both sexes. However, this association was substantially stronger in males (β = 0.215; SE = 0.050; p < 0.0001) than in females (β = 0.122; SE = 0.035; p = 0.0005).

CONCLUSION

We found evidence suggesting that higher BMI is associated with greater brain aging in adults. Furthermore, the association between higher BMI and greater brain aging was stronger in males than in females. Future studies are needed to explore the mechanistic pathways that link higher BMI to greater brain aging and whether weight-loss interventions, such as exercise, can reverse higher BMI-associated greater brain aging.

Apolipoprotein ɛ4 Status and Brain Structure 12 Months after Mild Traumatic Injury: Brain Age Prediction Using Brain Morphometry and Diffusion Tensor Imaging

Background: Apolipoprotein E (APOE) ɛ4 is associated with poor outcome following moderate to severe traumatic brain injury (TBI). There is a lack of studies investigating the influence of APOE ɛ4 on intracranial pathology following mild traumatic brain injury (MTBI). This study explores the association between APOE ɛ4 and MRI measures of brain age prediction, brain morphometry, and diffusion tensor imaging (DTI). Methods: Patients aged 16 to 65 with acute MTBI admitted to the trauma center were included. Multimodal MRI was performed 12 months after injury and associated with APOE ɛ4 status. Corrections for multiple comparisons were done using false discovery rate (FDR). Results: Of included patients, 123 patients had available APOE, volumetric, and DTI data of sufficient quality. There were no differences between APOE ɛ4 carriers (39%) and non-carriers in demographic and clinical data. Age prediction revealed high accuracy both for the DTI-based and the brain morphometry based model. Group comparisons revealed no significant differences in brain-age gap between ɛ4 carriers and non-carriers, and no significant differences in conventional measures of brain morphometry and volumes. Compared to non-carriers, APOE ɛ4 carriers showed lower fractional anisotropy (FA) in the hippocampal part of the cingulum bundle, which did not remain significant after FDR adjustment. Conclusion: APOE ɛ4 carriers might be vulnerable to reduced neuronal integrity in the cingulum. Larger cohort studies are warranted to replicate this finding.

A venous mechanism of ventriculomegaly shared between traumatic brain injury and normal ageing

Recently, age-related timing dissociation between the superficial and deep venous systems has been observed; this was particularly pronounced in patients with normal pressure hydrocephalus, suggesting a common mechanism of ventriculomegaly. Establishing the relationship between venous drainage and ventricular enlargement would be clinically relevant and could provide insight into the mechanisms underlying brain ageing. To investigate a possible link between venous drainage and ventriculomegaly in both normal ageing and pathological conditions, we compared 225 healthy subjects (137 males and 88 females) and 71 traumatic brain injury patients of varying ages (53 males and 18 females) using MRI-based volumetry and a novel perfusion-timing analysis. Volumetry, focusing on the CSF space, revealed that the sulcal space and ventricular size presented different lifespan profiles with age; the latter presented a quadratic, rather than linear, pattern of increase. The venous timing shift slightly preceded this change, supporting a role for venous drainage in ventriculomegaly. In traumatic brain injury, a small but significant disease effect, similar to idiopathic normal pressure hydrocephalus, was found in venous timing, but it tended to decrease with age at injury, suggesting an overlapping mechanism with normal ageing. Structural bias due to, or a direct causative role of ventriculomegaly was unlikely to play a dominant role, because of the low correlation between venous timing and ventricular size after adjustment for age in both patients and controls. Since post-traumatic hydrocephalus can be asymptomatic and occasionally overlooked, the observation suggested a link between venous drainage and CSF accumulation. Thus, hydrocephalus, involving venous insufficiency, may be a part of normal ageing, can be detected non-invasively, and is potentially treatable. Further investigation into the clinical application of this new marker of venous function is therefore warranted.

