Differences between chronological and brain age are related to education and self-reported physical activity

Accelerated brain aging in major depressive disorder and antidepressant treatment response: A CAN-BIND report

OBJECTIVES

Previous studies suggest that major depressive disorder (MDD) may be associated with volumetric indications of accelerated brain aging. This study investigated neuroanatomical signs of accelerated aging in MDD and evaluated whether a brain age gap is associated with antidepressant response.

METHODS

Individuals in a major depressive episode received escitalopram treatment (10-20 mg/d) for 8 weeks. Depression severity was assessed at baseline and at weeks 8 and 16 using the Montgomery-Asberg Depression Rating Scale (MADRS). Response to treatment was characterized by a significant reduction in the MADRS (≥50%). Nonresponders received adjunctive aripiprazole treatment (2-10 mg/d) for a further 8 weeks. The brain-predicted age difference (brain-PAD) at baseline was determined using machine learning methods trained on 3377 healthy individuals from seven publicly available datasets. The model used features from all brain regions extracted from structural magnetic resonance imaging data.

RESULTS

Brain-PAD was significantly higher in older MDD participants compared to younger MDD participants [t(147.35) = -2.35, p < 0.03]. BMI was significantly associated with brain-PAD in the MDD group [r(155) = 0.19, p < 0.03]. Response to treatment was not significantly associated with brain-PAD.

CONCLUSION

We found an elevated brain age gap in older individuals with MDD. Brain-PAD was not associated with overall treatment response to escitalopram monotherapy or escitalopram plus adjunctive aripiprazole.

Machine learning for brain age prediction: Introduction to methods and clinical applications

The rise of machine learning has unlocked new ways of analysing structural neuroimaging data, including brain age prediction. In this state-of-the-art review, we provide an introduction to the methods and potential clinical applications of brain age prediction. Studies on brain age typically involve the creation of a regression machine learning model of age-related neuroanatomical changes in healthy people. This model is then applied to new subjects to predict their brain age. The difference between predicted brain age and chronological age in a given individual is known as ‘brain-age gap’. This value is thought to reflect neuroanatomical abnormalities and may be a marker of overall brain health. It may aid early detection of brain-based disorders and support differential diagnosis, prognosis, and treatment choices. These applications could lead to more timely and more targeted interventions in age-related disorders.

Using Deep Neural Networks for Predicting Age and Sex in Healthy Adult Chest Radiographs

Background: The performance of chest radiography-based age and sex prediction has not been well validated. We used a deep learning model to predict the age and sex of healthy adults based on chest radiographs (CXRs). Methods: In this retrospective study, 66,643 CXRs of 47,060 healthy adults were used for model training and testing. In total, 47,060 individuals (mean age ± standard deviation, 38.7 ± 11.9 years; 22,144 males) were included. By using chronological ages as references, mean absolute error (MAE), root mean square error (RMSE), and Pearson’s correlation coefficient were used to assess the model performance. Summarized class activation maps were used to highlight the activated anatomical regions. The area under the curve (AUC) was used to examine the validity for sex prediction. Results: When model predictions were compared with the chronological ages, the MAE was 2.1 years, RMSE was 2.8 years, and Pearson’s correlation coefficient was 0.97 (p < 0.001). Cervical, thoracic spines, first ribs, aortic arch, heart, rib cage, and soft tissue of thorax and flank seemed to be the most crucial activated regions in the age prediction model. The sex prediction model demonstrated an AUC of >0.99. Conclusion: Deep learning can accurately estimate age and sex based on CXRs.

Quantifying neural efficiency and neural capacity across the brain during a working memory task using a quadratic model of neural-cognitive relationships

Task-based functional magnetic resonance imaging (MRI) neuroimaging for the study of cognitive neuroscience provides insight into how the brain responds to increasing cognitive demands. Theoretical models of neural-cognitive relationships define neural efficiency and neural capacity as two parameters to describe the rate of gain of brain activity and the upper limits of the increases, respectively. Although qualitatively well described, there are limited discussions and demonstrations of estimating these parameters from data. The current work presents a method using a quadratic equation model of cognitive demands. The methods were applied to 21 healthy young adults while engaging in four levels of the verbal n-back working memory task (0, 1, 2 and 3-back). Measures of the area under the curve captured both linear and curvilinear responses to quantify the locations and amounts of task-related increases in brain activity. In addition, we calculated voxel-wise maps of neural efficiency and neural capacity. Results showed increases in brain activation in regions typically involved in working memory. The relationships between increasing cognitive demands and brain activity also differed across the brain within and between individuals, as indicated by differential neural efficiency and neural capacity values. This approach provides tools for evaluating current theories about the relationships between brain activity and cognition. Neural efficiency and neural capacity provide physiological measures of brain activity, which will help evaluate how age, disease and intervention processes affect brain activity. Finally, all presented methods are readily applicable using standard current software packages for neuroimaging.

Advanced brain ageing in Parkinson's disease is related to disease duration and individual impairment

Machine learning can reliably predict individual age from MRI data, revealing that patients with neurodegenerative disorders show an elevated biological age. A surprising gap in the literature, however, pertains to Parkinson's disease. Here, we evaluate brain age in two cohorts of Parkinson's patients and investigated the relationship between individual brain age and clinical characteristics. We assessed 372 patients with idiopathic Parkinson's disease, newly diagnosed cases from the Parkinson's Progression Marker Initiative database and a more chronic local sample, as well as age- and sex-matched healthy controls. Following morphometric preprocessing and atlas-based compression, individual brain age was predicted using a multivariate machine learning model trained on an independent, multi-site reference sample. Across cohorts, healthy controls were well predicted with a mean error of 4.4 years. In turn, Parkinson's patients showed a significant (controlling for age, gender and site) increase in brain age of ∼3 years. While this effect was already present in the newly diagnosed sample, advanced biological age was significantly related to disease duration as well as worse cognitive and motor impairment. While biological age is increased in patients with Parkinson's disease, the effect is at the lower end of what is found for other neurological and psychiatric disorders. We argue that this may reflect a heterochronicity between forebrain atrophy and small but behaviourally salient midbrain pathology. Finally, we point to the need to disentangle physiological ageing trajectories, lifestyle effects and core pathological changes.

