Predicting brain age with deep learning from raw imaging data results in a reliable and heritable biomarker

Advanced Brain Age and Chronic Poststroke Aphasia Severity

BACKGROUND AND OBJECTIVES

Chronic poststroke language impairment is typically worse in older individuals or those with large stroke lesions. However, there is unexplained variance that likely depends on intact tissue beyond the lesion. Brain age is an emerging concept, which is partially independent from chronologic age. Advanced brain age is associated with cognitive decline in healthy older adults; therefore, we aimed to investigate the relationship with stroke aphasia. We hypothesized that advanced brain age is a significant factor associated with chronic poststroke language impairments, above and beyond chronologic age, and lesion characteristics.

METHODS

This cohort study retrospectively evaluated participants from the Predicting Outcomes of Language Rehabilitation in Aphasia clinical trial (NCT03416738), recruited through local advertisement in South Carolina (US). Primary inclusion criteria were left hemisphere stroke and chronic aphasia (≥12 months after stroke). Participants completed baseline behavioral testing including the Western Aphasia Battery-Revised (WAB-R), Philadelphia Naming Test (PNT), Pyramids and Palm Trees Test (PPTT), and Wechsler Adult Intelligence Scale Matrices subtest, before completing 6 weeks of language therapy. The PNT was repeated 1 month after therapy. We leveraged modern neuroimaging techniques to estimate brain age and computed a proportional difference between chronologic age and estimated brain age. Multiple linear regression models were used to evaluate the relationship between proportional brain age difference (PBAD) and behavior.

RESULTS

Participants (N = 93, 58 males and 35 females, average age = 61 years) had estimated brain ages ranging from 14 years younger to 23 years older than chronologic age. Advanced brain age predicted performance on semantic tasks (PPTT) and language tasks (WAB-R). For participants with advanced brain aging (n = 47), treatment gains (improvement on the PNT) were independently predicted by PBAD (T = -2.0474, p = 0.0468, 9% of variance explained).

DISCUSSION

Through the application of modern neuroimaging techniques, advanced brain aging was associated with aphasia severity and performance on semantic tasks. Notably, therapy outcome scores were also associated with PBAD, albeit only among participants with advanced brain aging. These findings corroborate the importance of brain age as a determinant of poststroke recovery and underscore the importance of personalized health factors in determining recovery trajectories, which should be considered during the planning or implementation of therapeutic interventions.

Alcohol use disorder: Neuroimaging evidence for accelerated aging of brain morphology and hypothesized contribution to age-related dementia

Excessive alcohol use curtails longevity by rendering intoxicated individuals vulnerable to heightened risk from accidents, violence, and alcohol poisoning, and makes chronically heavy drinkers vulnerable to acceleration of age-related medical and psychiatric conditions that can be life threatening (Yoon, Chen, Slater, Jung, & White, 2020). Thus, studies of factors influencing age-alcohol interactions must consider the potential that the alcohol use disorder (AUD) population may not represent the oldest ages of the unaffected population and may well have accrued comorbidities associated with both AUD and aging itself. Herein, we focus on the aging of the brains of men and women with AUD, keeping AUD contextual factors in mind. Knowledge of the potential influence of the AUD-associated co-factors on the condition of brain structure may lead to identifying modifiable risk factors to avert physical declines and may reverse or arrest further AUD-related degradation of the brain. In this narrative review, we 1) describe quantitative, controlled studies of brain macrostructure and microstructure of adults with AUD, 2) consider the possibility of recovery of brain integrity through harm reduction with sustained abstinence or reduced drinking, and 3) speculate on the ramifications of accelerated aging in AUD as contributing to age-related dementia.

BrainAge of patients with severe late-life depression referred for electroconvulsive therapy

BACKGROUND

Severe depression is associated with accelerated brain aging. BrainAge gap, the difference between predicted and observed BrainAge, was investigated in patients with late-life depression (LLD). We aimed to examine BrainAge gap in LLD and its associations with clinical characteristics indexing LLD chronicity, current severity, prior to electroconvulsive therapy (ECT) and ECT outcome.

METHODS

Data was analyzed from the Mood Disorders in Elderly treated with Electroconvulsive Therapy (MODECT) study. A previously established BrainAge algorithm (BrainAge R by James Cole, (https://github.com/james-cole/brainageR)) was applied to pre-ECT T1-weighted structural MRI-scans of 42 patients who underwent ECT.

RESULTS

A BrainAge gap of 1.8 years (SD = 5.5) was observed, Cohen's d = 0.3. No significant associations between BrainAge gap, number of previous episodes, current episode duration, age of onset, depression severity, psychotic symptoms or ECT outcome were observed.

LIMITATIONS

Limited sample size.

CONCLUSIONS

Our initial findings suggest an older BrainAge than chronological age in patients with severe LLD referred for ECT, however with high degree of variability and direction of the gap. No associations were found with clinical measures. Larger samples are needed to better understand brain aging and to evaluate the usability of BrainAge gap as potential biomarker of prognosis an treatment-response in LLD.

TRIAL REGISTRATION

ClinicalTrials.gov identifier: NCT02667353.

Linking brain maturation and puberty during early adolescence using longitudinal brain age prediction in the ABCD cohort

The temporal characteristics of adolescent neurodevelopment are shaped by a complex interplay of genetic, biological, and environmental factors. Using a large longitudinal dataset of children aged 9-13 from the Adolescent Brain Cognitive Development (ABCD) study we tested the associations between pubertal status and brain maturation. Brain maturation was assessed using brain age prediction based on convolutional neural networks and minimally processed T1-weighted structural MRI data. Brain age prediction provided highly accurate and reliable estimates of individual age, with an overall mean absolute error of 0.7 and 1.4 years at the two timepoints respectively, and an intraclass correlation of 0.65. Linear mixed effects (LME) models accounting for age and sex showed that on average, a one unit increase in pubertal maturational level was associated with a 2.22 months higher brain age across time points (β = 0.10, p < .001). Moreover, annualized change in pubertal development was weakly related to the rate of change in brain age (β = .047, p = 0.04). These results demonstrate a link between sexual development and brain maturation in early adolescence, and provides a basis for further investigations of the complex sociobiological impacts of puberty on life outcomes.

Radiomics-Derived Brain Age Predicts Functional Outcome After Acute Ischemic Stroke

BACKGROUND AND OBJECTIVES

While chronological age is one of the most influential determinants of poststroke outcomes, little is known of the impact of neuroimaging-derived biological "brain age." We hypothesized that radiomics analyses of T2-FLAIR images texture would provide brain age estimates and that advanced brain age of patients with stroke will be associated with cardiovascular risk factors and worse functional outcomes.

METHODS

We extracted radiomics from T2-FLAIR images acquired during acute stroke clinical evaluation. Brain age was determined from brain parenchyma radiomics using an ElasticNet linear regression model. Subsequently, relative brain age (RBA), which expresses brain age in comparison with chronological age-matched peers, was estimated. Finally, we built a linear regression model of RBA using clinical cardiovascular characteristics as inputs and a logistic regression model of favorable functional outcomes taking RBA as input.

RESULTS

We reviewed 4,163 patients from a large multisite ischemic stroke cohort (mean age = 62.8 years, 42.0% female patients). T2-FLAIR radiomics predicted chronological ages (mean absolute error = 6.9 years, r = 0.81). After adjustment for covariates, RBA was higher and therefore described older-appearing brains in patients with hypertension, diabetes mellitus, a history of smoking, and a history of a prior stroke. In multivariate analyses, age, RBA, NIHSS, and a history of prior stroke were all significantly associated with functional outcome (respective adjusted odds ratios: 0.58, 0.76, 0.48, 0.55; all p-values < 0.001). Moreover, the negative effect of RBA on outcome was especially pronounced in minor strokes.

DISCUSSION

T2-FLAIR radiomics can be used to predict brain age and derive RBA. Older-appearing brains, characterized by a higher RBA, reflect cardiovascular risk factor accumulation and are linked to worse outcomes after stroke.

No signs of neurodegenerative effects in 15q11.2 BP1-BP2 copy number variant carriers in the UK Biobank

The 15q11.2 BP1-BP2 copy number variant (CNV) is associated with altered brain morphology and risk for atypical development, including increased risk for schizophrenia and learning difficulties for the deletion. However, it is still unclear whether differences in brain morphology are associated with neurodevelopmental or neurodegenerative processes. This study derived morphological brain MRI measures in 15q11.2 BP1-BP2 deletion (n = 124) and duplication carriers (n = 142), and matched deletion-controls (n = 496) and duplication-controls (n = 568) from the UK Biobank study to investigate the association with brain morphology and estimates of brain ageing. Further, we examined the ageing trajectory of age-affected measures (i.e., cortical thickness, surface area, subcortical volume, reaction time, hand grip strength, lung function, and blood pressure) in 15q11.2 BP1-BP2 CNV carriers compared to non-carriers. In this ageing population, the results from the machine learning models showed that the estimated brain age gaps did not differ between the 15q11.2 BP1-BP2 CNV carriers and non-carriers, despite deletion carriers displaying thicker cortex and lower subcortical volume compared to the deletion-controls and duplication carriers, and lower surface area compared to the deletion-controls. Likewise, the 15q11.2 BP1-BP2 CNV carriers did not deviate from the ageing trajectory on any of the age-affected measures examined compared to non-carriers. Despite altered brain morphology in 15q11.2 BP1-BP2 CNV carriers, the results did not show any clear signs of apparent altered ageing in brain structure, nor in motor, lung or heart function. The results do not indicate neurodegenerative effects in 15q11.2 BP1-BP2 CNV carriers.