When your brain looks older than expected: combined lifestyle risk and BrainAGE

Lifestyle may be one source of unexplained variance in the great interindividual variability of the brain in age-related structural differences. While physical and social activity may protect against structural decline, other lifestyle behaviors may be accelerating factors. We examined whether riskier lifestyle correlates with accelerated brain aging using the BrainAGE score in 622 older adults from the 1000BRAINS cohort. Lifestyle was measured using a combined lifestyle risk score, composed of risk (smoking, alcohol intake) and protective variables (social integration and physical activity). We estimated individual BrainAGE from T1-weighted MRI data indicating accelerated brain atrophy by higher values. Then, the effect of combined lifestyle risk and individual lifestyle variables was regressed against BrainAGE. One unit increase in combined lifestyle risk predicted 5.04 months of additional BrainAGE. This prediction was driven by smoking (0.6 additional months of BrainAGE per pack-year) and physical activity (0.55 less months in BrainAGE per metabolic equivalent). Stratification by sex revealed a stronger association between physical activity and BrainAGE in males than females. Overall, our observations may be helpful with regard to lifestyle-related tailored prevention measures that slow changes in brain structure in older adults.

A Comparison of Quantitative R1 and Cortical Thickness in Identifying Age, Lifespan Dynamics, and Disease States of the Human Cortex

Brain development and aging are complex processes that unfold in multiple brain regions simultaneously. Recently, models of brain age prediction have aroused great interest, as these models can potentially help to understand neurological diseases and elucidate basic neurobiological mechanisms. We test whether quantitative magnetic resonance imaging can contribute to such age prediction models. Using R1, the longitudinal rate of relaxation, we explore lifespan dynamics in cortical gray matter. We compare R1 with cortical thickness, a well-established biomarker of brain development and aging. Using 160 healthy individuals (6-81 years old), we found that R1 and cortical thickness predicted age similarly, but the regions contributing to the prediction differed. Next, we characterized R1 development and aging dynamics. Compared with anterior regions, in posterior regions we found an earlier R1 peak but a steeper postpeak decline. We replicate these findings: firstly, we tested a subset (N = 10) of the original dataset for whom we had additional scans at a lower resolution; and second, we verified the results on an independent dataset (N = 34). Finally, we compared the age prediction models on a subset of 10 patients with multiple sclerosis. The patients are predicted older than their chronological age using R1 but not with cortical thickness.

Improving Individual Brain Age Prediction Using an Ensemble Deep Learning Framework

Brain age is an imaging-based biomarker with excellent feasibility for characterizing individual brain health and may serve as a single quantitative index for clinical and domain-specific usage. Brain age has been successfully estimated using extensive neuroimaging data from healthy participants with various feature extraction and conventional machine learning (ML) approaches. Recently, several end-to-end deep learning (DL) analytical frameworks have been proposed as alternative approaches to predict individual brain age with higher accuracy. However, the optimal approach to select and assemble appropriate input feature sets for DL analytical frameworks remains to be determined. In the Predictive Analytics Competition 2019, we proposed a hierarchical analytical framework which first used ML algorithms to investigate the potential contribution of different input features for predicting individual brain age. The obtained information then served as a priori knowledge for determining the input feature sets of the final ensemble DL prediction model. Systematic evaluation revealed that ML approaches with multiple concurrent input features, including tissue volume and density, achieved higher prediction accuracy when compared with approaches with a single input feature set [Ridge regression: mean absolute error (MAE) = 4.51 years, R ² = 0.88; support vector regression, MAE = 4.42 years, R ² = 0.88]. Based on this evaluation, a final ensemble DL brain age prediction model integrating multiple feature sets was constructed with reasonable computation capacity and achieved higher prediction accuracy when compared with ML approaches in the training dataset (MAE = 3.77 years; R ² = 0.90). Furthermore, the proposed ensemble DL brain age prediction model also demonstrated sufficient generalizability in the testing dataset (MAE = 3.33 years). In summary, this study provides initial evidence of how-to efficiency for integrating ML and advanced DL approaches into a unified analytical framework for predicting individual brain age with higher accuracy. With the increase in large open multiple-modality neuroimaging datasets, ensemble DL strategies with appropriate input feature sets serve as a candidate approach for predicting individual brain age in the future.