Effects of a Brief Stair-Climbing Intervention on Cognitive Functioning and Mood States in Older Adults: A Randomized Controlled Trial

Despite an abundance of evidence that exercise benefits cognition and mood, physical activity levels among older adults remain low, with time and inaccessibility posing major barriers. Interval stair climbing is an accessible time-efficient form of physical activity demonstrated to benefit cognition and mood in young adults, but effectiveness in older adults remains unknown. To address this, 28 older adults (Mage = 69.78 years, 16 females) undertook cognitive and mood assessments twice, 1 week apart, once preceded by interval stair climbing. A fairly large, albeit only marginally significant, effect size (ηp2=.12) indicated improved cognition following the moderate- to high-intensity intervention; however, rather than improving mood, older adults reported feeling more tired (g = 0.51). These outcomes provide initial indications that this mode of exercise that can easily translate to naturalistic settings offers promise as an intervention strategy, but more research is needed to optimize the protocol to suit aged populations (ACTRN1261900169014).

Accelerated functional brain aging in pre-clinical familial Alzheimer's disease

Resting state functional connectivity (rs-fMRI) is impaired early in persons who subsequently develop Alzheimer's disease (AD) dementia. This impairment may be leveraged to aid investigation of the pre-clinical phase of AD. We developed a model that predicts brain age from resting state (rs)-fMRI data, and assessed whether genetic determinants of AD, as well as beta-amyloid (Aβ) pathology, can accelerate brain aging. Using data from 1340 cognitively unimpaired participants between 18-94 years of age from multiple sites, we showed that topological properties of graphs constructed from rs-fMRI can predict chronological age across the lifespan. Application of our predictive model to the context of pre-clinical AD revealed that the pre-symptomatic phase of autosomal dominant AD includes acceleration of functional brain aging. This association was stronger in individuals having significant Aβ pathology.

Measuring Resilience and Resistance in Aging and Alzheimer Disease Using Residual Methods: A Systematic Review and Meta-analysis

BACKGROUND AND OBJECTIVE

There is a lack of consensus on how to optimally define and measure resistance and resilience in brain and cognitive aging. Residual methods use residuals from regression analysis to quantify the capacity to avoid (resistance) or cope (resilience) "better or worse than expected" given a certain level of risk or cerebral damage. We reviewed the rapidly growing literature on residual methods in the context of aging and Alzheimer disease (AD) and performed meta-analyses to investigate associations of residual method-based resilience and resistance measures with longitudinal cognitive and clinical outcomes.

METHODS

A systematic literature search of PubMed and Web of Science databases (consulted until March 2020) and subsequent screening led to 54 studies fulfilling eligibility criteria, including 10 studies suitable for the meta-analyses.

RESULTS

We identified articles using residual methods aimed at quantifying resistance (n = 33), cognitive resilience (n = 23), and brain resilience (n = 2). Critical examination of the literature revealed that there is considerable methodologic variability in how the residual measures were derived and validated. Despite methodologic differences across studies, meta-analytic assessments showed significant associations of levels of resistance (hazard ratio [HR] [95% confidence interval (CI)] 1.12 [1.07-1.17]; p < 0.0001) and levels of resilience (HR [95% CI] 0.46 [0.32-0.68]; p < 0.001) with risk of progression to dementia/AD. Resilience was also associated with rate of cognitive decline (β [95% CI] 0.05 [0.01-0.08]; p < 0.01).

DISCUSSION

This review and meta-analysis supports the usefulness of residual methods as appropriate measures of resilience and resistance, as they capture clinically meaningful information in aging and AD. More rigorous methodologic standardization is needed to increase comparability across studies and, ultimately, application in clinical practice.

Exploring domains, clinical implications and environmental associations of a deep learning marker of biological ageing

Deep Neural Networks (DNN) have been recently developed for the estimation of Biological Age (BA), the hypothetical underlying age of an organism, which can differ from its chronological age (CA). Although promising, these population-specific algorithms warrant further characterization and validation, since their biological, clinical and environmental correlates remain largely unexplored. Here, an accurate DNN was trained to compute BA based on 36 circulating biomarkers in an Italian population (N = 23,858; age ≥ 35 years; 51.7% women). This estimate was heavily influenced by markers of metabolic, heart, kidney and liver function. The resulting Δage (BA-CA) significantly predicted mortality and hospitalization risk for all and specific causes. Slowed biological aging (Δage < 0) was associated with higher physical and mental wellbeing, healthy lifestyles (e.g. adherence to Mediterranean diet) and higher socioeconomic status (educational attainment, household income and occupational status), while accelerated aging (Δage > 0) was associated with smoking and obesity. Together, lifestyles and socioeconomic variables explained ~48% of the total variance in Δage, potentially suggesting the existence of a genetic basis. These findings validate blood-based biological aging as a marker of public health in adult Italians and provide a robust body of knowledge on its biological architecture, clinical implications and potential environmental influences.

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.

APPLAUSE: Automatic Prediction of PLAcental health via U-net Segmentation and statistical Evaluation

PURPOSE

Artificial-intelligence population-based automated quantification of placental maturation and health from a rapid functional Magnetic Resonance scan. The placenta plays a crucial role for any successful human pregnancy. Deviations from the normal dynamic maturation throughout gestation are closely linked to major pregnancy complications. Antenatal assessment in-vivo using T2* relaxometry has shown great promise to inform management and possible interventions but clinical translation is hampered by time consuming manual segmentation and analysis techniques based on comparison against normative curves over gestation.

METHODS

This study proposes a fully automatic pipeline to predict the biological age and health of the placenta based on a free-breathing rapid (sub-30 second) T2* scan in two steps: Automatic segmentation using a U-Net and a Gaussian process regression model to characterize placental maturation and health. These are trained and evaluated on 108 3T MRI placental data sets, the evaluation included 20 high-risk pregnancies diagnosed with pre-eclampsia and/or fetal growth restriction. An independent cohort imaged at 1.5 T is used to assess the generalization of the training and evaluation pipeline.

RESULTS

Across low- and high-risk groups, automatic segmentation performs worse than inter-rater performance (mean Dice coefficients of 0.58 and 0.68, respectively) but is sufficient for estimating placental mean T2* (0.986 Pearson Correlation Coefficient). The placental health prediction achieves an excellent ability to differentiate cases of placental insufficiency between 27 and 33 weeks. High abnormality scores correlate with low birth weight, premature birth and histopathological findings. Retrospective application on a different cohort imaged at 1.5 T illustrates the ability for direct clinical translation.

