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

Author(s):  
Jeyeon Lee ◽  
Brian Burkett ◽  
Hoon-Ki Min ◽  
Matthew Senjem ◽  
Emily Lundt ◽  
...  

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.

2020 ◽  
Author(s):  
Jaroslav Rokicki ◽  
Thomas Wolfers ◽  
Wibeke Nordhøy ◽  
Natalia Tesli ◽  
Daniel S. Quintana ◽  
...  

BackgroundThe deviation between chronological age and age predicted using brain MRI is a putative marker of brain health and disease-related deterioration. Age prediction based on structural MRI data shows high accuracy and sensitivity to common brain disorders. However, brain aging is complex and heterogenous, both in terms of individual differences and the biological processes involved. Here, we implemented a multimodal age prediction approach and tested the predictive value across patients with a range of disorders with distinct etiologies and clinical features.MethodsWe implemented a multimodal model to estimate brain age using different combinations of cortical area, thickness and sub-cortical volumes, cortical and subcortical T1/T2-weighted ratios, and cerebral blood flow (CBF) calculated from functional arterial spin labeling (ASL) data. For each of the 11 models we assessed the age prediction accuracy in HC n=761 and compared the resulting brain age gaps (BAGs) between each clinical group and age-matched subsets of HC in patients with Alzheimer’s disease (AD, n=54), mild cognitive impairment (MCI, n=88), subjective cognitive impairment (SCI, n=55), schizophrenia (SZ, n=156), bipolar disorder (BD, n=136), autism spectrum disorder (ASD, n=28).ResultsAmong the 11 models, we found highest age prediction accuracy in HC when integrating all modalities (mean absolute error=6.5 years). Beyond this global BAG, the area under the curve for the receiver-operating characteristics based on two-group case-control classifications showed strongest effects for AD and ASD in global T1-weighted BAG (T1w-BAG), while MCI, SCI, BD and SZ showed strongest effects in CBF-based BAGs.ConclusionsCombining multiple MRI modalities improves brain age prediction and reveals distinct deviations in patients with psychiatric and neurological disorders. The multimodal BAG was most accurate in predicting age in HC, while group differences between patients and controls were often larger for BAGs based on single modalities. These findings demonstrate that multidimensional phenotyping provides a mapping of overlapping and distinct pathophysiology in common disorders of the brain, and specifically suggest metabolic and neurovascular aberrations in SZ and at-risk and early stage dementia.


2019 ◽  
Author(s):  
Gidon Levakov ◽  
Gideon Rosenthal ◽  
Ilan Shelef ◽  
Tammy Riklin Raviv ◽  
Galia Avidan

AbstractWe present a Deep Learning framework for the prediction of chronological age from structural MRI scans. Previous findings associate an overestimation of brain age with neurodegenerative diseases and higher mortality rates. However, the importance of brain age prediction goes beyond serving as biomarkers for neurological disorders. Specifically, utilizing convolutional neural network (CNN) analysis to identify brain regions contributing to the prediction can shed light on the complex multivariate process of brain aging. Previous work examined methods to attribute pixel/voxel-wise contributions to the prediction in a single image, resulting in ‘explanation maps’ that were found noisy and unreliable. To address this problem, we developed an inference framework for combining these maps across subjects, thus creating a population-based rather than a subject-specific map. We applied this method to a CNN ensemble trained on predicting subjects’ age from raw T1 brain images of 10,176 subjects. Evaluating the model on an untouched test set resulted in mean absolute error of 3.07 years and a correlation between chronological and predicted age of r=0.98. Using the inference method, we revealed that cavities containing CSF, previously found as general atrophy markers, had the highest contribution for age prediction. Comparing maps derived from different models within the ensemble allowed to assess differences and similarities in brain regions utilized by the model. We showed that this method substantially increased the replicability of explanation maps, converged with results from voxel-based morphometry age studies and highlighted brain regions whose volumetric variability contributed the most to the prediction.HighlightsCNNs ensemble is shown to estimate “brain age” from sMRI with an MAE of ∼3.1 yearsA novel framework enables to highlight brain regions contributing to the predictionThis framework results in explanation maps showing consistency with the literatureAs sample size increases, these maps show higher inter-sample replicabilityCSF cavities reflecting general atrophy were found as a prominent aging biomarker


Microbiome ◽  
2021 ◽  
Vol 9 (1) ◽  
Author(s):  
Hongli Shi ◽  
Xing Ge ◽  
Xi Ma ◽  
Mingxuan Zheng ◽  
Xiaoying Cui ◽  
...  