Correlation Constraints for Regression Models: Controlling Bias in Brain Age Prediction

In neuroimaging, the difference between chronological age and predicted brain age, also known as brain age delta, has been proposed as a pathology marker linked to a range of phenotypes. Brain age delta is estimated using regression, which involves a frequently observed bias due to a negative correlation between chronological age and brain age delta. In brain age prediction models, this correlation can manifest as an overprediction of the age of young brains and an underprediction for elderly ones. We show that this bias can be controlled for by adding correlation constraints to the model training procedure. We develop an analytical solution to this constrained optimization problem for Linear, Ridge, and Kernel Ridge regression. The solution is optimal in the least-squares sense i.e., there is no other model that satisfies the correlation constraints and has a better fit. Analyses on the PAC2019 competition data demonstrate that this approach produces optimal unbiased predictive models with a number of advantages over existing approaches. Finally, we introduce regression toolboxes for Python and MATLAB that implement our algorithm.

Neuroimaging-based brain-age prediction in diverse forms of epilepsy: a signature of psychosis and beyond

Epilepsy is a diverse brain disorder, and the pathophysiology of its various forms and comorbidities is largely unknown. A recent machine learning method enables us to estimate an individual's "brain-age" from MRI; this brain-age prediction is expected as a novel individual biomarker of neuropsychiatric disorders. The aims of this study were to estimate the brain-age for various categories of epilepsy and to evaluate clinical discrimination by brain-age for (1) the effect of psychosis on temporal lobe epilepsy (TLE), (2) psychogenic nonepileptic seizures (PNESs) from MRI-negative epilepsies, and (3) progressive myoclonic epilepsy (PME) from juvenile myoclonic epilepsy (JME). In total, 1196 T1-weighted MRI scans from healthy controls (HCs) were used to build a brain-age prediction model with support vector regression. Using the model, we calculated the brain-predicted age difference (brain-PAD: predicted age-chronological age) of the HCs and 318 patients with epilepsy. We compared the brain-PAD values based on the research questions. As a result, all categories of patients except for extra-temporal lobe focal epilepsy showed a significant increase in brain-PAD. TLE with hippocampal sclerosis presented a significantly higher brain-PAD than several other categories. The mean brain-PAD in TLE with inter-ictal psychosis was 10.9 years, which was significantly higher than TLE without psychosis (5.3 years). PNES showed a comparable mean brain-PAD (10.6 years) to that of epilepsy patients. PME had a higher brain-PAD than JME (22.0 vs. 9.3 years). In conclusion, neuroimaging-based brain-age prediction can provide novel insight into or clinical usefulness for the diverse symptoms of epilepsy.

Deep learning for brain disorders: from data processing to disease treatment

In order to reach precision medicine and improve patients' quality of life, machine learning is increasingly used in medicine. Brain disorders are often complex and heterogeneous, and several modalities such as demographic, clinical, imaging, genetics and environmental data have been studied to improve their understanding. Deep learning, a subpart of machine learning, provides complex algorithms that can learn from such various data. It has become state of the art in numerous fields, including computer vision and natural language processing, and is also growingly applied in medicine. In this article, we review the use of deep learning for brain disorders. More specifically, we identify the main applications, the concerned disorders and the types of architectures and data used. Finally, we provide guidelines to bridge the gap between research studies and clinical routine.

Disentangled-Multimodal Adversarial Autoencoder: Application to Infant Age Prediction With Incomplete Multimodal Neuroimages

