Brain age prediction using fMRI network coupling in youths and associations with psychiatric symptoms

AbstractObjectiveMagnetic resonance imaging (MRI) has shown that estimated brain age is deviant from chronological age in various common brain disorders. Brain age estimation could be useful for investigating patterns of brain maturation and integrity, aiding to elucidate brain mechanisms underlying these heterogeneous conditions. Here, we examined functional brain age in two large samples of children and adolescents and its relation to mental health.MethodsWe used resting-state fMRI data from the Philadelphia Neurodevelopmental Cohort (PNC; n=1126, age range 8-22 years) to estimate functional connectivity between brain networks, and utilized these as features for brain age prediction. We applied the prediction model to 1387 individuals (age range 8-22 years) in the Healthy Brain Network sample (HBN). In addition, we estimated brain age in PNC using a cross-validation framework. Next, we tested for associations between brain age gap and various aspects of psychopathology and cognitive performance.ResultsOur model was able to predict age in the independent test samples, with a model performance of r=0.54 for the HBN test set, supporting consistency in functional connectivity patterns between samples and scanners. Linear models revealed a significant association between brain age gap and psychopathology in PNC, where individuals with a lower estimated brain age, had a higher overall symptom burden. These associations were not replicated in HBN.DiscussionOur findings support the use of brain age prediction from fMRI-based connectivity. While requiring further extensions and validations, the approach may be instrumental for detecting brain phenotypes related to intrinsic connectivity and could assist in characterizing risk in non-typically developing populations.

Download Full-text

Reliable longitudinal brain age prediction in stroke patients: Associations with cognitive function and response to cognitive training

10.1101/687079 ◽

2019 ◽

Cited By ~ 1

Author(s):

Geneviève Richard ◽

Knut Kolskår ◽

Kristine M. Ulrichsen ◽

Tobias Kaufmann ◽

Dag Alnæs ◽

...

Keyword(s):

Cognitive Training ◽

Outcome Prediction ◽

Cognitive Intervention ◽

Chronological Age ◽

Double Blind Study ◽

Stroke Patients ◽

Brain Morphometry ◽

Age Gap ◽

Brain Age ◽

Age Prediction

AbstractCognitive deficits are important predictors for outcome, independence and quality of life after stroke, but often remain unnoticed and unattended because other impairments are more evident. Computerized cognitive training (CCT) is among the candidate interventions that may alleviate cognitive difficulties, but the evidence supporting its feasibility and effectiveness is scarce, partly due to the lack of tools for outcome prediction and monitoring. Magnetic resonance imaging (MRI) provides candidate markers for disease monitoring and outcome prediction. By integrating information not only about lesion extent and localization, but also regarding the integrity of the unaffected parts of the brain, advanced MRI provides relevant information for developing better prediction models in order to tailor cognitive intervention for patients, especially in a chronic phase.Using brain age prediction based on MRI based brain morphometry and machine learning, we tested the hypotheses that stroke patients with a younger-appearing brain relative to their chronological age perform better on cognitive tests and benefit more from cognitive training compared to patients with an older-appearing brain. In this randomized double-blind study, 54 patients who suffered mild stroke (>6 months since hospital admission, NIHSS<7 at hospital discharge) underwent 3-weeks CCT and MRI before and after the intervention. In addition, patients were randomized to one of two groups receiving either active or sham transcranial direct current stimulation (tDCS). We tested for main effects of brain age gap (estimated age – chronological age) on cognitive performance, and associations between brain age gap and task improvement. Finally, we tested if longitudinal changes in brain age gap during the intervention were sensitive to treatment response. Briefly, our results suggest that longitudinal brain age prediction based on automated brain morphometry is feasible and reliable in stroke patients. However, no significant association between brain age and both performance and response to cognitive training were found.

Download Full-text

Individual variation underlying brain age estimates in typical development

10.1101/2020.11.30.405290 ◽

2020 ◽

Author(s):

Gareth Ball ◽

Claire E Kelly ◽

Richard Beare ◽

Marc L Seal

Keyword(s):

Machine Learning ◽

Brain Development ◽

Machine Learning Algorithms ◽

Brain Maturation ◽

Childhood And Adolescence ◽

Typically Developing ◽

Feature Importance ◽

Brain Age ◽

Age Estimates ◽

Age Prediction

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

Download Full-text

The Evaluation of Brain Age Prediction by Different Functional Brain Network Construction Methods

Neural Information Processing - Lecture Notes in Computer Science ◽

10.1007/978-3-030-63836-8_11 ◽

2020 ◽

pp. 122-134

Author(s):

Hongfang Han ◽

Xingliang Xiong ◽

Jianfeng Yan ◽

Haixian Wang ◽

Mengting Wei

Keyword(s):