CONCLUSION

The presented automatic pipeline facilitates a fast, robust and reliable prediction of placental maturation. It yields human-interpretable and verifiable intermediate results and quantifies uncertainties on the cohort-level and for individual predictions. The proposed machine-learning pipeline runs in close to real-time and, deployed in clinical settings, has the potential to become a cornerstone of diagnosis and intervention of placental insufficiency. APPLAUSE generalizes to an independent cohort imaged at 1.5 T, demonstrating robustness to different operational and clinical environments.

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.

Linking objective measures of physical activity and capability with brain structure in healthy community dwelling older adults

Maintaining high levels of daily activity and physical capability have been proposed as important constituents to promote healthy brain and cognitive aging. Studies investigating the associations between brain health and physical activity in late life have, however, mainly been based on self-reported data or measures designed for clinical populations. In the current study, we examined cross-sectional associations between physical activity, recorded by an ankle-positioned accelerometer for seven days, physical capability (grip strength, postural control, and walking speed), and neuroimaging based surrogate markers of brain health in 122 healthy older adults aged 65-88 years. We used a multimodal brain imaging approach offering complementary structural MRI based indicators of brain health: global white matter fractional anisotropy (FA) and mean diffusivity (MD) based on diffusion tensor imaging, and subcortical and global brain age based on brain morphology inferred from T1-weighted MRI data. In addition, based on the results from the main analysis, follow-up regression analysis was performed to test for association between the volume of key subcortical regions of interest (hippocampus, caudate, thalamus and cerebellum) and daily steps, and a follow-up voxelwise analysis to test for associations between walking speed and FA across the white matter Tract-Based Spatial Statistics (TBSS) skeleton. The analyses revealed a significant association between global FA and walking speed, indicating higher white matter integrity in people with higher pace. Voxelwise analysis supported widespread significant associations. We also found a significant interaction between sex and subcortical brain age on number of daily steps, indicating younger-appearing brains in more physically active women, with no significant associations among men. These results provide insight into the intricate associations between different measures of brain and physical health in old age, and corroborate established public health advice promoting physical activity.

Contributing factors to advanced brain aging in depression and anxiety disorders

Depression and anxiety are common and often comorbid mental health disorders that represent risk factors for aging-related conditions. Brain aging has shown to be more advanced in patients with major depressive disorder (MDD). Here, we extend prior work by investigating multivariate brain aging in patients with MDD, anxiety disorders, or both, and examine which factors contribute to older-appearing brains. Adults aged 18-57 years from the Netherlands Study of Depression and Anxiety underwent structural MRI. A pretrained brain-age prediction model based on >2000 samples from the ENIGMA consortium was applied to obtain brain-predicted age differences (brain PAD, predicted brain age minus chronological age) in 65 controls and 220 patients with current MDD and/or anxiety. Brain-PAD estimates were associated with clinical, somatic, lifestyle, and biological factors. After correcting for antidepressant use, brain PAD was significantly higher in MDD (+2.78 years, Cohen's d = 0.25, 95% CI -0.10-0.60) and anxiety patients (+2.91 years, Cohen's d = 0.27, 95% CI -0.08-0.61), compared with controls. There were no significant associations with lifestyle or biological stress systems. A multivariable model indicated unique contributions of higher severity of somatic depression symptoms (b = 4.21 years per unit increase on average sum score) and antidepressant use (-2.53 years) to brain PAD. Advanced brain aging in patients with MDD and anxiety was most strongly associated with somatic depressive symptomatology. We also present clinically relevant evidence for a potential neuroprotective antidepressant effect on the brain-PAD metric that requires follow-up in future research.

Examining the Role of the Noradrenergic Locus Coeruleus for Predicting Attention and Brain Maintenance in Healthy Old Age and Disease: An MRI Structural Study for the Alzheimer's Disease Neuroimaging Initiative

The noradrenergic theory of Cognitive Reserve (Robertson, 2013-2014) postulates that the upregulation of the locus coeruleus-noradrenergic system (LC-NA) originating in the brainstem might facilitate cortical networks involved in attention, and protracted activation of this system throughout the lifespan may enhance cognitive stimulation contributing to reserve. To test the above-mentioned theory, a study was conducted on a sample of 686 participants (395 controls, 156 mild cognitive impairment, 135 Alzheimer's disease) investigating the relationship between LC volume, attentional performance and a biological index of brain maintenance (BrainPAD-an objective measure, which compares an individual's structural brain health, reflected by their voxel-wise grey matter density, to the state typically expected at that individual's age). Further analyses were carried out on reserve indices including education and occupational attainment. Volumetric variation across groups was also explored along with gender differences. Control analyses on the serotoninergic (5-HT), dopaminergic (DA) and cholinergic (Ach) systems were contrasted with the noradrenergic (NA) hypothesis. The antithetic relationships were also tested across the neuromodulatory subcortical systems. Results supported by Bayesian modelling showed that LC volume disproportionately predicted higher attentional performance as well as biological brain maintenance across the three groups. These findings lend support to the role of the noradrenergic system as a key mediator underpinning the neuropsychology of reserve, and they suggest that early prevention strategies focused on the noradrenergic system (e.g., cognitive-attentive training, physical exercise, pharmacological and dietary interventions) may yield important clinical benefits to mitigate cognitive impairment with age and disease.

Verbal intelligence is a more robust cross-sectional measure of cognitive reserve than level of education in healthy older adults

BACKGROUND

Cognitive reserve is most commonly measured using socio-behavioural proxy variables. These variables are easy to collect, have a straightforward interpretation, and are widely associated with reduced risk of dementia and cognitive decline in epidemiological studies. However, the specific proxies vary across studies and have rarely been assessed in complete models of cognitive reserve (i.e. alongside both a measure of cognitive outcome and a measure of brain structure). Complete models can test independent associations between proxies and cognitive function in addition to the moderation effect of proxies on the brain-cognition relationship. Consequently, there is insufficient empirical evidence guiding the choice of proxy measures of cognitive reserve and poor comparability across studies.