Effective fusion of structural magnetic resonance imaging (sMRI) and functional magnetic resonance imaging (fMRI) data has the potential to boost the accuracy of infant age prediction thanks to the complementary information provided by different imaging modalities. However, functional connectivity measured by fMRI during infancy is largely immature and noisy compared to the morphological features from sMRI, thus making the sMRI and fMRI fusion for infant brain analysis extremely challenging. With the conventional multimodal fusion strategies, adding fMRI data for age prediction has a high risk of introducing more noises than useful features, which would lead to reduced accuracy than that merely using sMRI data. To address this issue, we develop a novel model termed as disentangled-multimodal adversarial autoencoder (DMM-AAE) for infant age prediction based on multimodal brain MRI. Specifically, we disentangle the latent variables of autoencoder into common and specific codes to represent the shared and complementary information among modalities, respectively. Then, cross-reconstruction requirement and common-specific distance ratio loss are designed as regularizations to ensure the effectiveness and thoroughness of the disentanglement. By arranging relatively independent autoencoders to separate the modalities and employing disentanglement under cross-reconstruction requirement to integrate them, our DMM-AAE method effectively restrains the possible interference cross modalities, while realizing effective information fusion. Taking advantage of the latent variable disentanglement, a new strategy is further proposed and embedded into DMM-AAE to address the issue of incompleteness of the multimodal neuroimages, which can also be used as an independent algorithm for missing modality imputation. By taking six types of cortical morphometric features from sMRI and brain functional connectivity from fMRI as predictors, the superiority of the proposed DMM-AAE is validated on infant age (35 to 848 days after birth) prediction using incomplete multimodal neuroimages. The mean absolute error of the prediction based on DMM-AAE reaches 37.6 days, outperforming state-of-the-art methods. Generally, our proposed DMM-AAE can serve as a promising model for prediction with multimodal data.

Applications of Convolutional Neural Networks in neurodegeneration and physiological aging

The process of aging is linked with significant changes in a human's physiological organization and structure. This is more evident in the case of the brain whose functions generally vary between young and old individuals. Detecting such patterns can be of significant importance especially during the Mild Cognitive Impairment (MCI) stage which is a transition state before the clinical onset of dementia. Intervening in that stage may delay or eventually prevent dementia onset. In this paper we propose a new methodology based in electroencephalographic (EEG) recordings, aiming to classify individuals into healthy, pathological (patients diagnosed with MCI or Mild Dementia) and young, old groups (healthy individuals over and under 50 years of age) through functional connectivity and macro-architecture features. These features are calculated on the estimated brain region activations through the inverse problem solution, enabling us to transform the sensor level EEG recordings through an appropriate transformation matrix. Afterwards, Synchronization Likelihood and Relative Wavelet Entropy values were calculated along with the graph metrics corresponding to the functional connectivity values, as well as the relative energy contributions of five EEG bands (delta, theta, alpha, beta and gamma). These features were organized in Red, Green, Blue (RGB) image-like data structures. Therefore, it was possible to classify each individual into one of the two groups per experiment employing Convolutional Neural Networks. From the maximum classification accuracy achieved on the test set, 90.48% for the pathological aging group and 91.19% for the physiological aging, it is evident that the proposed approach is capable of providing adequate health and age group classification.

Accelerated MRI-predicted brain ageing and its associations with cardiometabolic and brain disorders

Brain structure in later life reflects both influences of intrinsic aging and those of lifestyle, environment and disease. We developed a deep neural network model trained on brain MRI scans of healthy people to predict "healthy" brain age. Brain regions most informative for the prediction included the cerebellum, hippocampus, amygdala and insular cortex. We then applied this model to data from an independent group of people not stratified for health. A phenome-wide association analysis of over 1,410 traits in the UK Biobank with differences between the predicted and chronological ages for the second group identified significant associations with over 40 traits including diseases (e.g., type I and type II diabetes), disease risk factors (e.g., increased diastolic blood pressure and body mass index), and poorer cognitive function. These observations highlight relationships between brain and systemic health and have implications for understanding contributions of the latter to late life dementia risk.

Comparison of Clinical Outcomes 1 and 5 Years Post-Injury Following Combat Concussion

OBJECTIVE

To compare 1-year and 5-year clinical outcomes in 2 groups of combat-deployed service members without brain injury to those of 2 groups with combat-related concussion to better understand long-term clinical outcome trajectories.

METHODS

This prospective, observational, longitudinal multicohort study examined 4 combat-deployed groups: controls without head injury with or without blast exposure and patients with combat concussion arising from blast or blunt trauma. One-year and 5-year clinical evaluations included identical batteries for neurobehavioral, psychiatric, and cognitive outcomes. A total of 347 participants completed both time points of evaluation. Cross-sectional and longitudinal comparisons were assessed. Overall group effect was modeled as a 4-category variable with rank regression adjusting for demographic factors using a 2-sided significance threshold of 0.05, with post hoc Tukey p values calculated for the pairwise comparisons.