Brain Network ◽

Network Construction ◽

Functional Brain ◽

Construction Methods ◽

Functional Brain Network ◽

Brain Age ◽

Age Prediction

Download Full-text

Brain age prediction based on resting-state functional connectivity patterns using convolutional neural networks

2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018) ◽

10.1109/isbi.2018.8363532 ◽

2018 ◽

Cited By ~ 14

Author(s):

Hongming Li ◽

Theodore D. Satterthwaite ◽

Yong Fan

Keyword(s):

Neural Networks ◽

Functional Connectivity ◽

Convolutional Neural Networks ◽

Resting State ◽

Resting State Functional Connectivity ◽

Connectivity Patterns ◽

Brain Age ◽

Age Prediction

Download Full-text

Women with a history of previous childbirths show less evident white matter brain ageing

10.1101/2020.11.20.391698 ◽

2020 ◽

Author(s):

Irene Voldsbekk ◽

Claudia Barth ◽

Ivan I. Maximov ◽

Tobias Kaufmann ◽

Dani Beck ◽

...

Keyword(s):

White Matter ◽

Nulliparous Women ◽

Brain Ageing ◽

Maternal Brain ◽

History Of ◽

The Uk ◽

Age Range ◽

Brain Age ◽

Age Estimates ◽

Age Prediction

AbstractMaternal brain adaptations occur in response to pregnancy, but little is known about how parity impacts white matter (WM) microstructure and WM ageing trajectories later in life. Utilising global and regional brain-age prediction based on multi-shell diffusion MRI data, we investigated the association between previous childbirths and WM brain age in 8,895 women in the UK Biobank cohort (age range = 54 - 81 years). The results showed that a higher number of previous childbirths was associated with lower WM brain age, in line with previous studies showing less evident grey matter (GM) brain ageing in parous relative to nulliparous women. Both global WM and GM brain age estimates showed unique contributions to the association with previous childbirths, suggesting partly independent processes. Corpus callosum contributed uniquely to the global WM association with previous childbirths, and showed a stronger relationship relative to several other tracts. While our findings demonstrate a link between reproductive history and brain WM characteristics later in life, longitudinal studies are required to understand how parity influences women’s WM trajectories across the lifespan.

Download Full-text

Brain age prediction using fMRI network coupling in youths and associations with psychiatric symptoms

NeuroImage Clinical ◽

10.1016/j.nicl.2021.102921 ◽

2021 ◽

pp. 102921

Author(s):

Martina J. Lund ◽

Dag Alnæs ◽

Ann-Marie de Lange ◽

Ole A. Andreassen ◽

Lars T. Westlye ◽

...

Keyword(s):

Psychiatric Symptoms ◽

Brain Age ◽

Age Prediction

Download Full-text

Deep learning-based brain age prediction in normal aging and dementia

10.21203/rs.3.rs-804454/v1 ◽

2021 ◽

Author(s):

Jeyeon Lee ◽

Brian Burkett ◽

Hoon-Ki Min ◽

Matthew Senjem ◽

Emily Lundt ◽

...

Keyword(s):

Deep Learning ◽

Cognitive Impairment ◽

Brain Aging ◽

Lewy Body Dementia ◽

Normal Aging ◽

Specific Pattern ◽

Normal Brain ◽

Age Gap ◽

Brain Age ◽

Age Prediction

Abstract Normal brain aging is accompanied by patterns of functional and structural change. Alzheimer's disease (AD), a representative neurodegenerative disease, has been linked to accelerated brain aging at respective age ranges. Here, we developed a deep learning-based brain age prediction model using fluorodeoxyglucose (FDG) PET and structural MRI and tested how the brain age gap relates to degenerative cognitive syndromes including mild cognitive impairment, AD, frontotemporal dementia, and Lewy body dementia. Occlusion analysis, performed to facilitate interpretation of the model, revealed that the model learns an age- and modality-specific pattern of brain aging. The elevated brain age gap in dementia cohorts was highly correlated with the cognitive impairment and AD biomarker. However, regions generating brain age gaps were different for each diagnosis group of which the AD continuum showed similar patterns to normal aging in the CU.

Download Full-text

O2.3. ABNORMAL BRAIN AGING IN YOUTH WITH SUBCLINICAL PSYCHOSIS AND OBSESSIVE-COMPULSIVE SYMPTOMS

Schizophrenia Bulletin ◽

10.1093/schbul/sbaa028.008 ◽

2020 ◽

Vol 46 (Supplement_1) ◽

pp. S4-S4

Author(s):

Vanessa Cropley ◽

Ye Tian ◽

Kavisha Fernando ◽

Sina Mansour ◽

Christos Pantelis ◽

...