METHOD

In a cross-sectional study, we assessed the validity of 5 common proxies (education, occupational complexity, verbal intelligence, leisure activities, and exercise) and all possible combinations of these proxies in 2 separate community-dwelling older adult cohorts: The Irish Longitudinal Study on Ageing (TILDA; N = 313, mean age = 68.9 years, range = 54-88) and the Cognitive Reserve/Reference Ability Neural Network Study (CR/RANN; N = 234, mean age = 64.49 years, range = 50-80). Fifteen models were created with 3 brain structure variables (grey matter volume, hippocampal volume, and mean cortical thickness) and 5 cognitive variables (verbal fluency, processing speed, executive function, episodic memory, and global cognition).

RESULTS

No moderation effects were observed. There were robust positive associations with cognitive function, independent of brain structure, for 2 individual proxies (verbal intelligence and education) and 16 composites (i.e. combinations of proxies). Verbal intelligence was statistically significant in all models. Education was significant only in models with executive function as the cognitive outcome variable. Three robust composites were observed in more than two-thirds of brain-cognition models: the composites of (1) occupational complexity and verbal intelligence, (2) education and verbal intelligence, and (3) education, occupational complexity, and verbal intelligence. However, no composite had larger average effects nor was more robust than verbal intelligence alone.

CONCLUSION

These results support the use of verbal intelligence as a proxy measure of CR in cross-sectional studies of cognitively healthy older adults.

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.

Pitfalls in brain age analyses

Over the past decade, there has been an abundance of research on the difference between age and age predicted using brain features, which is commonly referred to as the “brain age gap.” Researchers have identified that the brain age gap, as a linear transformation of an out‐of‐sample residual, is dependent on age. As such, any group differences on the brain age gap could simply be due to group differences on age. To mitigate the brain age gap's dependence on age, it has been proposed that age be regressed out of the brain age gap. If this modified brain age gap is treated as a corrected deviation from age, model accuracy statistics such as R² will be artificially inflated to the extent that it is highly improbable that an R² value below .85 will be obtained no matter the true model accuracy. Given the limitations of proposed brain age analyses, further theoretical work is warranted to determine the best way to quantify deviation from normality.

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.

Estimating Gender and Age from Brain Structural MRI of Children and Adolescents: A 3D Convolutional Neural Network Multitask Learning Model

Despite recent advances, assessing biological measurements for neuropsychiatric disorders is still a challenge, where confounding variables such as gender and age (as a proxy for neurodevelopment) play an important role. This study explores brain structural magnetic resonance imaging (sMRI) from two public data sets (ABIDE-II and ADHD-200) with healthy control (HC, N = 894), autism spectrum disorder (ASD, N = 251), and attention deficit hyperactivity disorder (ADHD, N = 357) individuals. We used gray and white matter preprocessed via voxel-based morphometry (VBM) to train a 3D convolutional neural network with a multitask learning strategy to estimate gender, age, and mental health status from structural brain differences. Gradient-based methods were employed to generate attention maps, providing clinically relevant identification of most representative brain regions for models' decision-making. This approach resulted in satisfactory predictions for gender and age. ADHD-200-trained models, evaluated in 10-fold cross-validation procedures on test set, obtained a mean absolute error (MAE) of 1.43 years (±0.22 SD) for age prediction and an area under the curve (AUC) of 0.85 (±0.04 SD) for gender classification. In out-of-sample validation, the best-performing ADHD-200 models satisfactorily predicted age (MAE = 1.57 years) and gender (AUC = 0.89) in the ABIDE-II data set. The models' accuracy was in line with the current state-of-the-art machine learning applications in neuroimaging. Key regions for models' accuracy were presented as a meaningful graphical output. New implementations, such as the use of VBM along with a 3D convolutional neural network multitask learning model and a brain imaging graphical output, reinforce the relevance of the proposed workflow.

Long-term Anabolic-Androgenic Steroid Use Is Associated With Deviant Brain Aging

BACKGROUND

High-dose long-term use of anabolic-androgenic steroids (AASs) may cause a range of adverse effects, including brain and cognitive abnormalities. We performed age prediction based on brain scans to test whether prolonged AAS use is associated with accentuated brain aging.

METHODS

T1-weighted magnetic resonance imaging (3D MPRAGE [magnetization-prepared rapid acquisition gradient-echo]) scans were obtained from male weightlifters with a history of prolonged AAS use (n = 130) or no AAS use (n = 99). We trained machine learning models on combinations of regional brain volumes, cortical thickness, and surface area in an independent training set of 1838 healthy male subjects (18-92 years of age) and predicted brain age for each participant in our study. Including cross-sectional and longitudinal (mean interval = 3.5 years, n = 76) magnetic resonance imaging data, we used linear mixed-effects models to compare the gap between chronological age and predicted brain age (the brain age gap [BAG]) for the two groups and tested for group differences in the rate of change in BAG. We tested for associations between apparent brain aging and AAS use duration, pattern of administration, and dependence.

RESULTS

AAS users had higher BAG compared with weightlifting control subjects, which was associated with dependency and longer history of use. Group differences in BAG could not be explained by other substance use, general cognitive abilities, or depression. While longitudinal analysis revealed no evidence of increased brain aging in the overall AAS group, accelerated brain aging was seen with longer AAS exposure.

CONCLUSIONS

The findings suggest that long-term high-dose AAS use may have adverse effects on brain aging, potentially linked to dependency and exaggerated use of AASs.

Defining brain health: A concept analysis

OBJECTIVES

Brain health is an important focus for coming decades due to population ageing. Although the term 'brain health' is increasingly used in lay and professional settings, a clear definition of the term is lacking. We conducted an analysis of the concept of brain health to inform policy, practice, and research.

METHODS

We applied a hybrid concept analysis method involving three stages: (1) a review of the extant literature for definitions of brain health; (2) field work, involving an international survey of 'brain health' researchers and practitioners; and (3) a final analysis, integrating the findings into a working definition and model.

RESULTS

Our review of the literature identified 13 articles defining brain health, six of which proposed their own definition. Our survey revealed that the term 'brain health' was used in diverse ways based on different theoretical frameworks. From the review and survey, we extracted attributes, antecedents, and consequences of brain health. These were synthesized into a definition of brain health as a life-long, multidimensional, dynamic state consisting of cognitive, emotional and motor domains underpinned by physiological processes and can be objectively measured and subjectively experienced. It is influenced by eco-biopsychosocial determinants.