RESULTS

Significant group differences in both combat concussion groups were identified cross-sectionally at 5-year follow-up compared to controls in neurobehavioral (Neurobehavioral Rating Scale-Revised [NRS]; Cohen d, -1.10 to -1.40, confidence intervals [CIs] [-0.82, -1.32] to [-0.97, -1.83] by group) and psychiatric domains (Clinician-Administered PTSD Scale for DSM-IV [CAPS]; Cohen d, -0.91 to -1.19, CIs [-0.63, -1.19] to [-0.76, -1.62] by group) symptoms with minimal differences in cognitive performance. Both combat concussion groups also showed clinically significant decline from 1- to 5-year evaluation (66%-76% neurobehavioral NRS; 41%-54% psychiatric CAPS by group). Both control groups fared better but a subset also had clinically significant decline (37%-50% neurobehavioral NRS; 9%-25% psychiatric CAPS by group).

CONCLUSIONS

There was an evolution, not resolution, of symptoms from 1- to 5-year evaluation, challenging the assumption that chronic stages of concussive injury are relatively stable. Even some of the combat-deployed controls worsened. The evidence supports new considerations for chronic trajectories of concussion outcome in combat-deployed service members.

Brain Age Prediction of Children Using Routine Brain MR Images via Deep Learning

Predicting brain age of children accurately and quantitatively can give help in brain development analysis and brain disease diagnosis. Traditional methods to estimate brain age based on 3D magnetic resonance (MR), T1 weighted imaging (T1WI), and diffusion tensor imaging (DTI) need complex preprocessing and extra scanning time, decreasing clinical practice, especially in children. This research aims at proposing an end-to-end AI system based on deep learning to predict the brain age based on routine brain MR imaging. We spent over 5 years enrolling 220 stacked 2D routine clinical brain MR T1-weighted images of healthy children aged 0 to 5 years old and randomly divided those images into training data including 176 subjects and test data including 44 subjects. Data augmentation technology, which includes scaling, image rotation, translation, and gamma correction, was employed to extend the training data. A 10-layer 3D convolutional neural network (CNN) was designed for predicting the brain age of children and it achieved reliable and accurate results on test data with a mean absolute deviation (MAE) of 67.6 days, a root mean squared error (RMSE) of 96.1 days, a mean relative error (MRE) of 8.2%, a correlation coefficient (R) of 0.985, and a coefficient of determination (R 2) of 0.971. Specially, the performance on predicting the age of children under 2 years old with a MAE of 28.9 days, a RMSE of 37.0 days, a MRE of 7.8%, a R of 0.983, and a R 2 of 0.967 is much better than that over 2 with a MAE of 110.0 days, a RMSE of 133.5 days, a MRE of 8.2%, a R of 0.883, and a R 2 of 0.780.

Machine learning and individual variability in electric field characteristics predict tDCS treatment response

BACKGROUND

Transcranial direct current stimulation (tDCS) is widely investigated as a therapeutic tool to enhance cognitive function in older adults with and without neurodegenerative disease. Prior research demonstrates that electric current delivery to the brain can vary significantly across individuals. Quantification of this variability could enable person-specific optimization of tDCS outcomes. This pilot study used machine learning and MRI-derived electric field models to predict working memory improvements as a proof of concept for precision cognitive intervention.

METHODS

Fourteen healthy older adults received 20 minutes of 2 mA tDCS stimulation (F3/F4) during a two-week cognitive training intervention. Participants performed an N-back working memory task pre-/post-intervention. MRI-derived current models were passed through a linear Support Vector Machine (SVM) learning algorithm to characterize crucial tDCS current components (intensity and direction) that induced working memory improvements in tDCS responders versus non-responders.

MAIN RESULTS

SVM models of tDCS current components had 86% overall accuracy in classifying treatment responders vs. non-responders, with current intensity producing the best overall model differentiating changes in working memory performance. Median current intensity and direction in brain regions near the electrodes were positively related to intervention responses (r=0.811,p<0.001 and r=0.774,p=0.001).