Mechanical Property Based Brain Age Prediction using Convolutional Neural Networks

Brain age is a quantitative estimate to explain an individual's structural and functional brain measurements relative to the overall population and is particularly valuable in describing differences related to developmental or neurodegenerative pathology. Accurately inferring brain age from brain imaging data requires sophisticated models that capture the underlying age-related brain changes. Magnetic resonance elastography (MRE) is a phase contrast MRI technology that uses external palpations to measure brain mechanical properties. Mechanical property measures of viscoelastic shear stiffness and damping ratio have been found to change across the entire life span and to reflect brain health due to neurodegenerative diseases and even individual differences in cognitive function. Here we develop and train a multi-modal 3D convolutional neural network (CNN) to model the relationship between age and whole brain mechanical properties. After training, the network maps the measurements and other inputs to a brain age prediction. We found high performance using the 3D maps of various mechanical properties to predict brain age. Stiffness maps alone were able to predict ages of the test group subjects with a mean absolute error (MAE) of 3.76 years, which is comparable to single inputs of damping ratio (MAE: 3.82) and outperforms single input of volume (MAE: 4.60). Combining stiffness and volume in a multimodal approach performed the best, with an MAE of 3.60 years, whereas including damping ratio worsened model performance. Our results reflect previous MRE literature that had demonstrated that stiffness is more strongly related to chronological age than damping ratio. This machine learning model provides the first prediction of brain age from brain biomechanical data-an advancement towards sensitively describing brain integrity differences in individuals with neuropathology.

Longitudinal brain age prediction and cognitive function after stroke

Advanced age is associated with post-stroke cognitive decline. Machine learning based on brain scans can be used to estimate brain age of patients, and the corresponding difference from chronological age, the brain age gap (BAG), has been investigated in a range of clinical conditions, yet not thoroughly in post-stroke neurocognitive disorder (NCD). We aimed to investigate the association between BAG and post-stroke NCD over time. Lower BAG (younger appearing brain compared to chronological age) was found associated with lower risk of post-stroke NCD up to 36 months after stroke, even among those showing no evidence of impairments 3 months after hospital admission. For patients with no NCD at baseline, survival analysis suggested that higher baseline BAG was associated with higher risk of post-stroke NCD at 18 and 36 months. In conclusion, a younger appearing brain is associated with a lower risk of post-stroke NCD.

Is an MRI-derived anatomical measure of dementia risk also a measure of brain aging?

Machine learning methods have been applied to estimate measures of brain aging from neuroimages. However, only rarely have these measures been examined in the context of biologic age. Here, we investigated associations of an MRI-based measure of dementia risk, the Alzheimer's disease pattern similarity (AD-PS) scores, with measures used to calculate biological age. Participants were those from visit 5 of the Atherosclerosis Risk in Communities Study with cognitive status adjudication, proteomic data, and AD-PS scores available. The AD-PS score estimation is based on previously reported machine learning methods. We evaluated associations of the AD-PS score with all-cause mortality. Sensitivity analyses using only cognitively normal (CN) individuals were performed treating CNS-related causes of death as competing risk. AD-PS score was examined in association with 32 proteins measured, using a Somalogic platform, previously reported to be associated with age. Finally, associations with a deficit accumulation index (DAI) based on a count of 38 health conditions were investigated. All analyses were adjusted for age, race, sex, education, smoking, hypertension, and diabetes. The AD-PS score was significantly associated with all-cause mortality and with levels of 9 of the 32 proteins. Growth/differentiation factor 15 (GDF-15) and pleiotrophin remained significant after accounting for multiple-testing and when restricting the analysis to CN participants. A linear regression model showed a significant association between DAI and AD-PS scores overall. While the AD-PS scores were created as a measure of dementia risk, our analyses suggest that they could also be capturing brain aging.

Investigation of genetic variants and causal biomarkers associated with brain aging

Delta age is a biomarker of brain aging that captures differences between the chronological age and the predicted biological brain age. Using multimodal data of brain MRI, genomics, and blood-based biomarkers and metabolomics in UK Biobank, this study investigates an explainable and causal basis of high delta age. A visual saliency map of brain regions showed that lower volumes in the fornix and the lower part of the thalamus are key predictors of high delta age. Genome-wide association analysis of the delta age using the SNP array data identified associated variants in gene regions such as KLF3-AS1 and STX1. GWAS was also performed on the volumes in the fornix and the lower part of the thalamus, showing a high genetic correlation with delta age, indicating that they share a genetic basis. Mendelian randomization (MR) for all metabolomic biomarkers and blood-related phenotypes showed that immune-related phenotypes have a causal impact on increasing delta age. Our analysis revealed regions in the brain that are susceptible to the aging process and provided evidence of the causal and genetic connections between immune responses and brain aging.

Multimodal data fusion based on IGERNNC algorithm for detecting pathogenic brain regions and genes in Alzheimer's disease

At present, the study on the pathogenesis of Alzheimer's disease (AD) by multimodal data fusion analysis has been attracted wide attention. It often has the problems of small sample size and high dimension with the multimodal medical data. In view of the characteristics of multimodal medical data, the existing genetic evolution random neural network cluster (GERNNC) model combine genetic evolution algorithm and neural network for the classification of AD patients and the extraction of pathogenic factors. However, the model does not take into account the non-linear relationship between brain regions and genes and the problem that the genetic evolution algorithm can fall into local optimal solutions, which leads to the overall performance of the model is not satisfactory. In order to solve the above two problems, this paper made some improvements on the construction of fusion features and genetic evolution algorithm in GERNNC model, and proposed an improved genetic evolution random neural network cluster (IGERNNC) model. The IGERNNC model uses mutual information correlation analysis method to combine resting-state functional magnetic resonance imaging data with single nucleotide polymorphism data for the construction of fusion features. Based on the traditional genetic evolution algorithm, elite retention strategy and large variation genetic algorithm are added to avoid the model falling into the local optimal solution. Through multiple independent experimental comparisons, the IGERNNC model can more effectively identify AD patients and extract relevant pathogenic factors, which is expected to become an effective tool in the field of AD research.

Brain age gap in neuromyelitis optica spectrum disorders and multiple sclerosis

OBJECTIVE

To evaluate the clinical significance of deep learning-derived brain age prediction in neuromyelitis optica spectrum disorder (NMOSD) relative to relapsing-remitting multiple sclerosis (RRMS).

METHODS

This cohort study used data retrospectively collected from 6 tertiary neurological centres in China between 2009 and 2018. In total, 199 patients with NMOSD and 200 patients with RRMS were studied alongside 269 healthy controls. Clinical follow-up was available in 85 patients with NMOSD and 124 patients with RRMS (mean duration NMOSD=5.8±1.9 (1.9-9.9) years, RRMS=5.2±1.7 (1.5-9.2) years). Deep learning was used to learn 'brain age' from MRI scans in the healthy controls and estimate the brain age gap (BAG) in patients.

RESULTS

A significantly higher BAG was found in the NMOSD (5.4±8.2 years) and RRMS (13.0±14.7 years) groups compared with healthy controls. A higher baseline disability score and advanced brain volume loss were associated with increased BAG in both patient groups. A longer disease duration was associated with increased BAG in RRMS. BAG significantly predicted Expanded Disability Status Scale worsening in patients with NMOSD and RRMS.

CONCLUSIONS

There is a clear BAG in NMOSD, although smaller than in RRMS. The BAG is a clinically relevant MRI marker in NMOSD and RRMS.

Age-level bias correction in brain age prediction

The predicted age difference (PAD) between an individual's predicted brain age and chronological age has been commonly viewed as a meaningful phenotype relating to aging and brain diseases. However, the systematic bias appears in the PAD achieved using machine learning methods. Recent studies have designed diverse bias correction methods to eliminate it for further downstream studies. Strikingly, here we demonstrate that bias still exists in the PAD of samples with the same age even after kind of correction. Therefore, current PAD may not be taken as a reliable phenotype and more investigations are needed to solve this fundamental defect. To this end, we propose an age-level bias correction method and demonstrate its efficacy in numerical experiments.

Naturalistic Sleep Patterns are Linked to Global Structural Brain Aging in Adolescence

PURPOSE

We examined whether interindividual differences in naturalistic sleep patterns correlate with any deviations from typical brain aging.