CONCLUSION

This working definition of brain health is a foundation for developing policy, practice, research and advocacy. The definition needs to be operationalised through further development of empirical referents, including cross-cultural understanding, adaptation and validation.

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.

Prediction of brain age and cognitive age: Quantifying brain and cognitive maintenance in aging

The concept of brain maintenance refers to the preservation of brain integrity in older age, while cognitive reserve refers to the capacity to maintain cognition in the presence of neurodegeneration or aging-related brain changes. While both mechanisms are thought to contribute to individual differences in cognitive function among older adults, there is currently no "gold standard" for measuring these constructs. Using machine-learning methods, we estimated brain and cognitive age based on deviations from normative aging patterns in the Whitehall II MRI substudy cohort (N = 537, age range = 60.34-82.76), and tested the degree of correspondence between these constructs, as well as their associations with premorbid IQ, education, and lifestyle trajectories. In line with established literature highlighting IQ as a proxy for cognitive reserve, higher premorbid IQ was linked to lower cognitive age independent of brain age. No strong evidence was found for associations between brain or cognitive age and lifestyle trajectories from midlife to late life based on latent class growth analyses. However, post hoc analyses revealed a relationship between cumulative lifestyle measures and brain age independent of cognitive age. In conclusion, we present a novel approach to characterizing brain and cognitive maintenance in aging, which may be useful for future studies seeking to identify factors that contribute to brain preservation and cognitive reserve mechanisms in older age.

White matter brain aging in relationship to schizophrenia and its cognitive deficit

We hypothesized that cerebral white matter deficits in schizophrenia (SZ) are driven in part by accelerated white matter aging and are associated with cognitive deficits. We used a machine learning model to predict individual age from diffusion tensor imaging features and calculated the delta age (Δage) as the difference between predicted and chronological age. Through this approach, we translated multivariate white matter imaging features into an age-scaled metric and used it to test the temporal trends of accelerated aging-related white matter deficit in SZ and its association with the cognition. A feature selection procedure was first employed to choose fractional anisotropy values in 34 of 43 white fiber tracts. Using these features, a machine learning model was trained based on a training set consisted of 107 healthy controls (HC). The brain age of 166 SZs and 107 HCs in the testing set were calculated using this model. Then, we examined the SZ-HC group effect on Δage and whether this effect was moderated by chronological age using the regression spline model. The results showed that Δage was significantly elevated in the age > 30 group in patients (p < 0.001) but not in age ≤ 30 group (p = 0.364). Δage in patients was significantly and negatively associated with both working memory (β = -0.176, p = 0.007) and processing speed (β = -0.519, p = 0.035) while adjusting sex and chronological age. Overall, these findings indicate that the Δage is elevated in SZs and become significantly from the third decade of life; the increase of Δage in SZs is associated with the declined neurocognitive performance.

Sex differences in brain aging among adults with family history of Alzheimer's disease and APOE4 genetic risk

Emerging evidence suggests that Alzheimer's Disease (AD) risk factors may differentially contribute to disease trajectory in women than men. Determining the effect of AD risk factors on brain aging in women, compared to men, is critical for understanding whether there are sex differences in the pathways towards AD in cognitively intact but at-risk adults. Brain Age Gap (BAG) is a concept used increasingly as a measure of brain health; BAG is defined as the difference between predicted age (based on structural MRI) and chronological age, with negative values reflecting preserved brain health with age. Using BAG, we investigated whether there were sex differences in the brain effects of AD risk factors (i.e., family history of AD, and carrying an apolipoprotein E ε4 allele [+APOE4]) in cognitively intact adults, and if this relationship was moderated by modifiable factors (i.e. body mass index [BMI], blood pressure and physical activity). We undertook a cross-sectional study of structural MRIs from 1067 cognitively normal adults across four neuroimaging datasets. An elastic net regression model found that women with a family history of AD and +APOE4 genotype had more advanced brain aging than their male counterparts. In a sub-cohort of women with those risk factors, higher BMI was associated with less brain aging whereas lower BMI was not. In a sub-cohort of women and men with +APOE4, engaging in physical activity was more beneficial to men's brain aging than women's. Our results demonstrate that AD risk factors are associated with greater brain aging in women than men, although there may be more unexplored modifiable factors that influence this relationship. These findings suggest that the complex interplay between unmodifiable and modifiable AD risk factors can potentially protect against brain aging in women and men.

Multimodal Image Analysis of Apparent Brain Age Identifies Physical Fitness as Predictor of Brain Maintenance

Maintaining a youthful brain structure and function throughout life may be the single most important determinant of successful cognitive aging. In this study, we addressed heterogeneity in brain aging by making image-based brain age predictions and relating the brain age prediction gap (BAPG) to cognitive change in aging. Structural, functional, and diffusion MRI scans from 351 participants were used to train and evaluate 5 single-modal and 4 multimodal prediction models, based on 7 regression methods. The models were compared on mean absolute error and whether they were related to physical fitness and cognitive ability, measured both currently and longitudinally, as well as study attrition and years of education. Multimodal prediction models performed at a similar level as single-modal models, and the choice of regression method did not significantly affect the results. Correlation with the BAPG was found for current physical fitness, current cognitive ability, and study attrition. Correlations were also found for retrospective physical fitness, measured 10 years prior to imaging, and slope for cognitive ability during a period of 15 years. The results suggest that maintaining a high physical fitness throughout life contributes to brain maintenance and preserved cognitive ability.