CONCLUSIONS

This study provides the first evidence that pattern recognition analyses of MRI-derived tDCS current models can provide individual prognostic classification of tDCS treatment response with 86% accuracy. Individual differences in current intensity and direction play important roles in determining treatment response to tDCS. These findings provide important insights into mechanisms of tDCS response as well as proof of concept for future precision dosing models of tDCS intervention.

Pre-injury health status and excess mortality in persons with traumatic brain injury: A decade-long historical cohort study

An increasing number of patients are able to survive traumatic brain injuries (TBIs) with advanced resuscitation. However, the role of their pre-injury health status in mortality in the following years is not known. Here, we followed 77,088 consecutive patients (59% male) who survived the TBI event in Ontario, Canada for more than a decade, and examined the relationships between their pre-injury health status and mortality rates in excess to the expected mortality calculated using sex- and age-specific life tables. There were 5792 deaths over the studied period, 3163 (6.95%) deaths in male and 2629 (8.33%) in female patients. The average excess mortality rate over the follow-up period of 14 years was 1.81 (95% confidence interval = 1.76-1.86). Analyses of follow-up time windows showed different patterns for the average excess rate of mortality following TBI, with the greatest rates observed in year one after injury. Among identified pre-injury comorbidity factors, 33 were associated with excess mortality rates. These rates were comparable between sexes. Additional analyses in the validation dataset confirmed that these findings were unlikely a result of TBI misclassification or unmeasured confounding. Thus, detection and subsequent management of pre-injury health status should be an integral component of any strategy to reduce excess mortality in TBI patients. The complexity of pre-injury comorbidity calls for integration of multidisciplinary health services to meet TBI patients' needs and prevent adverse outcomes.

Fetal brain age estimation and anomaly detection using attention-based deep ensembles with uncertainty

MRI-based brain age prediction has been widely used to characterize normal brain development, and deviations from the typical developmental trajectory are indications of brain abnormalities. Age prediction of the fetal brain remains unexplored, although it can be of broad interest to prenatal examination given the limited diagnostic tools available for assessment of the fetal brain. In this work, we built an attention-based deep residual network based on routine clinical T2-weighted MR images of 659 fetal brains, which achieved an overall mean absolute error of 0.767 weeks and R² of 0.920 in fetal brain age prediction. The predictive uncertainty and estimation confidence were simultaneously quantified from the network as markers for detecting fetal brain anomalies using an ensemble method. The novel markers overcame the limitations in conventional brain age estimation and demonstrated promising diagnostic power in differentiating several types of fetal abnormalities, including small head circumference, malformations and ventriculomegaly with the area under the curve of 0.90, 0.90 and 0.67, respectively. In addition, attention maps were derived from the network, which revealed regional features that contributed to fetal age estimation at each gestational stage. The proposed attention-based deep ensembles demonstrated superior performance in fetal brain age estimation and fetal anomaly detection, which has the potential to be translated to prenatal diagnosis in clinical practice.

Loss of the Antimicrobial Peptide Metchnikowin Protects Against Traumatic Brain Injury Outcomes in Drosophila melanogaster

Neuroinflammation is a major pathophysiological feature of traumatic brain injury (TBI). Early and persistent activation of innate immune response signaling pathways by primary injuries is associated with secondary cellular injuries that cause TBI outcomes to change over time. We used a Drosophila melanogaster model to investigate the role of antimicrobial peptides (AMPs) in acute and chronic outcomes of closed-head TBI. AMPs are effectors of pathogen and stress defense mechanisms mediated by the evolutionarily conserved Toll and Immune-deficiency (Imd) innate immune response pathways that activate Nuclear Factor kappa B (NF-κB) transcription factors. Here, we analyzed the effect of null mutations in 10 of the 14 known Drosophila AMP genes on TBI outcomes. We found that mutation of Metchnikowin (Mtk) was unique in protecting flies from mortality within the 24 h following TBI under two diet conditions that produce different levels of mortality. In addition, Mtk mutants had reduced behavioral deficits at 24 h following TBI and increased lifespan either in the absence or presence of TBI. Using a transcriptional reporter of gene expression, we found that TBI increased Mtk expression in the brain. Quantitative analysis of mRNA in whole flies revealed that expression of other AMPs in the Toll and Imd pathways as well as NF-κB transcription factors were not altered in Mtk mutants. Overall, these results demonstrate that Mtk plays an infection-independent role in the fly nervous system, and TBI-induced expression of Mtk in the brain activates acute and chronic secondary injury pathways that are also activated during normal aging.