METHODS

Our sample consisted of 251 participants without current psychiatric diagnoses (9-25 years; mean [standard deviation] = 17.4 ± 4.52 yr; 58% female) drawn from the Neuroimaging and Pediatric Sleep Databank. Participants completed a T1-weighted structural magnetic resonance imaging scan and 5-7 days of wrist actigraphy to assess naturalistic sleep patterns (duration, timing, continuity, and regularity). We estimated brain age from extracted structural magnetic resonance imaging indices and calculated brain age gap (estimated brain age-chronological age). Robust regressions tested cross-sectional associations between brain age gap and sleep patterns. Exploratory models investigated moderating effects of age and biological gender and, in a subset of the sample, links between sleep, brain age gap, and depression severity (Patient-Reported Outcomes Measurement Information System Depression).

RESULTS

Later sleep timing (midsleep) was associated with more advanced brain aging (larger brain age gap), β = 0.1575, puncorr = .0042, pfdr = .0167. Exploratory models suggested that this effect may be driven by males, although the interaction of gender and brain age gap did not survive multiple comparison correction (β = 0.2459, puncorr = .0336, pfdr = .1061). Sleep duration, continuity, and regularity were not significantly associated with brain age gap. Age did not moderate any brain age gap-sleep relationships. In this psychiatrically healthy sample, depression severity was also not associated with brain age gap or sleep.

DISCUSSION

Later midsleep may be one behavioral cause or correlate of more advanced brain aging, particularly among males. Future studies should examine whether advanced brain aging and individual differences in sleep precede the onset of suboptimal cognitive-emotional outcomes in adolescents.

Elevated Pure Tone Thresholds Are Associated with Altered Microstructure in Cortical Areas Related to Auditory Processing and Attentional Allocation

BACKGROUND

Hearing loss is associated with cognitive decline and increased risk for Alzheimer's disease, but the basis of this association is not understood.

OBJECTIVE

To determine whether hearing impairment is associated with advanced brain aging or altered microstructure in areas involved with auditory and cognitive processing.

METHODS

130 participants, (mean 76.4±7.3 years; 65% women) of the Rancho Bernardo Study of Healthy Aging had a screening audiogram in 2003-2005 and brain magnetic resonance imaging in 2014-2016. Hearing ability was defined as the average pure tone threshold (PTA) at 500, 1000, 2000, and 4000 Hz in the better-hearing ear. Brain-predicted age difference (Brain-pad) was calculated as the difference between brain-predicted age based on a validated structural imaging biomarker of brain age, and chronological age. Regional diffusion metrics in temporal and frontal cortex regions were obtained from diffusion-weighted MRIs. Linear regression analyses adjusted for age, gender, education, and health-related measures.

RESULTS

PTAs were not associated with brain-PAD (β= 0.09; 95% CI: -0.084 to 0.243; p = 0.34). PTAs were associated with reduced restricted diffusion and increased free water diffusion primarily in right hemisphere temporal and frontal areas (restricted diffusion: βs = -0.21 to -0.30; 95% CIs from -0.48 to -0.02; ps < 0.03; free water: βs = 0.18 to 0.26; 95% CIs 0.01 to 0.438; ps < 0.04).

CONCLUSIONS

Hearing impairment is not associated with advanced brain aging but is associated with differences in brain regions involved with auditory processing and attentional control. It is thus possible that increased dementia risk associated with hearing impairment arises, in part, from compensatory brain changes that may decrease resilience.

Is musical engagement enough to keep the brain young?

Music-making and engagement in music-related activities have shown procognitive benefits for healthy and pathological populations, suggesting reductions in brain aging. A previous brain aging study, using Brain Age Gap Estimation (BrainAGE), showed that professional and amateur-musicians had younger appearing brains than non-musicians. Our study sought to replicate those findings and analyze if musical training or active musical engagement was necessary to produce an age-decelerating effect in a cohort of healthy individuals. We scanned 125 healthy controls and investigated if musician status, and if musical behaviors, namely active engagement (AE) and musical training (MT) [as measured using the Goldsmiths Musical Sophistication Index (Gold-MSI)], had effects on brain aging. Our findings suggest that musician status is not related to BrainAGE score, although involvement in current physical activity is. Although neither MT nor AE subscales of the Gold-MSI are predictive for BrainAGE scores, dispositional resilience, namely the ability to deal with challenge, is related to both musical behaviors and sensitivity to musical pleasure. While the study failed to replicate the findings in a previous brain aging study, musical training and active musical engagement are related to the resilience factor of challenge. This finding may reveal how such musical behaviors can potentially strengthen the brain's resilience to age, which may tap into a type of neurocognitive reserve.

An individual-level weighted artificial neural network method to improve the systematic bias in BrainAGE analysis

BrainAGE is a commonly used machine learning technique to measure the accelerated/delayed development pattern of human brain structure/function with neuropsychiatric disorders. However, recent studies have shown a systematic bias ("regression toward mean" effect) in the BrainAGE method, which indicates that the prediction error is not uniformly distributed across Chronological Ages: for the older individuals, the Brain Ages would be under-estimated but would be over-estimated for the younger individuals. In the present study, we propose an individual-level weighted artificial neural network method and apply it to simulation datasets (containing 5000 simulated subjects) and a real dataset (containing 135 subjects). Results show that compared with traditional machine learning methods, the individual-level weighted strategy can significantly reduce the "regression toward mean" effect, while the prediction performance can achieve the comparable level with traditional machine learning methods. Further analysis indicates that the sigmoid active function for artificial neural network shows better performance than the relu active function. The present study provides a novel strategy to reduce the "regression toward mean" effect of BrainAGE analysis, which is helpful to improve accuracy in exploring the atypical brain structure/function development pattern of neuropsychiatric disorders.

Multimodal brain age prediction fusing morphometric and imaging data and association with cardiovascular risk factors

Introduction

The difference between the chronological and biological brain age, called the brain age gap (BAG), has been identified as a promising biomarker to detect deviation from normal brain aging and to indicate the presence of neurodegenerative diseases. Moreover, the BAG has been shown to encode biological information about general health, which can be measured through cardiovascular risk factors. Current approaches for biological brain age estimation, and therefore BAG estimation, either depend on hand-crafted, morphological measurements extracted from brain magnetic resonance imaging (MRI) or on direct analysis of brain MRI images. The former can be processed with traditional machine learning models while the latter is commonly processed with convolutional neural networks (CNNs). Using a multimodal setting, this study aims to compare both approaches in terms of biological brain age prediction accuracy and biological information captured in the BAG.

Methods

T1-weighted MRI, containing brain tissue information, and magnetic resonance angiography (MRA), providing information about brain arteries, from 1,658 predominantly healthy adults were used. The volumes, surface areas, and cortical thickness of brain structures were extracted from the T1-weighted MRI data, while artery density and thickness within the major blood flow territories and thickness of the major arteries were extracted from MRA data. Independent multilayer perceptron and CNN models were trained to estimate the brain age from the hand-crafted features and image data, respectively. Next, both approaches were fused to assess the benefits of combining image data and hand-crafted features for brain age prediction.

Results

The combined model achieved a mean absolute error of 4 years between the chronological and predicted biological brain age. Among the independent models, the lowest mean absolute error was observed for the CNN using T1-weighted MRI data (4.2 years). When evaluating the BAGs obtained using the different approaches and imaging modalities, diverging associations between cardiovascular risk factors were found. For example, BAGs obtained from the CNN models showed an association with systolic blood pressure, while BAGs obtained from hand-crafted measurements showed greater associations with obesity markers.

Discussion

In conclusion, the use of more diverse sources of data can improve brain age estimation modeling and capture more diverse biological deviations from normal aging.

Fatness, fitness and the aging brain: A cross sectional study of the associations between a physiological estimate of brain age and physical fitness, activity, sleep, and body composition

Introduction

Changes in brain structure and function occur with aging. However, there is substantial heterogeneity both in terms of when these changes begin, and the rate at which they progress. Understanding the mechanisms and/or behaviors underlying this heterogeneity may allow us to act to target and slow negative changes associated with aging.

Methods

Using T1 weighted MRI images, we applied a novel algorithm to determine the physiological age of the brain (brain-predicted age) and the predicted age difference between this physiologically based estimate and chronological age (BrainPAD) to 551 sedentary adults aged 65 to 84 with self-reported cognitive complaint measured at baseline as part of a larger study. We also assessed maximal aerobic capacity with a graded exercise test, physical activity and sleep with accelerometers, and body composition with dual energy x-ray absorptiometry. Associations were explored both linearly and logistically using categorical groupings.