Keyword(s):

Brain Structure ◽

Grey Matter ◽

Psychiatric Symptoms ◽

Chronological Age ◽

Typically Developing ◽

Obsessive Compulsive ◽

General Psychopathology ◽

Age Gap ◽

Brain Age ◽

Age And Sex

Abstract Background Psychiatric symptoms in childhood and adolescence have been associated with both delayed and accelerated patterns of grey matter development. This suggests that deviation in brain structure from a normative range of variation for a given age might be important in the emergence of psychopathology. Distinct from chronological age, brain age refers to the age of an individual that is inferred from a normative model of brain structure for individuals of the same age and sex. We predicted brain age from a common set of grey matter features and examined whether the difference between an individual’s chronological and brain age was associated with the severity of psychopathology in children and adolescents. Methods Participants included 1313 youths (49.8% male) aged 8–21 who underwent structural imaging as part of the Philadelphia Neurodevelopmental Cohort. Independent Component Analysis was used to obtain 7 psychopathology dimensions representing Conduct, Anxiety, Obsessive-Compulsive, Attention, Depression, Bipolar, and Psychosis symptoms and an overall measure of severity (General Psychopathology). Using 10-fold cross-validation, support vector machine regression was trained in 402 typically developing youth to predict individual age based on a feature space comprising 111 grey matter regions. This yielded a brain age prediction for each individual. Brain age gap was calculated for each individual by subtracting chronological age from predicted brain age. The general linear model was used to test for an association between brain age gap and each of the 8 dimensions of psychopathology in a test sample of 911 youth. The regional specificity and spatial pattern of brain age gap was also investigated. Error control across the 8 models was achieved with a false discovery rate of 5%. Results Brain age gap was significantly associated with dimensions characterizing obsessive-compulsive (t=2.5, p=0.01), psychosis (t=3.16, p=0.0016) and general psychopathology (t=4.08, p<0.0001). For all three dimensions, brain age gap was positively associated with symptom severity, indicating that individuals with a brain that was predicted to be ‘older’ than expectations set by youth of the same chronological age and sex tended to have higher symptom scores. Findings were confirmed with a categorical approach, whereby higher brain age gap was observed in youth with a lifetime endorsement of psychosis (t=2.35, p=0.02) and obsessive-compulsive (t=2.35, p=0.021) symptoms, in comparison to typically developing individuals. Supplementary analyses revealed that frontal grey matter was the most important feature mediating the association between brain age gap and psychosis symptoms, whereas subcortical volumes were most important for the association between brain age gap and obsessive-compulsive and general symptoms. Discussion We found that the brain was ‘older’ in youth experiencing higher subclinical symptoms of psychosis, obsession-compulsion, and general psychopathology, compared to normally developing youth of the same chronological age. Our results suggest that deviations in normative brain age patterns in youth may contribute to the manifestation of specific psychiatric symptoms of subclinical severity that cut across psychopathology dimensions.

Download Full-text

Gray Matter Age Prediction as a Biomarker for Risk of Dementia

Proceedings of the National Academy of Sciences ◽

10.1073/pnas.1902376116 ◽

2019 ◽

Vol 116 (42) ◽

pp. 21213-21218 ◽

Cited By ~ 21

Author(s):

Johnny Wang ◽

Maria J. Knol ◽

Aleksei Tiulpin ◽

Florian Dubost ◽

Marleen de Bruijne ◽

...

Keyword(s):

Gray Matter ◽

Proportional Hazards ◽

Early Stage ◽

Hippocampal Volume ◽

Cox Proportional Hazards ◽

Intracranial Volume ◽

Age Gap ◽

Incident Dementia ◽

Brain Age ◽

Age Prediction

The gap between predicted brain age using magnetic resonance imaging (MRI) and chronological age may serve as a biomarker for early-stage neurodegeneration. However, owing to the lack of large longitudinal studies, it has been challenging to validate this link. We aimed to investigate the utility of such a gap as a risk biomarker for incident dementia using a deep learning approach for predicting brain age based on MRI-derived gray matter (GM). We built a convolutional neural network (CNN) model to predict brain age trained on 3,688 dementia-free participants of the Rotterdam Study (mean age 66 ± 11 y, 55% women). Logistic regressions and Cox proportional hazards were used to assess the association of the age gap with incident dementia, adjusted for age, sex, intracranial volume, GM volume, hippocampal volume, white matter hyperintensities, years of education, and APOE ε4 allele carriership. Additionally, we computed the attention maps, which shows which regions are important for age prediction. Logistic regression and Cox proportional hazard models showed that the age gap was significantly related to incident dementia (odds ratio [OR] = 1.11 and 95% confidence intervals [CI] = 1.05–1.16; hazard ratio [HR] = 1.11, and 95% CI = 1.06–1.15, respectively). Attention maps indicated that GM density around the amygdala and hippocampi primarily drove the age estimation. We showed that the gap between predicted and chronological brain age is a biomarker, complimentary to those that are known, associated with risk of dementia, and could possibly be used for early-stage dementia risk screening.

Download Full-text