An automated machine learning approach to predict brain age from cortical anatomical measures

The use of machine learning (ML) algorithms has significantly increased in neuroscience. However, from the vast extent of possible ML algorithms, which one is the optimal model to predict the target variable? What are the hyperparameters for such a model? Given the plethora of possible answers to these questions, in the last years, automated ML (autoML) has been gaining attention. Here, we apply an autoML library called Tree-based Pipeline Optimisation Tool (TPOT) which uses a tree-based representation of ML pipelines and conducts a genetic programming-based approach to find the model and its hyperparameters that more closely predicts the subject's true age. To explore autoML and evaluate its efficacy within neuroimaging data sets, we chose a problem that has been the focus of previous extensive study: brain age prediction. Without any prior knowledge, TPOT was able to scan through the model space and create pipelines that outperformed the state-of-the-art accuracy for Freesurfer-based models using only thickness and volume information for anatomical structure. In particular, we compared the performance of TPOT (mean absolute error [MAE]: 4.612 ± .124 years) and a relevance vector regression (MAE 5.474 ± .140 years). TPOT also suggested interesting combinations of models that do not match the current most used models for brain prediction but generalise well to unseen data. AutoML showed promising results as a data-driven approach to find optimal models for neuroimaging applications.

A 3D Tissue Model of Traumatic Brain Injury with Excitotoxicity That Is Inhibited by Chronic Exposure to Gabapentinoids

Injury progression associated with cerebral laceration is insidious. Following the initial trauma, brain tissues become hyperexcitable, begetting further damage that compounds the initial impact over time. Clinicians have adopted several strategies to mitigate the effects of secondary brain injury; however, higher throughput screening tools with modular flexibility are needed to expedite mechanistic studies and drug discovery that will contribute to the enhanced protection, repair, and even the regeneration of neural tissues. Here we present a novel bioengineered cortical brain model of traumatic brain injury (TBI) that displays characteristics of primary and secondary injury, including an outwardly radiating cell death phenotype and increased glutamate release with excitotoxic features. DNA content and tissue function were normalized by high-concentration, chronic administrations of gabapentinoids. Additional experiments suggested that the treatment effects were likely neuroprotective rather than regenerative, as evidenced by the drug-mediated decreases in cell excitability and an absence of drug-induced proliferation. We conclude that the present model of traumatic brain injury demonstrates validity and can serve as a customizable experimental platform to assess the individual contribution of cell types on TBI progression, as well as to screen anti-excitotoxic and pro-regenerative compounds.

Structure-Function Connectomics Reveals Aberrant Developmental Trajectory Occurring at Preadolescence in the Autistic Brain

Accumulating neuroimaging evidence shows that age estimation obtained from brain connectomics reflects the level of brain maturation along with neural development. It is well known that autism spectrum disorder (ASD) alters neurodevelopmental trajectories of brain connectomics, but the precise relationship between chronological age (ChA) and brain connectome age (BCA) during development in ASD has not been addressed. This study uses neuroimaging data collected from 50 individuals with ASD and 47 age- and gender-matched typically developing controls (TDCs; age range: 5-18 years). Both functional and structural connectomics were assessed using resting-state functional magnetic resonance imaging and diffusion tensor imaging data from the Autism Brain Imaging Data Exchange repository. For each participant, BCA was estimated from structure-function connectomics through linear support vector regression. We found that BCA matched well with ChA in TDC children and adolescents, but not in ASD. In particular, our findings revealed that individuals with ASD exhibited accelerated brain maturation in youth, followed by a delay of brain development starting at preadolescence. Our results highlight the critical role of BCA in understanding aberrant developmental trajectories in ASD and provide the new insights into the pathophysiological mechanisms of this disorder.