Results

Visceral Adipose Tissue (VAT), Total Sleep Time (TST) and maximal aerobic capacity all showed significant associations with BrainPAD. Greater VAT was associated with higher (i.e,. older than chronological) BrainPAD (r = 0.149 p = 0.001)Greater TST was associated with higher BrainPAD (r = 0.087 p = 0.042) and greater aerobic capacity was associated with lower BrainPAD (r = - 0.088 p = 0.040). With linear regression, both VAT and TST remained significant (p = 0.036 and 0.008 respectively). Each kg of VAT predicted a 0.741 year increase in BrainPAD, and each hour of increased TST predicted a 0.735 year increase in BrainPAD. Maximal aerobic capacity did not retain statistical significance in fully adjusted linear models.

Discussion

Accumulation of visceral adipose tissue and greater total sleep time, but not aerobic capacity, total daily physical activity, or sleep quantity and/or quality are associated with brains that are physiologically older than would be expected based upon chronological age alone (BrainPAD).

White matter hyperintensity load is associated with premature brain aging

BACKGROUND

Brain age is an MRI-derived estimate of brain tissue loss that has a similar pattern to aging-related atrophy. White matter hyperintensities (WMHs) are neuroimaging markers of small vessel disease and may represent subtle signs of brain compromise. We tested the hypothesis that WMHs are independently associated with premature brain age in an original aging cohort.

METHODS

Brain age was calculated using machine-learning on whole-brain tissue estimates from T1-weighted images using the BrainAgeR analysis pipeline in 166 healthy adult participants. WMHs were manually delineated on FLAIR images. WMH load was defined as the cumulative volume of WMHs. A positive difference between estimated brain age and chronological age (BrainGAP) was used as a measure of premature brain aging. Then, partial Pearson correlations between BrainGAP and volume of WMHs were calculated (accounting for chronological age).

RESULTS

Brain and chronological age were strongly correlated (r(163)=0.932, p<0.001). There was significant negative correlation between BrainGAP scores and chronological age (r(163)=-0.244, p<0.001) indicating that younger participants had higher BrainGAP (premature brain aging). Chronological age also showed a positive correlation with WMH load (r(163)=0.506, p<0.001) indicating older participants had increased WMH load. Controlling for chronological age, there was a statistically significant relationship between premature brain aging and WMHs load (r(163)=0.216, p=0.003). Each additional year in brain age beyond chronological age corresponded to an additional 1.1mm3 in WMH load.

CONCLUSIONS

WMHs are an independent factor associated with premature brain aging. This finding underscores the impact of white matter disease on global brain integrity and progressive age-like brain atrophy.

Deep learning prediction of stroke thrombus red blood cell content from multiparametric MRI

BACKGROUND AND PURPOSE

Thrombus red blood cell (RBC) content has been shown to be a significant factor influencing the efficacy of acute ischemic stroke treatment. In this study, our objective was to evaluate the ability of convolutional neural networks (CNNs) to predict ischemic stroke thrombus RBC content using multiparametric MR images.

MATERIALS AND METHODS

Retrieved stroke thrombi were scanned ex vivo using a three-dimensional multi-echo gradient echo sequence and histologically analyzed. 188 thrombus R2*, quantitative susceptibility mapping and late-echo GRE magnitude image slices were used to train and test a 3-layer CNN through cross-validation. Data augmentation techniques involving input equalization and random image transformation were employed to improve network performance. The network was assessed for its ability to quantitatively predict RBC content and to classify thrombi into RBC-rich and RBC-poor groups.

RESULTS

The CNN predicted thrombus RBC content with an accuracy of 62% (95% CI 48-76%) when trained on the original dataset and improved to 72% (95% CI 60-84%) on the augmented dataset. The network classified thrombi as RBC-rich or poor with an accuracy of 71% (95% CI 58-84%) and an area under the curve of 0.72 (95% CI 0.57-0.87) when trained on the original dataset and improved to 80% (95% CI 69-91%) and 0.84 (95% CI 0.73-0.95), respectively, on the augmented dataset.

CONCLUSIONS

The CNN was able to accurately predict thrombus RBC content using multiparametric MR images, and could provide a means to guide treatment strategy in acute ischemic stroke.

Predicting the brain age of children with cerebral palsy using a two-dimensional convolutional neural networks prediction model without gray and white matter segmentation

Background

Abnormal brain development is common in children with cerebral palsy (CP), but there are no recent reports on the actual brain age of children with CP.

Objective

Our objective is to use the brain age prediction model to explore the law of brain development in children with CP.

Methods

A two-dimensional convolutional neural networks brain age prediction model was designed without segmenting the white and gray matter. Training and testing brain age prediction model using magnetic resonance images of healthy people in a public database. The brain age of children with CP aged 5-27 years old was predicted.

Results

The training dataset mean absolute error (MAE) = 1.85, r = 0.99; test dataset MAE = 3.98, r = 0.95. The brain age gap estimation (BrainAGE) of the 5- to 27-year-old patients with CP was generally higher than that of healthy peers (p < 0.0001). The BrainAGE of male patients with CP was higher than that of female patients (p < 0.05). The BrainAGE of patients with bilateral spastic CP was higher than those with unilateral spastic CP (p < 0.05).

Conclusion

A two-dimensional convolutional neural networks brain age prediction model allows for brain age prediction using routine hospital T1-weighted head MRI without segmenting the white and gray matter of the brain. At the same time, these findings suggest that brain aging occurs in patients with CP after brain damage. Female patients with CP are more likely to return to their original brain development trajectory than male patients after brain injury. In patients with spastic CP, brain aging is more serious in those with bilateral cerebral hemisphere injury than in those with unilateral cerebral hemisphere injury.

Improving the repeatability of deep learning models with Monte Carlo dropout

The integration of artificial intelligence into clinical workflows requires reliable and robust models. Repeatability is a key attribute of model robustness. Ideal repeatable models output predictions without variation during independent tests carried out under similar conditions. However, slight variations, though not ideal, may be unavoidable and acceptable in practice. During model development and evaluation, much attention is given to classification performance while model repeatability is rarely assessed, leading to the development of models that are unusable in clinical practice. In this work, we evaluate the repeatability of four model types (binary classification, multi-class classification, ordinal classification, and regression) on images that were acquired from the same patient during the same visit. We study the each model’s performance on four medical image classification tasks from public and private datasets: knee osteoarthritis, cervical cancer screening, breast density estimation, and retinopathy of prematurity. Repeatability is measured and compared on ResNet and DenseNet architectures. Moreover, we assess the impact of sampling Monte Carlo dropout predictions at test time on classification performance and repeatability. Leveraging Monte Carlo predictions significantly increases repeatability, in particular at the class boundaries, for all tasks on the binary, multi-class, and ordinal models leading to an average reduction of the 95% limits of agreement by 16% points and of the class disagreement rate by 7% points. The classification accuracy improves in most settings along with the repeatability. Our results suggest that beyond about 20 Monte Carlo iterations, there is no further gain in repeatability. In addition to the higher test-retest agreement, Monte Carlo predictions are better calibrated which leads to output probabilities reflecting more accurately the true likelihood of being correctly classified.

Interpretation for Individual Brain Age Prediction Based on Gray Matter Volume

The relationship between age and the central nervous system (CNS) in humans has been a classical issue that has aroused extensive attention. Especially for individuals, it is of far greater importance to clarify the mechanisms between CNS and age. The primary goal of existing methods is to use MR images to derive high-accuracy predictions for age or degenerative diseases. However, the associated mechanisms between the images and the age have rarely been investigated. In this paper, we address the correlation between gray matter volume (GMV) and age, both in terms of gray matter themselves and their interaction network, using interpretable machine learning models for individuals. Our goal is not only to predict age accurately but more importantly, to explore the relationship between GMV and age. In addition to targeting each individual, we also investigate the dynamic properties of gray matter and their interaction network with individual age. The results show that the mean absolute error (MAE) of age prediction is 7.95 years. More notably, specific locations of gray matter and their interactions play different roles in age, and these roles change dynamically with age. The proposed method is a data-driven approach, which provides a new way to study aging mechanisms and even to diagnose degenerative brain diseases.

Multidimensional brain-age prediction reveals altered brain developmental trajectory in psychiatric disorders

Brain-age prediction has emerged as a novel approach for studying brain development. However, brain regions change in different ways and at different rates. Unitary brain-age indices represent developmental status averaged across the whole brain and therefore do not capture the divergent developmental trajectories of various brain structures. This staggered developmental unfolding, determined by genetics and postnatal experience, is implicated in the progression of psychiatric and neurological disorders. We propose a multidimensional brain-age index (MBAI) that provides regional age predictions. Using a database of 556 individuals, we identified clusters of imaging features with distinct developmental trajectories and built machine learning models to obtain brain-age predictions from each of the clusters. Our results show that the MBAI provides a flexible analysis of region-specific brain-age changes that are invisible to unidimensional brain-age. Importantly, brain-ages computed from region-specific feature clusters contain complementary information and demonstrate differential ability to distinguish disorder groups (e.g., depression and oppositional defiant disorder) from healthy controls. In summary, we show that MBAI is sensitive to alterations in brain structures and captures distinct regional change patterns that may serve as biomarkers that contribute to our understanding of healthy and pathological brain development and the characterization and diagnosis of psychiatric disorders.