Abstract Background Cognitive impairment, an increasing mental health issue, is a core feature of the aging brain and neurodegenerative diseases. Industrialized nations especially, have experienced a marked decrease in dietary fiber intake, but the potential mechanism linking low fiber intake and cognitive impairment is poorly understood. Emerging research reported that the diversity of gut microbiota in Western populations is significantly reduced. However, it is unknown whether a fiber-deficient diet (which alters gut microbiota) could impair cognition and brain functional elements through the gut-brain axis. Results In this study, a mouse model of long-term (15 weeks) dietary fiber deficiency (FD) was used to mimic a sustained low fiber intake in humans. We found that FD mice showed impaired cognition, including deficits in object location memory, temporal order memory, and the ability to perform daily living activities. The hippocampal synaptic ultrastructure was damaged in FD mice, characterized by widened synaptic clefts and thinned postsynaptic densities. A hippocampal proteomic analysis further identified a deficit of CaMKIId and its associated synaptic proteins (including GAP43 and SV2C) in the FD mice, along with neuroinflammation and microglial engulfment of synapses. The FD mice also exhibited gut microbiota dysbiosis (decreased Bacteroidetes and increased Proteobacteria), which was significantly associated with the cognitive deficits. Of note, a rapid differentiating microbiota change was observed in the mice with a short-term FD diet (7 days) before cognitive impairment, highlighting a possible causal impact of the gut microbiota profile on cognitive outcomes. Moreover, the FD diet compromised the intestinal barrier and reduced short-chain fatty acid (SCFA) production. We exploit these findings for SCFA receptor knockout mice and oral SCFA supplementation that verified SCFA playing a critical role linking the altered gut microbiota and cognitive impairment. Conclusions This study, for the first time, reports that a fiber-deprived diet leads to cognitive impairment through altering the gut microbiota-hippocampal axis, which is pathologically distinct from normal brain aging. These findings alert the adverse impact of dietary fiber deficiency on brain function, and highlight an increase in fiber intake as a nutritional strategy to reduce the risk of developing diet-associated cognitive decline and neurodegenerative diseases.


2021 ◽  
Vol 13 ◽  
Author(s):  
Dennis M. Hedderich ◽  
Aurore Menegaux ◽  
Benita Schmitz-Koep ◽  
Rachel Nuttall ◽  
Juliana Zimmermann ◽  
...  

Recent evidence suggests increased metabolic and physiologic aging rates in premature-born adults. While the lasting consequences of premature birth on human brain development are known, its impact on brain aging remains unclear. We addressed the question of whether premature birth impacts brain age gap estimates (BrainAGE) using an accurate and robust machine-learning framework based on structural MRI in a large cohort of young premature-born adults (n = 101) and full-term (FT) controls (n = 111). Study participants are part of a geographically defined population study of premature-born individuals, which have been followed longitudinally from birth until young adulthood. We investigated the association between BrainAGE scores and perinatal variables as well as with outcomes of physical (total intracranial volume, TIV) and cognitive development (full-scale IQ, FS-IQ). We found increased BrainAGE in premature-born adults [median (interquartile range) = 1.4 (−1.3–4.7 years)] compared to full-term controls (p = 0.002, Cohen’s d = 0.443), which was associated with low Gestational age (GA), low birth weight (BW), and increased neonatal treatment intensity but not with TIV or FS-IQ. In conclusion, results demonstrate elevated BrainAGE in premature-born adults, suggesting an increased risk for accelerated brain aging in human prematurity.