Predicting Brain Age at Slice Level: Convolutional Neural Networks and Consequences for Interpretability

Problem: Chronological aging in later life is associated with brain degeneration processes and increased risk for disease such as stroke and dementia. With a worldwide tendency of aging populations and increased longevity, mental health, and psychiatric research have paid increasing attention to understanding brain-related changes of aging. Recent findings suggest there is a brain age gap (a difference between chronological age and brain age predicted by brain imaging indices); the magnitude of the gap may indicate early onset of brain aging processes and disease. Artificial intelligence has allowed for a narrowing of the gap in chronological and predicted brain age. However, the factors that drive model predictions of brain age are still unknown, and there is not much about these factors that can be gleaned from the black-box nature of machine learning models. The goal of the present study was to test a brain age regression approach that is more amenable to interpretation by researchers and clinicians. Methods: Using convolutional neural networks we trained multiple regressor models to predict brain age based on single slices of magnetic resonance imaging, which included gray matter- or white matter-segmented inputs. We evaluated the trained models in all brain image slices to generate a final prediction of brain age. Unlike whole-brain approaches to classification, the slice-level predictions allows for the identification of which brain slices and associated regions have the largest difference between chronological and neuroimaging-derived brain age. We also evaluated how model predictions were influenced by slice index and plane, participant age and sex, and MRI data collection site. Results: The results show, first, that the specific slice used for prediction affects prediction error (i.e., difference between chronological age and neuroimaging-derived brain age); second, the MRI site-stratified separation of training and test sets removed site effects and also minimized sex effects; third, the choice of MRI slice plane influences the overall error of the model. Conclusion: Compared to whole brain-based predictive models of neuroimaging-derived brain age, slice-based approach improves the interpretability and therefore the reliability of the prediction of brain age using MRI data.

Extracting Robust Biomarkers From Multichannel EEG Time Series Using Nonlinear Dimensionality Reduction Applied to Ordinal Pattern Statistics and Spectral Quantities

In this study, ordinal pattern analysis and classical frequency-based EEG analysis methods are used to differentiate between EEGs of different age groups as well as individuals. As characteristic features, functional connectivity as well as single-channel measures in both the time and frequency domain are considered. We compare the separation power of each feature set after nonlinear dimensionality reduction using t-distributed stochastic neighbor embedding and demonstrate that ordinal pattern-based measures yield results comparable to frequency-based measures applied to preprocessed data, and outperform them if applied to raw data. Our analysis yields no significant differences in performance between single-channel features and functional connectivity features regarding the question of age group separation.

Occupation-related effects on motor cortex thickness among older, cognitive healthy individuals

Both, decline of sensorimotor functions and cortical thickness are known processes in healthy aging. Physical activity has been suggested to enhance the execution of daily routine activities and to extend the time of functional independence in advanced age. We hypothesized that cortical thickness of motor areas in retired individuals could be related to physical demands of the profession carried out during working life. Depending on their former occupations, 69 cognitively healthy individuals (range 70–85 years) were divided into higher and lower physically complex occupations (HPCO n = 27 and LPCO n = 42) according to the international standard classification of occupations (ISCO-08). Participants underwent a high-resolution 3T T1-weighted MRI scan. Surface-based analysis revealed higher cortical thickness in the left precentral (P = 0.001) and postcentral gyrus (P < 0.001) and right postcentral gyrus (P = 0.001) for the HPCO relative to the LPCO group (corrected for multiple comparisons, sex, age and leisure activities in the past 20 years). Physical leisure activities associated with exertion were positively correlated with cortical thickness in the left pre- and postcentral gyrus (P = 0.037) of the LPCO group. Time since retirement was negatively associated with cortical thickness in the left postcentral gyrus (P = 0.004) of the HPCO group. Executing a higher physically complex occupation before retirement was related to relative higher cortical thickness in the primary motor and somatosensory cortex in later life, supporting the hypothesis that physical activity contributes to neural reserve in these regions. However, these benefits appear to vanish when physical activity is reduced due to retirement.

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.

Cognitive reserve and brain maintenance in aging and dementia: An integrative review

This research is an integrative review of scientific evidence differentiating between cognitive reserve (CR) and brain maintenance concepts. Thus, we have examined how CR socio-behavioral proxies (i.e. education, occupational attainment, and leisure activities) may help to cope with age-related cognitive decline and negative consequences of brain pathology. We also analyze lifestyle factors associated with brain maintenance or the relative absence of change in neural resources over time. Medline and Web of Science databases were used for the bibliographic search in the last 20 years. Observational cohort studies were selected to analyze the effect of different CR proxies on cognitive decline, including dementia incidence, whereas studies employing functional neuroimaging (fMRI) were used to display the existence of compensation mechanisms. Besides, structural MRI studies were used to test the association between lifestyle factors and neural changes. Our findings suggest that education, leisure activities, and occupational activity are protective factors against cognitive decline and dementia. Moreover, functional neuroimaging studies have verified the existence of brain networks that may underlie CR. Therefore, CR may be expressed either through a more efficient utilization (neural reserve) of brain networks or the recruitment of additional brain regions (compensation). Finally, lifestyle factors such as abstaining from smoking, lower alcohol consumption, and physical activity contributed to brain maintenance and were associated with the preservation of cognitive function. Advances in multimodal neuroimaging studies, preferably longitudinal design, will allow a better understanding of the neural mechanisms associated with the prevention of cognitive decline and preservation of neural resources in aging.

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.

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.

Education and age-related differences in cortical thickness and volume across the lifespan

This study investigated whether relationships between age and measures of gray matter in the brain differed across the lifespan and by years of education. The hypothesis is that year to year differences in brain measures vary across the lifespan and are affected by the years of education someone has. Cortical thickness and subcortical volume were measured from 391 healthy adults (age range: 19-80 years). Brain measures were predicted using a quadratic age effect and moderating effects of education using linear regression. Results demonstrate that 12 brain regions had significant moderating effects of age and education on brain measures. These are brain regions where the effect of age on gray matter varied across the lifespan and across levels of education. The results highlighted that when the moderating effects of education are absent from the model, age and brain measures were linearly related. The moderating effects reveal complex age-brain dynamics and support theories of brain maintenance, suggesting that lifestyle factors limit the negative effects of advancing age. Greater education was related to maintained gray matter until later ages. This protection came at a cost, which indicated that year to year decline in gray matter was larger in late life in those with greater levels of education. Improving our understanding of how age and individual differences affect gray matter measures is an important step toward improving the clinical utility of cortical thickness and volume. This article is part of the Virtual Special Issue titled "COGNITIVE NEUROSCIENCE OF HEALTHY AND PATHOLOGICAL AGING". The full issue can be found on ScienceDirect at https://www.sciencedirect.com/journal/neurobiology-of-aging/special-issue/105379XPWJP.