Neuroimaging-Based Brain Age Estimation: A Promising Personalized Biomarker in Neuropsychiatry

It is now possible to estimate an individual's brain age via brain scans and machine-learning models. This validated technique has opened up new avenues for addressing clinical questions in neurology, and, in this review, we summarize the many clinical applications of brain-age estimation in neuropsychiatry and general populations. We first provide an introduction to typical neuroimaging modalities, feature extraction methods, and machine-learning models that have been used to develop a brain-age estimation framework. We then focus on the significant findings of the brain-age estimation technique in the field of neuropsychiatry as well as the usefulness of the technique for addressing clinical questions in neuropsychiatry. These applications may contribute to more timely and targeted neuropsychiatric therapies. Last, we discuss the practical problems and challenges described in the literature and suggest some future research directions.

Accelerated brain aging in individuals with diabetes: Association with poor glycemic control and increased all-cause mortality

BACKGROUND

Diabetes has been linked to accelerated brain aging, i.e., neuroimaging-predicted age of brain is higher than chronological age. This report evaluated whether accelerated brain aging in diabetes is associated with higher levels of glycated hemoglobin (HbA1c) and increased mortality.

METHODS

Brain age in Dallas Heart Study (n = 1949) was estimated using T1-weighted magnetic resonance imaging (MRI) scans and a previously-published Gaussian Processes Regression model. Accelerated brain aging (adjusted Δ brain age) was computed as follows: (brain age adjusted for chronological age)-minus-(chronological age). Mortality data until 12/31/2016 were obtained from the National Death Index. Associations of adjusted Δ brain age with diabetes in full sample and with HbA1c in individuals with diabetes were evaluated. Proportion of association between diabetes and all-cause mortality that was accounted for by adjusted Δ brain age were evaluated with mediation analyses. Covariates included Framingham 10-year risk score, race/ethnicity, income, body mass index, and history of myocardial infarction.

RESULTS

Diabetes was associated with] higher adjusted Δ brain age [estimate= 1.79; 95% confidence interval (CI): 0.889, 2.68]. Among those with diabetes, higher HbA1c (log-base-2-transformed) was associated with higher adjusted Δ brain age (estimate=3.88; 95% CI: 1.47, 6.30). Over a median follow-up of 97.5 months, 24/246 (9.8%) with diabetes and 63/1703 (3.7%) without diabetes died. Adjusted Δ brain age accounted for 65.3 (95% CI: 39.3, 100.0)% of the association between diabetes and all-cause mortality.

CONCLUSION

Accelerated brain aging may be related to poor glycemic control in diabetes and partly account for the association between diabetes and all-cause mortality.

Assessing brain and biological aging trajectories associated with Alzheimer’s disease

The development of effective treatments to prevent and slow Alzheimer’s disease (AD) pathogenesis is needed in order to tackle the steady increase in the global prevalence of AD. This challenge is complicated by the need to identify key health shifts that precede the onset of AD and cognitive decline as these represent windows of opportunity for intervening and preventing disease. Such shifts may be captured through the measurement of biomarkers that reflect the health of the individual, in particular those that reflect brain age and biological age. Brain age biomarkers provide a composite view of the health of the brain based on neuroanatomical analyses, while biological age biomarkers, which encompass the epigenetic clock, provide a measurement of the overall health state of an individual based on DNA methylation analysis. Acceleration of brain and biological ages is associated with changes in cognitive function, as well as neuropathological markers of AD. In this mini-review, we discuss brain age and biological age research in the context of cognitive decline and AD. While more research is needed, studies show that brain and biological aging trajectories are variable across individuals and that such trajectories are non-linear at older ages. Longitudinal monitoring of these biomarkers may be valuable for enabling earlier identification of divergent pathological trajectories toward AD and providing insight into points for intervention.

Artificial neural networks for non-linear age correction of diffusion metrics in the brain

Human aging is characterized by progressive loss of physiological functions. To assess changes in the brain that occur with increasing age, the concept of brain aging has gained momentum in neuroimaging with recent advancements in statistical regression and machine learning (ML). A common technique to assess the brain age of a person is, first, fitting a regression model to neuroimaging data from a group of healthy subjects, and then, using the resulting model for age prediction. Although multiparametric MRI-based models generally perform best, models solely based on diffusion tensor imaging have achieved similar results, with the benefits of faster data acquisition and better replicability across scanners and field strengths. In the present study, we developed an artificial neural network (ANN) for brain age prediction based upon tract-based fractional anisotropy (FA). Consequently, we investigated if this age-prediction model could also be used for non-linear age correction of white matter diffusion metrics in healthy adults. The brain age prediction accuracy of the ANN (R 2 = 0.47) was similar to established multimodal models. The comparison of the ANN-based age-corrected FA with the tract-wise linear age-corrected FA resulted in an R 2 value of 0.90 [0.82; 0.93] and a mean difference of 0.00 [-0.04; 0.05] for all tract systems combined. In conclusion, this study demonstrated the applicability of complex ANN models to non-linear age correction of tract-based diffusion metrics as a proof of concept.

Sex differences in predictors and regional patterns of brain age gap estimates

The brain-age-gap estimate (brainAGE) quantifies the difference between chronological age and age predicted by applying machine-learning models to neuroimaging data and is considered a biomarker of brain health. Understanding sex differences in brainAGE is a significant step toward precision medicine. Global and local brainAGE (G-brainAGE and L-brainAGE, respectively) were computed by applying machine learning algorithms to brain structural magnetic resonance imaging data from 1113 healthy young adults (54.45% females; age range: 22-37 years) participating in the Human Connectome Project. Sex differences were determined in G-brainAGE and L-brainAGE. Random forest regression was used to determine sex-specific associations between G-brainAGE and non-imaging measures pertaining to sociodemographic characteristics and mental, physical, and cognitive functions. L-brainAGE showed sex-specific differences; in females, compared to males, L-brainAGE was higher in the cerebellum and brainstem and lower in the prefrontal cortex and insula. Although sex differences in G-brainAGE were minimal, associations between G-brainAGE and non-imaging measures differed between sexes with the exception of poor sleep quality, which was common to both. While univariate relationships were small, the most important predictor of higher G-brainAGE was self-identification as non-white in males and systolic blood pressure in females. The results demonstrate the value of applying sex-specific analyses and machine learning methods to advance our understanding of sex-related differences in factors that influence the rate of brain aging and provide a foundation for targeted interventions.

Differentiate preterm and term infant brains and characterize the corresponding biomarkers via DICCCOL-based multi-modality graph neural networks

Preterm birth is a worldwide problem that affects infants throughout their lives significantly. Therefore, differentiating brain disorders, and further identifying and characterizing the corresponding biomarkers are key issues to investigate the effects of preterm birth, which facilitates the interventions for neuroprotection and improves outcomes of prematurity. Until now, many efforts have been made to study the effects of preterm birth; however, most of the studies merely focus on either functional or structural perspective. In addition, an effective framework not only jointly studies the brain function and structure at a group-level, but also retains the individual differences among the subjects. In this study, a novel dense individualized and common connectivity-based cortical landmarks (DICCCOL)-based multi-modality graph neural networks (DM-GNN) framework is proposed to differentiate preterm and term infant brains and characterize the corresponding biomarkers. This framework adopts the DICCCOL system as the initialized graph node of GNN for each subject, utilizing both functional and structural profiles and effectively retaining the individual differences. To be specific, functional magnetic resonance imaging (fMRI) of the brain provides the features for the graph nodes, and brain fiber connectivity is utilized as the structural representation of the graph edges. Self-attention graph pooling (SAGPOOL)-based GNN is then applied to jointly study the function and structure of the brain and identify the biomarkers. Our results successfully demonstrate that the proposed framework can effectively differentiate the preterm and term infant brains. Furthermore, the self-attention-based mechanism can accurately calculate the attention score and recognize the most significant biomarkers. In this study, not only 87.6% classification accuracy is observed for the developing Human Connectome Project (dHCP) dataset, but also distinguishing features are explored and extracted. Our study provides a novel and uniform framework to differentiate brain disorders and characterize the corresponding biomarkers.

Decentralized Brain Age Estimation Using MRI Data

Recent studies have demonstrated that neuroimaging data can be used to estimate biological brain age, as it captures information about the neuroanatomical and functional changes the brain undergoes during development and the aging process. However, researchers often have limited access to neuroimaging data because of its challenging and expensive acquisition process, thereby limiting the effectiveness of the predictive model. Decentralized models provide a way to build more accurate and generalizable prediction models, bypassing the traditional data-sharing methodology. In this work, we propose a decentralized method for biological brain age estimation using support vector regression models and evaluate it on three different feature sets, including both volumetric and voxelwise structural MRI data as well as resting functional MRI data. The results demonstrate that our decentralized brain age regression models can achieve similar performance compared to the models trained with all the data in one location.