Dynamic neural and glial responses of a head-specific model for traumatic brain injury in Drosophila

Traumatic brain injury (TBI) is the strongest environmental risk factor for the accelerated development of neurodegenerative diseases. There are currently no therapeutics to address this due to lack of insight into mechanisms of injury progression, which are challenging to study in mammalian models. Here, we have developed and extensively characterized a head-specific approach to TBI in Drosophila, a powerful genetic system that shares many conserved genes and pathways with humans. The Drosophila TBI (dTBI) device inflicts mild, moderate, or severe brain trauma by precise compression of the head using a piezoelectric actuator. Head-injured animals display features characteristic of mammalian TBI, including severity-dependent ataxia, life span reduction, and brain degeneration. Severe dTBI is associated with cognitive decline and transient glial dysfunction, and stimulates antioxidant, proteasome, and chaperone activity. Moreover, genetic or environmental augmentation of the stress response protects from severe dTBI-induced brain degeneration and life span deficits. Together, these findings present a tunable, head-specific approach for TBI in Drosophila that recapitulates mammalian injury phenotypes and underscores the ability of the stress response to mitigate TBI-induced brain degeneration.

Nonlinear biomarker interactions in conversion from mild cognitive impairment to Alzheimer's disease

Multiple biomarkers can capture different facets of Alzheimer's disease. However, statistical models of biomarkers to predict outcomes in Alzheimer's rarely model nonlinear interactions between these measures. Here, we used Gaussian Processes to address this, modelling nonlinear interactions to predict progression from mild cognitive impairment (MCI) to Alzheimer's over 3 years, using Alzheimer's Disease Neuroimaging Initiative (ADNI) data. Measures included: demographics, APOE4 genotype, CSF (amyloid‐β42, total tau, phosphorylated tau), [18^F]florbetapir, hippocampal volume and brain‐age. We examined: (a) the independent value of each biomarker; and (b) whether modelling nonlinear interactions between biomarkers improved predictions. Each measured added complementary information when predicting conversion to Alzheimer's. A linear model classifying stable from progressive MCI explained over half the variance (R² = 0.51, p < .001); the strongest independently contributing biomarker was hippocampal volume (R² = 0.13). When comparing sensitivity of different models to progressive MCI (independent biomarker models, additive models, nonlinear interaction models), we observed a significant improvement (p < .001) for various two‐way interaction models. The best performing model included an interaction between amyloid‐β‐PET and P‐tau, while accounting for hippocampal volume (sensitivity = 0.77, AUC = 0.826). Closely related biomarkers contributed uniquely to predict conversion to Alzheimer's. Nonlinear biomarker interactions were also implicated, and results showed that although for some patients adding additional biomarkers may add little value (i.e., when hippocampal volume is high), for others (i.e., with low hippocampal volume) further invasive and expensive examination may be warranted. Our framework enables visualisation of these interactions, in individual patient biomarker ‘space', providing information for personalised or stratified healthcare or clinical trial design.

Estimating brain age based on a uniform healthy population with deep learning and structural magnetic resonance imaging

Numerous studies have established that estimated brain age constitutes a valuable biomarker that is predictive of cognitive decline and various neurological diseases. In this work, we curate a large-scale brain MRI data set of healthy individuals, on which we train a uniform deep learning model for brain age estimation. We demonstrate an age estimation accuracy on a hold-out test set (mean absolute error = 4.06 years, r = 0.970) and an independent life span evaluation data set (mean absolute error = 4.21 years, r = 0.960). We further demonstrate the utility of the estimated age in a life span aging analysis of cognitive functions. In summary, we achieve age estimation performance comparable to previous studies, but with a more heterogenous data set confirming the efficacy of this deep learning framework. We also evaluated training with varying age distributions. The analysis of regional contributions to our brain age predictions through multiple analyses, and confirmation of the association of divergence between the estimated and chronological brain age with neuropsychological measures, may be useful in the development and evaluation of similar imaging biomarkers.