Learning patterns of the ageing brain in MRI using deep convolutional networks

Both normal ageing and neurodegenerative diseases cause morphological changes to the brain. Age-related brain changes are subtle, nonlinear, and spatially and temporally heterogenous, both within a subject and across a population. Machine learning models are particularly suited to capture these patterns and can produce a model that is sensitive to changes of interest, despite the large variety in healthy brain appearance. In this paper, the power of convolutional neural networks (CNNs) and the rich UK Biobank dataset, the largest database currently available, are harnessed to address the problem of predicting brain age. We developed a 3D CNN architecture to predict chronological age, using a training dataset of 12,802 T1-weighted MRI images and a further 6,885 images for testing. The proposed method shows competitive performance on age prediction, but, most importantly, the CNN prediction errors Δ_BrainAge=Age_Predicted-Age_True correlated significantly with many clinical measurements from the UK Biobank in the female and male groups. In addition, having used images from only one imaging modality in this experiment, we examined the relationship between Δ_BrainAge and the image-derived phenotypes (IDPs) from all other imaging modalities in the UK Biobank, showing correlations consistent with known patterns of ageing. Furthermore, we show that the use of nonlinearly registered images to train CNNs can lead to the network being driven by artefacts of the registration process and missing subtle indicators of ageing, limiting the clinical relevance. Due to the longitudinal aspect of the UK Biobank study, in the future it will be possible to explore whether the Δ_BrainAge from models such as this network were predictive of any health outcomes.

Discovering correlates of age-related decline in a healthy late-midlife male birth cohort

Studies exploring age-related brain and cognitive change have identified substantial heterogeneity among individuals, but the underlying reasons for the differential trajectories remain largely unknown. We investigated cross-sectional and longitudinal associations between brain-imaging phenotypes (IDPs) and cognitive ability, and how these relations may be modified by common risk and protective factors. Participants were recruited from the 1953 Danish Male Birth Cohort (N=123), a longitudinal study of cognitive and brain ageing. Childhood IQ and socio-demographic factors are available for these participants who have been assessed regularly on multiple IDPs and behavioural factors in midlife. Using Pearson correlations and canonical correlation analysis (CCA), we explored the relation between 454 IDPs and 114 behavioural variables. CCA identified a single mode of population covariation coupling cross-subject longitudinal changes in brain structure to changes in cognitive performance and to a range of age-related covariates (r=0.92, Pcorrected < 0.001). Specifically, this CCA-mode indicated that; decreases in IQ and speed assessed tasks, higher rates of familial myocardial infarct, less physical activity, and poorer mental health are associated with larger decreases in whole brain grey matter and white matter. We found no evidence supporting the role of baseline scores as predictors of impending brain and behavioural change in late-midlife.

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.

Multimodality neuroimaging brain-age in UK biobank: relationship to biomedical, lifestyle, and cognitive factors

The brain-age paradigm is proving increasingly useful for exploring aging-related disease and can predict important future health outcomes. Most brain-age research uses structural neuroimaging to index brain volume. However, aging affects multiple aspects of brain structure and function, which can be examined using multimodality neuroimaging. Using UK Biobank, brain-age was modeled in n = 2205 healthy people with T1-weighted MRI, T2-FLAIR, T2∗, diffusion-MRI, task fMRI, and resting-state fMRI. In a held-out healthy validation set (n = 520), chronological age was accurately predicted (r = 0.78, mean absolute error = 3.55 years) using LASSO regression, higher than using any modality separately. Thirty-four neuroimaging phenotypes were deemed informative by the regression (after bootstrapping); predominantly gray-matter volume and white-matter microstructure measures. When applied to new individuals from UK Biobank (n = 14,701), significant associations with multimodality brain-predicted age difference (brain-PAD) were found for stroke history, diabetes diagnosis, smoking, alcohol intake and some, but not all, cognitive measures (corrected p < 0.05). Multimodality neuroimaging can improve brain-age prediction, and derived brain-PAD values are sensitive to biomedical and lifestyle factors that negatively impact brain and cognitive health.

•

Brain-age was predicted from 6 different neuroimaging modalities.

•

Combined multi-modality brain-age was more accurate than any single modality.

•

Thirty-four neuroimaging measures were informative for brain-age prediction.

•

Informative measures generally reflect brain volume and white-matter microstructure.

•

Brain-age was associated with stroke, diabetes, smoking, alcohol and cognition.

Deep Granular Feature-Label Distribution Learning for Neuroimaging-based Infant Age Prediction

Neuroimaging-based infant age prediction is important for brain development analysis but often suffers insufficient data. To address this challenge, we introduce label distribution learning (LDL), a popular machine learning paradigm focusing on the small sample problem, for infant age prediction. As directly applying LDL yields dramatically increased number of day-to-day age labels and also extremely scarce data describing each label, we propose a new strategy, called granular label distribution (GLD). Particularly, by assembling the adjacent labels to granules and designing granular distributions, GLD makes each brain MRI contribute to not only its own age but also its neighboring ages at a granule scale, which effectively keeps the information augmentation superiority of LDL and reduces the number of labels. Furthermore, to extremely augment the information supplied by the small data, we propose a novel method named granular feature distribution (GFD). GFD leverages the variability of the brain images at the same age, thus significantly increasing the learning effectiveness. Moreover, deep neural network is exploited to approximate the GLD. These strategies constitute a new model: deep granular feature-label distribution learning (DGFLDL). By taking 8 types of cortical morphometric features from structural MRI as predictors, the proposed DGFLDL is validated on infant age prediction using 384 brain MRI scans from 35 to 848 days after birth. Our proposed method, approaching the mean absolute error as 36.1 days, significantly outperforms the baseline methods. Besides, the permutation importance analysis of features based on our method reveals important biomarkers of infant brain development.

Association of relative brain age with tobacco smoking, alcohol consumption, and genetic variants

Brain age is a metric that quantifies the degree of aging of a brain based on whole-brain anatomical characteristics. While associations between individual human brain regions and environmental or genetic factors have been investigated, how brain age is associated with those factors remains unclear. We investigated these associations using UK Biobank data. We first trained a statistical model for obtaining relative brain age (RBA), a metric describing a subject's brain age relative to peers, based on whole-brain anatomical measurements, from training set subjects (n = 5,193). We then applied this model to evaluation set subjects (n = 12,115) and tested the association of RBA with tobacco smoking, alcohol consumption, and genetic variants. We found that daily or almost daily consumption of tobacco and alcohol were both significantly associated with increased RBA (P < 0.001). We also found SNPs significantly associated with RBA (p-value < 5E-8). The SNP most significantly associated with RBA is located in MAPT gene. Our results suggest that both environmental and genetic factors are associated with structural brain aging.