Brain age estimation reveals older adults' accelerated senescence after traumatic brain injury

Adults aged 60 and over are most vulnerable to mild traumatic brain injury (mTBI). Nevertheless, the extent to which chronological age (CA) at injury affects TBI-related brain aging is unknown. This study applies Gaussian process regression to T1-weighted magnetic resonance images (MRIs) acquired within [Formula: see text]7 days and again [Formula: see text]6 months after a single mTBI sustained by 133 participants aged 20-83 (CA [Formula: see text] = 42.6 ± 17 years; 51 females). Brain BAs are estimated, modeled, and compared as a function of sex and CA at injury using a statistical model selection procedure. On average, the brains of older adults age by 15.3 ± 6.9 years after mTBI, whereas those of younger adults age only by 1.8 ± 5.6 years, a significant difference (Welch's t32 =  - 9.17, p ≃ 9.47 × 10-11). For an adult aged [Formula: see text]30 to [Formula: see text]60, the expected amount of TBI-related brain aging is [Formula: see text]3 years greater than in an individual younger by a decade. For an individual over [Formula: see text]60, the respective amount is [Formula: see text]7 years. Despite no significant sex differences in brain aging (Welch's t108 = 0.78, p > 0.78), the statistical test is underpowered. BAs estimated at acute baseline versus chronic follow-up do not differ significantly (t264 = 0.41, p > 0.66, power = 80%), suggesting negligible TBI-related brain aging during the chronic stage of TBI despite accelerated aging during the acute stage. Our results indicate that a single mTBI sustained after age [Formula: see text]60 involves approximately [Formula: see text]10 years of premature and lasting brain aging, which is MRI detectable as early as [Formula: see text]7 days post-injury.

Accurate segmentation of neonatal brain MRI with deep learning

An important step toward delivering an accurate connectome of the human brain is robust segmentation of 3D Magnetic Resonance Imaging (MRI) scans, which is particularly challenging when carried out on perinatal data. In this paper, we present an automated, deep learning-based pipeline for accurate segmentation of tissues from neonatal brain MRI and extend it by introducing an age prediction pathway. A major constraint to using deep learning techniques on developing brain data is the need to collect large numbers of ground truth labels. We therefore also investigate two practical approaches that can help alleviate the problem of label scarcity without loss of segmentation performance. First, we examine the efficiency of different strategies of distributing a limited budget of annotated 2D slices over 3D training images. In the second approach, we compare the segmentation performance of pre-trained models with different strategies of fine-tuning on a small subset of preterm infants. Our results indicate that distributing labels over a larger number of brain scans can improve segmentation performance. We also show that even partial fine-tuning can be superior in performance to a model trained from scratch, highlighting the relevance of transfer learning strategies under conditions of label scarcity. We illustrate our findings on large, publicly available T1- and T2-weighted MRI scans (n = 709, range of ages at scan: 26–45 weeks) obtained retrospectively from the Developing Human Connectome Project (dHCP) cohort.

Deep Learning Assessment for Mining Important Medical Image Features of Various Modalities

Deep learning (DL) is a well-established pipeline for feature extraction in medical and nonmedical imaging tasks, such as object detection, segmentation, and classification. However, DL faces the issue of explainability, which prohibits reliable utilisation in everyday clinical practice. This study evaluates DL methods for their efficiency in revealing and suggesting potential image biomarkers. Eleven biomedical image datasets of various modalities are utilised, including SPECT, CT, photographs, microscopy, and X-ray. Seven state-of-the-art CNNs are employed and tuned to perform image classification in tasks. The main conclusion of the research is that DL reveals potential biomarkers in several cases, especially when the models are trained from scratch in domains where low-level features such as shapes and edges are not enough to make decisions. Furthermore, in some cases, device acquisition variations slightly affect the performance of DL models.

OpenBHB: a Large-Scale Multi-Site Brain MRI Data-set for Age Prediction and Debiasing

Prediction of chronological age from neuroimaging in the healthy population is an important issue because the deviations from normal brain age may highlight abnormal trajectories towards brain disorders. As a first step, ML models have emerged to predict chronological age from brain MRI, as a proxy measure of biological age. However, there is currently no consensus w.r.t which Machine Learning (ML) model is best suited for this task, largely because of a lack of public benchmark. Furthermore, new large emerging population neuroimaging datasets are often biased by the acquisition center images are coming from. This bias heavily deteriorates models generalization capacities, especially for Deep Learning (DL) algorithms that are known to overfit rapidly on the simplest features (known as simplicity bias). Here we propose a new public benchmarking resource, namely Open Big Healthy Brains (OpenBHB), along with a challenge for both brain age prediction and site-effect removal through a representation learning framework. OpenBHB is large-scale, gathering >5K 3D T1 brain MRI from Healthy Controls (HC) and highly multi-sites, aggregating >60 centers worldwide and 10 studies. OpenBHB is expected to grow both in terms of available modalities and number of subjects. All OpenBHB datasets are uniformly preprocessed, including quality check, with container technologies that consist in: 3D Voxel-Based Morphometry maps (VBM from CAT12), quasi-raw (simple linear alignment of images), and Surface-Based Morphometry indices (SBM, from FreeSurfer). The OpenBHB challenge is permanent and we provide all tools, materials and tutorials for participants to easily submit and benchmark their model against each other on a public leaderboard.

Brain age vector: A measure of brain aging with enhanced neurodegenerative disorder specificity

Neuroimaging‐driven brain age estimation has become popular in measuring brain aging and identifying neurodegenerations. However, the single estimated brain age (gap) compromises regional variations of brain aging, losing spatial specificity across diseases which is valuable for early screening. In this study, we combined brain age modeling with Shapley Additive Explanations to measure brain aging as a feature contribution vector underlying spatial pathological aging mechanism. Specifically, we regressed age with volumetric brain features using machine learning to construct the brain age model, and model‐agnostic Shapley values were calculated to attribute regional brain aging for each subject's age estimation, forming the brain age vector. Spatial specificity of the brain age vector was evaluated among groups of normal aging, prodromal Parkinson disease (PD), stable mild cognitive impairment (sMCI), and progressive mild cognitive impairment (pMCI). Machine learning methods were adopted to examine the discriminability of the brain age vector in early disease screening, compared with the other two brain aging metrics (single brain age gap, regional brain age gaps) and brain volumes. Results showed that the proposed brain age vector accurately reflected disorder‐specific abnormal aging patterns related to the medial temporal and the striatum for prodromal AD (sMCI vs. pMCI) and PD (healthy controls [HC] vs. prodromal PD), respectively, and demonstrated outstanding performance in early disease screening, with area under the curves of 83.39% and 72.28% in detecting pMCI and prodromal PD, respectively. In conclusion, the proposed brain age vector effectively improves spatial specificity of brain aging measurement and enables individual screening of neurodegenerative diseases.

Ayu-Characterization of healthy aging from neuroimaging data with deep learning and rsfMRI

Estimating brain age and establishing functional biomarkers that are prescient of cognitive declines resulting from aging and different neurological diseases are still open research problems. Functional measures such as functional connectivity are gaining interest as potentially more subtle markers of neurodegeneration. However, brain functions are also affected by “normal” brain aging. More information is needed on how functional connectivity relates to aging, particularly in the absence of neurodegenerative disorders. Resting-state fMRI enables us to investigate functional brain networks and can potentially help us understand the processes of development as well as aging in terms of how functional connectivity (FC) matures during the early years and declines during the late years. We propose models for estimation of the chronological age of a healthy person from the resting state brain activation (rsfMRI). In this work, we utilized a dataset (N = 638, age-range 20–88) comprising rsfMRI images from the Cambridge Centre for Aging and Neuroscience (Cam-CAN) repository of a healthy population. We propose an age prediction pipeline Ayu which consists of data preprocessing, feature selection, and an attention-based model for deep learning architecture for brain age assessment. We extracted features from the static functional connectivity (sFC) to predict the subject's age and classified them into different age groups (young, middle, middle, and old ages). To the best of our knowledge, a classification accuracy of 72.619 % and a mean absolute error of 6.797, and an r² of 0.754 reported by our Ayu pipeline establish competitive benchmark results as compared to the state-of-the-art-approach. Furthermore, it is vital to identify how different functional regions of the brain are correlated. We also analyzed how functional regions contribute differently across ages by applying attention-based networks and integrated gradients. We obtained well-known resting-state networks using the attention model, which maps to within the default mode network, visual network, ventral attention network, limbic network, frontoparietal network, and somatosensory network connected to aging. Our analysis of fMRI data in healthy elderly Age groups revealed that dynamic FC tends to slow down and becomes less complex and more random with increasing age.

Invertible Modeling of Bidirectional Relationships in Neuroimaging With Normalizing Flows: Application to Brain Aging

Many machine learning tasks in neuroimaging aim at modeling complex relationships between a brain's morphology as seen in structural MR images and clinical scores and variables of interest. A frequently modeled process is healthy brain aging for which many image-based brain age estimation or age-conditioned brain morphology template generation approaches exist. While age estimation is a regression task, template generation is related to generative modeling. Both tasks can be seen as inverse directions of the same relationship between brain morphology and age. However, this view is rarely exploited and most existing approaches train separate models for each direction. In this paper, we propose a novel bidirectional approach that unifies score regression and generative morphology modeling and we use it to build a bidirectional brain aging model. We achieve this by defining an invertible normalizing flow architecture that learns a probability distribution of 3D brain morphology conditioned on age. The use of full 3D brain data is achieved by deriving a manifold-constrained formulation that models morphology variations within a low-dimensional subspace of diffeomorphic transformations. This modeling idea is evaluated on a database of MR scans of more than 5000 subjects. The evaluation results show that our bidirectional brain aging model (1) accurately estimates brain age, (2) is able to visually explain its decisions through attribution maps and counterfactuals, (3) generates realistic age-specific brain morphology templates, (4) supports the analysis of morphological variations, and (5) can be utilized for subject-specific brain aging simulation.

Life course, genetic, and neuropathological associations with brain age in the 1946 British Birth Cohort: a population-based study

BACKGROUND

A neuroimaging-based biomarker termed the brain age is thought to reflect variability in the brain's ageing process and predict longevity. Using Insight 46, a unique narrow-age birth cohort, we aimed to examine potential drivers and correlates of brain age.

METHODS

Participants, born in a single week in 1946 in mainland Britain, have had 24 prospective waves of data collection to date, including MRI and amyloid PET imaging at approximately 70 years old. Using MRI data from a previously defined selection of this cohort, we derived brain-predicted age from an established machine-learning model (trained on 2001 healthy adults aged 18-90 years); subtracting this from chronological age (at time of assessment) gave the brain-predicted age difference (brain-PAD). We tested associations with data from early life, midlife, and late life, as well as rates of MRI-derived brain atrophy.

FINDINGS

Between May 28, 2015, and Jan 10, 2018, 502 individuals were assessed as part of Insight 46. We included 456 participants (225 female), with a mean chronological age of 70·7 years (SD 0·7; range 69·2 to 71·9). The mean brain-predicted age was 67·9 years (8·2, 46·3 to 94·3). Female sex was associated with a 5·4-year (95% CI 4·1 to 6·8) younger brain-PAD than male sex. An increase in brain-PAD was associated with increased cardiovascular risk at age 36 years (β=2·3 [95% CI 1·5 to 3·0]) and 69 years (β=2·6 [1·9 to 3·3]); increased cerebrovascular disease burden (1·9 [1·3 to 2·6]); lower cognitive performance (-1·3 [-2·4 to -0·2]); and increased serum neurofilament light concentration (1·2 [0·6 to 1·9]). Higher brain-PAD was associated with future hippocampal atrophy over the subsequent 2 years (0·003 mL/year [0·000 to 0·006] per 5-year increment in brain-PAD). Early-life factors did not relate to brain-PAD. Combining 12 metrics in a hierarchical partitioning model explained 33% of the variance in brain-PAD.

INTERPRETATION

Brain-PAD was associated with cardiovascular risk, and imaging and biochemical markers of neurodegeneration. These findings support brain-PAD as an integrative summary metric of brain health, reflecting multiple contributions to pathological brain ageing, and which might have prognostic utility.

FUNDING

Alzheimer's Research UK, Medical Research Council Dementia Platforms UK, Selfridges Group Foundation, Wolfson Foundation, Wellcome Trust, Brain Research UK, Alzheimer's Association.

Deep Relation Learning for Regression and Its Application to Brain Age Estimation

Most deep learning models for temporal regression directly output the estimation based on single input images, ignoring the relationships between different images. In this paper, we propose deep relation learning for regression, aiming to learn different relations between a pair of input images. Four non-linear relations are considered: "cumulative relation," "relative relation," "maximal relation" and "minimal relation." These four relations are learned simultaneously from one deep neural network which has two parts: feature extraction and relation regression. We use an efficient convolutional neural network to extract deep features from the pair of input images and apply a Transformer for relation learning. The proposed method is evaluated on a merged dataset with 6,049 subjects with ages of 0-97 years using 5-fold cross-validation for the task of brain age estimation. The experimental results have shown that the proposed method achieved a mean absolute error (MAE) of 2.38 years, which is lower than the MAEs of 8 other state-of-the-art algorithms with statistical significance (p<0.05) in paired T-test (two-side).

Geometric deep learning reveals a structuro-temporal understanding of healthy and pathologic brain aging

Background

Brain age has historically been investigated primarily at the whole brain level. The ability to deconstruct the brain into its composite parts and explore brain age at the sub-structure level offers unique advantages. These include the exploration of dynamic and interconnected relationships between different brain structures in healthy and pathologic aging. To achieve this, individual brain structures can be rendered as surface representations on which morphologic analysis is carried out. Combining the advantages of deep learning with the strengths of surface analysis, we investigate the aging process at the individual structure level with the hypothesis being that pathologic aging does not uniformly affect the aging process of individual structures.

Methods

MRI data, age at scan time and diagnosis of dementia were collected from seven publicly available data repositories. The data from 17,440 unique subjects were collected, representing a total of 26,276 T1-weighted MRI accounting for longitudinal acquisitions. Surfaces were extracted for the cortex and seven subcortical structures. Deep learning networks were trained to estimate a subject's age either using several structures together or a single structure. We conducted a cross-sectional analysis to assess the difference between the predicted and actual ages for all structures between healthy subjects, individuals with mild cognitive impairment (MCI) or Alzheimer's disease dementia (ADD). We then performed a longitudinal analysis to assess the difference in the aging pace for each structure between stable healthy controls and healthy controls converting to either MCI or ADD.

Findings

Using an independent cohort of healthy subjects, age was well estimated for all structures. Cross-sectional analysis identified significantly larger predicted age for all structures in patients with either MCI and ADD compared to healthy subjects. Longitudinal analysis revealed varying degrees of involvement of individual subcortical structures for both age difference across groups and aging pace across time. These findings were most notable in the whole brain, cortex, hippocampus and amygdala.

Conclusion

Although similar patterns of abnormal aging were found related to MCI and ADD, the involvement of individual subcortical structures varied greatly and was consistently more pronounced in ADD patients compared to MCI patients.

Peripheral inflammation levels associated with degree of advanced brain aging in schizophrenia

Brain structural abnormalities have been demonstrated in schizophrenia (SZ); these resemble those seen in typical aging, but are seen at younger ages. Furthermore, SZ is associated with accelerated global brain aging, as measured by brain structure-based brain predicted age difference (Brain-PAD). High heterogeneity exists in the degree of brain abnormalities in SZ, and individual differences may be related to levels of peripheral inflammation and may relate to cognitive deficits and negative symptoms. The goal of our study was to investigate the relationship between brain aging, peripheral inflammation, and symptoms of SZ. We hypothesized older brain-PAD in SZ vs. healthy comparison (HC) participants, as well as positive relationships of brain-PAD with peripheral inflammation markers and symptoms in SZ. We analyzed data from two cross-sectional studies in SZ (n = 26; M/F: 21/5) and HC (n = 28; 20/8) (22-64 years). Brain-PAD was calculated using a previously validated Gaussian process regression model applied to raw T1-weighted MRI data. Plasma levels of inflammatory biomarkers (CRP, Eotaxin, Fractalkine, IP10, IL6, IL10, ICAM1, IFNγ, MCP1, MIP1β, SAA, TNFα, VEGF, VCAM1) and cognitive and negative symptoms were assessed. We observed a higher brain-PAD in SZ vs. HC, and advanced brain age relative to chronological age was related to higher peripheral levels of TNFα in the overall group and in the SZ group; other inflammatory markers were not related to brain-PAD. Within the SZ group, we observed no association between cognitive or negative symptoms and brain-PAD. These results support our hypothesis of advanced brain aging in SZ. Furthermore, our findings on the relationship of the pro-inflammatory cytokine TNFα with higher brain-PAD of SZ are relevant to explain heterogeneity of brain ages in SZ, but we did not find strong evidence for cognitive or negative symptom relationships with brain-PAD.

A novel network architecture combining central-peripheral deviation with image-based convolutional neural networks for diffusion tensor imaging studies

Brain imaging research is a very challenging topic due to complex structure and lack of explicitly identifiable features in the image. With the advancement of magnetic resonance imaging (MRI) technologies, such as diffusion tensor imaging (DTI), developing classification methods to improve clinical diagnosis is crucial. This paper proposes a classification method for DTI data based on a novel neural network strategy that combines a convolutional neural network (CNN) with a multilayer neural network using central-peripheral deviation (CPD), which reflects diffusion dynamics in the white matter by spatially evaluating the deviation of diffusion coefficients between the inner and outer parts of the brain. In our method, a multilayer perceptron (MLP) using CPD is combined with the final layers for classification after reducing the dimensions of images in the convolutional layers of the neural network architecture. In terms of training loss and the classification error, the proposed classification method improves the existing image classification with CNN. For real data analysis, we demonstrate how to process raw DTI image data sets obtained from a traumatic brain injury study (MagNeTS) and a brain atlas construction study (ICBM), and apply the proposed approach to the data, successfully improving classification performance with two age groups.