Distributional Transformation Improves Decoding Accuracy When Predicting Chronological Age From Structural MRI

When predicting a certain subject-level variable (e.g., age in years) from measured biological data (e.g., structural MRI scans), the decoding algorithm does not always preserve the distribution of the variable to predict. In such a situation, distributional transformation (DT), i.e., mapping the predicted values to the variable's distribution in the training data, might improve decoding accuracy. Here, we tested the potential of DT within the 2019 Predictive Analytics Competition (PAC) which aimed at predicting chronological age of adult human subjects from structural MRI data. In a low-dimensional setting, i.e., with less features than observations, we applied multiple linear regression, support vector regression and deep neural networks for out-of-sample prediction of subject age. We found that (i) when the number of features is low, no method outperforms linear regression; and (ii) except when using deep regression, distributional transformation increases decoding performance, reducing the mean absolute error (MAE) by about half a year. We conclude that DT can be advantageous when predicting variables that are non-controlled, but have an underlying distribution in healthy or diseased populations.

Differences in Total Brain Volume between Sexes in a Cognitively Unimpaired Elderly Population

OBJECTIVES

Although a large number of studies have shown brain volumetric differences between men and women, only a few investigations have analyzed brain tissue volumes in representative samples of the general elderly population. We investigated differences in gray matter (GM) volumes, white matter (WM) volumes, and intracranial volumes (ICVs) between the sexes in individuals older than 66 years using structural magnetic resonance imaging (MRI).

METHODS

Using FreeSurfer version 5.3, we obtained the ICVs and GM and WM volumes from the MRI datasets of 84 men and 92 women. To correct for interindividual variations in ICV, GM and WM volumes were adjusted with a method using the residuals of a least-square-derived linear regression between raw volumes and ICVs. We then performed an analysis of covariance comparing men and women, including age and years of schooling as confounding factors.

RESULTS

Women had a lower socioeconomic status overall and fewer years of schooling than men. The comparison of unadjusted brain volumes showed larger GM and WM volumes in men. After the ICV correction, the adjusted volumes of GM and WM were larger in women.

CONCLUSION

After the ICV correction and taking into account differences in socioeconomic status and years of schooling, our results confirm previous findings of proportionally larger GM in women, as well as larger WM volumes. These results in an elderly population indicate that brain volumetric differences between sexes persist throughout the aging process. Additional studies combining MRI and other biomarkers to identify the hormonal and molecular bases influencing such differences are warranted.

Improved prediction of brain age using multimodal neuroimaging data

Brain age prediction based on imaging data and machine learning (ML) methods has great potential to provide insights into the development of cognition and mental disorders. Though different ML models have been proposed, a systematic comparison of ML models in combination with imaging features derived from different modalities is still needed. In this study, we evaluate the prediction performance of 36 combinations of imaging features and ML models including deep learning. We utilize single and multimodal brain imaging data including MRI, DTI, and rs‐fMRI from a large data set with 839 subjects. Our study is a follow‐up to the initial work (Liang et al., 2019. Human Brain Mapping) to investigate different analytic strategies to combine data from MRI, DTI, and rs‐fMRI with the goal to improve brain age prediction accuracy. Additionally, the traditional approach to predicting the brain age gap has been shown to have a systematic bias. The potential nonlinear relationship between the brain age gap and chronological age has not been thoroughly tested. Here we propose a new method to correct the systematic bias of brain age gap by taking gender, chronological age, and their interactions into consideration. As the true brain age is unknown and may deviate from chronological age, we further examine whether various levels of behavioral performance across subjects predict their brain age estimated from neuroimaging data. This is an important step to quantify the practical implication of brain age prediction. Our findings are helpful to advance the practice of optimizing different analytic methodologies in brain age prediction.

Predicted Brain Age After Stroke

Aging is a known non-modifiable risk factor for stroke. Usually, this refers to chronological rather than biological age. Biological brain age can be estimated based on cortical and subcortical brain measures. For stroke patients, it could serve as a more sensitive marker of brain health than chronological age. In this study, we investigated whether there is a difference in brain age between stroke survivors and control participants matched on chronological age. We estimated brain age at 3 months after stroke, and then followed the longitudinal trajectory over three time-points: within 6 weeks (baseline), at 3 and at 12 months following their clinical event. We found that brain age in stroke participants was higher compared to controls, with the mean difference between the groups varying between 3.9 and 8.7 years depending on the brain measure used for prediction. This difference in brain age was observed at 6 weeks after stroke and maintained at 3 and 12 months after stroke. The presence of group differences already at baseline suggests that stroke might be an ultimate manifestation of gradual cerebrovascular burden accumulation and brain degeneration. Brain age prediction, therefore, has the potential to be a useful biomarker for quantifying stroke risk.

Brain age prediction using deep learning uncovers associated sequence variants

Machine learning algorithms can be trained to estimate age from brain structural MRI. The difference between an individual’s predicted and chronological age, predicted age difference (PAD), is a phenotype of relevance to aging and brain disease. Here, we present a new deep learning approach to predict brain age from a T1-weighted MRI. The method was trained on a dataset of healthy Icelanders and tested on two datasets, IXI and UK Biobank, utilizing transfer learning to improve accuracy on new sites. A genome-wide association study (GWAS) of PAD in the UK Biobank data (discovery set: \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$N=12378$$\end{document}N=12378, replication set: \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$N=4456$$\end{document}N=4456) yielded two sequence variants, rs1452628-T (\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\beta =-0.08$$\end{document}β=−0.08, \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$P=1.15\times{10}^{-9}$$\end{document}P=1.15×10−9) and rs2435204-G (\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\beta =0.102$$\end{document}β=0.102, \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$P=9.73\times 1{0}^{-12}$$\end{document}P=9.73×10−12). The former is near KCNK2 and correlates with reduced sulcal width, whereas the latter correlates with reduced white matter surface area and tags a well-known inversion at 17q21.31 (H2).

Machine learning algorithms can be trained to estimate age from brain structural MRI. Here, the authors introduce a new deep-learning-based age prediction approach, and then carry out a GWAS of the difference between predicted and chronological age, revealing two associated variants.