Connectome-based predictive models using resting-state fMRI for studying brain aging

Changes in the brain with age can provide useful information regarding an individual's chronological age. studies have suggested that functional connectomes identified via resting-state functional magnetic resonance imaging (fMRI) could be a powerful feature for predicting an individual's age. We applied connectome-based predictive modeling (CPM) to investigate individual chronological age predictions via resting-state fMRI using open-source datasets. The significant feature for age prediction was confirmed in 168 subjects from the Southwest University Adult Lifespan Dataset. The higher contributing nodes for age production included a positive connection from the left inferior parietal sulcus and a negative connection from the right middle temporal sulcus. On the network scale, the subcortical-cerebellum network was the dominant network for age prediction. The generalizability of CPM, which was constructed using the identified features, was verified by applying this model to independent datasets that were randomly selected from the Autism Brain Imaging Data Exchange I and the Open Access Series of Imaging Studies 3. CPM via resting-state fMRI is a potential robust predictor for determining an individual's chronological age from changes in the brain.

Interrelating differences in structural and functional connectivity in the older adult's brain

In the normal aging process, the functional connectome restructures and shows a shift from more segregated to more integrated brain networks, which manifests itself in highly different cognitive performances in older adults. Underpinnings of this reorganization are not fully understood, but may be related to age-related differences in structural connectivity, the underlying scaffold for information exchange between regions. The structure-function relationship might be a promising factor to understand the neurobiological sources of interindividual cognitive variability, but remain unclear in older adults. Here, we used diffusion weighted and resting-state functional magnetic resonance imaging as well as cognitive performance data of 573 older subjects from the 1000BRAINS cohort (55-85 years, 287 males) and performed a partial least square regression on 400 regional functional and structural connectivity (FC and SC, respectively) estimates comprising seven resting-state networks. Our aim was to identify FC and SC patterns that are, together with cognitive performance, characteristic of the older adults aging process. Results revealed three different aging profiles prevalent in older adults. FC was found to behave differently depending on the severity of age-related SC deteriorations. A functionally highly interconnected system is associated with a structural connectome that shows only minor age-related decreases. Because this connectivity profile was associated with the most severe age-related cognitive decline, a more interconnected FC system in older adults points to a process of dedifferentiation. Thus, functional network integration appears to increase primarily when SC begins to decline, but this does not appear to mitigate the decline in cognitive performance.

Glucose metabolism patterns: A potential index to characterize brain ageing and predict high conversion risk into cognitive impairment

Exploring individual hallmarks of brain ageing is important. Here, we propose the age-related glucose metabolism pattern (ARGMP) as a potential index to characterize brain ageing in cognitively normal (CN) elderly people. We collected 18F-fluorodeoxyglucose (18F-FDG) PET brain images from two independent cohorts: the Alzheimer's Disease Neuroimaging Initiative (ADNI, N = 127) and the Xuanwu Hospital of Capital Medical University, Beijing, China (N = 84). During follow-up (mean 80.60 months), 23 participants in the ADNI cohort converted to cognitive impairment. ARGMPs were identified using the scaled subprofile model/principal component analysis method, and cross-validations were conducted in both independent cohorts. A survival analysis was further conducted to calculate the predictive effect of conversion risk by using ARGMPs. The results showed that ARGMPs were characterized by hypometabolism with increasing age primarily in the bilateral medial superior frontal gyrus, anterior cingulate and paracingulate gyri, caudate nucleus, and left supplementary motor area and hypermetabolism in part of the left inferior cerebellum. The expression network scores of ARGMPs were significantly associated with chronological age (R = 0.808, p < 0.001), which was validated in both the ADNI and Xuanwu cohorts. Individuals with higher network scores exhibited a better predictive effect (HR: 0.30, 95% CI: 0.1340 ~ 0.6904, p = 0.0068). These findings indicate that ARGMPs derived from CN participants may represent a novel index for characterizing brain ageing and predicting high conversion risk into cognitive impairment.

Deep neural networks learn general and clinically relevant representations of the ageing brain

The discrepancy between chronological age and the apparent age of the brain based on neuroimaging data - the brain age delta - has emerged as a reliable marker of brain health. With an increasing wealth of data, approaches to tackle heterogeneity in data acquisition are vital. To this end, we compiled raw structural magnetic resonance images into one of the largest and most diverse datasets assembled (n=53542), and trained convolutional neural networks (CNNs) to predict age. We achieved state-of-the-art performance on unseen data from unknown scanners (n=2553), and showed that higher brain age delta is associated with diabetes, alcohol intake and smoking. Using transfer learning, the intermediate representations learned by our model complemented and partly outperformed brain age delta in predicting common brain disorders. Our work shows we can achieve generalizable and biologically plausible brain age predictions using CNNs trained on heterogeneous datasets, and transfer them to clinical use cases.

Multimodal MRI-Based Whole-Brain Assessment in Patients In Anoxoischemic Coma by Using 3D Convolutional Neural Networks

Background

There is an unfulfilled need to find the best way to automatically capture, analyze, organize, and merge structural and functional brain magnetic resonance imaging (MRI) data to ultimately extract relevant signals that can assist the medical decision process at the bedside of patients in postanoxic coma. We aimed to develop and validate a deep learning model to leverage multimodal 3D MRI whole-brain times series for an early evaluation of brain damages related to anoxoischemic coma.

Methods

This proof-of-concept, prospective, cohort study was undertaken at the intensive care unit affiliated with the University Hospital (Toulouse, France), between March 2018 and May 2020. All patients were scanned in coma state at least 2 days (4 ± 2 days) after cardiac arrest. Over the same period, age-matched healthy volunteers were recruited and included. Brain MRI quantification encompassed both “functional data” from regions of interest (precuneus and posterior cingulate cortex) with whole-brain functional connectivity analysis and “structural data” (gray matter volume, T1-weighted, fractional anisotropy, and mean diffusivity). A specifically designed 3D convolutional neuronal network (CNN) was created to allow conscious state discrimination (coma vs. controls) by using raw MRI indices as the input. A voxel-wise visualization method based on the study of convolutional filters was applied to support CNN outcome. The Ethics Committee of the University Teaching Hospital of Toulouse, France (2018-A31) approved the study and informed consent was obtained from all participants.

Results

The final cohort consisted of 29 patients in postanoxic coma and 34 healthy volunteers. Coma patients were successfully discerned from controls by using 3D CNN in combination with different MR indices. The best accuracy was achieved by functional MRI data, in particular with resting-state functional MRI of the posterior cingulate cortex, with an accuracy of 0.96 (range 0.94–0.98) on the test set from 10-time repeated tenfold cross-validation. Even more satisfactory performances were achieved through the majority voting strategy, which was able to compensate for mistakes from single MR indices. Visualization maps allowed us to identify the most relevant regions for each MRI index, notably regions previously described as possibly being involved in consciousness emergence. Interestingly, a posteriori analysis of misclassified patients indicated that they may present some common functional MRI traits with controls, which suggests further favorable outcomes.

Conclusions

A fully automated identification of clinically relevant signals from complex multimodal neuroimaging data is a major research topic that may bring a radical paradigm shift in the neuroprognostication of patients with severe brain injury. We report for the first time a successful discrimination between patients in postanoxic coma patients from people serving as controls by using 3D CNN whole-brain structural and functional MRI data.

Clinical Trial Numberhttp://ClinicalTrials.gov (No. NCT03482115).

Supplementary Information

The online version contains supplementary material available at 10.1007/s12028-022-01525-z.

A model of healthy aging based on smartphone interactions reveals advanced behavioral age in neurological disease

Smartphones offer unique opportunities to trace the convoluted behavioral patterns accompanying healthy aging. Here we captured smartphone touchscreen interactions from a healthy population (N = 684, ∼309 million interactions) spanning 16 to 86 years of age and trained a decision tree regression model to estimate chronological age based on the interactions. The interactions were clustered according to their next interval dynamics to quantify diverse smartphone behaviors. The regression model well-estimated the chronological age in health (mean absolute error = 6 years, R² = 0.8). We next deployed this model on a population of stroke survivors (N = 41) to find larger prediction errors such that the estimated age was advanced by 6 years. A similar pattern was observed in people with epilepsy (N = 51), with prediction errors advanced by 10 years. The smartphone behavioral model trained in health can be used to study altered aging in neurological diseases.

•

A smartphone data-driven model was trained to estimate chronological age

•

The model trained in health performed well to estimate the age

•

The same model estimated advanced aging in stroke and epilepsy

•

Smartphone-based model of healthy behavior may help understand aging in diseases