2019 ◽  
Author(s):  
Geneviève Richard ◽  
Knut Kolskår ◽  
Kristine M. Ulrichsen ◽  
Tobias Kaufmann ◽  
Dag Alnæs ◽  
...  

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.


Neuroreport ◽  
2001 ◽  
Vol 12 (11) ◽  
pp. 2315-2317 ◽  
Author(s):  
Marco Catani ◽  
Antonio Cherubini ◽  
Robert Howard ◽  
Roberto Tarducci ◽  
GianPiero Pelliccioli ◽  
...  

Author(s):  
Ann-Marie G. de Lange ◽  
Claudia Barth ◽  
Tobias Kaufmann ◽  
Melis Anatürk ◽  
Sana Suri ◽  
...  

AbstractPregnancy involves maternal brain adaptations, but little is known about how parity influences women’s brain aging trajectories later in life. In this study, we replicated previous findings showing less apparent brain aging in women with a history of childbirths, and identified regional brain aging patterns linked to parity in 19,787 middle and older-aged women. Using novel applications of brain-age prediction methods, we found that a higher number of previous childbirths was linked to less apparent brain aging in striatal and limbic regions. The strongest effect was found in the accumbens – a key region in the mesolimbic reward system, which plays an important role in maternal behavior. While only prospective longitudinal studies would be conclusive, our findings indicate that subcortical brain modulations during pregnancy and postpartum may be traceable decades after childbirth.


2021 ◽  
Vol 13 ◽  
Author(s):  
Shouneng Peng ◽  
Lu Zeng ◽  
Jean-Vianney Haure-Mirande ◽  
Minghui Wang ◽  
Derek M. Huffman ◽  
...  

Aging is a major risk factor for late-onset Alzheimer’s disease (LOAD). How aging contributes to the development of LOAD remains elusive. In this study, we examined multiple large-scale transcriptomic datasets from both normal aging and LOAD brains to understand the molecular interconnection between aging and LOAD. We found that shared gene expression changes between aging and LOAD are mostly seen in the hippocampal and several cortical regions. In the hippocampus, the expression of phosphoprotein, alternative splicing and cytoskeleton genes are commonly changed in both aging and AD, while synapse, ion transport, and synaptic vesicle genes are commonly down-regulated. Aging-specific changes are associated with acetylation and methylation, while LOAD-specific changes are more related to glycoprotein (both up- and down-regulations), inflammatory response (up-regulation), myelin sheath and lipoprotein (down-regulation). We also found that normal aging brain transcriptomes from relatively young donors (45–70 years old) clustered into several subgroups and some subgroups showed gene expression changes highly similar to those seen in LOAD brains. Using brain transcriptomic datasets from another cohort of older individuals (&gt;70 years), we found that samples from cognitively normal older individuals clustered with the “healthy aging” subgroup while AD samples mainly clustered with the “AD similar” subgroups. This may imply that individuals in the healthy aging subgroup will likely remain cognitively normal when they become older and vice versa. In summary, our results suggest that on the transcriptome level, aging and LOAD have strong interconnections in some brain regions in a subpopulation of cognitively normal aging individuals. This supports the theory that the initiation of LOAD occurs decades earlier than the manifestation of clinical phenotype and it may be essential to closely study the “normal brain aging” to identify the very early molecular events that may lead to LOAD development.


2016 ◽  
Author(s):  
Franziskus Liem ◽  
Gaël Varoquaux ◽  
Jana Kynast ◽  
Frauke Beyer ◽  
Shahrzad Kharabian Masouleh ◽  
...  

The disparity between the chronological age of an individual and their brain-age measured based on biological information has the potential to offer clinically-relevant biomarkers of neurological syndromes that emerge late in the lifespan. While prior brain-age prediction studies have relied exclusively on either structural or functional brain data, here we investigate how multimodal brain-imaging data improves age prediction. Using cortical anatomy and whole-brain functional connectivity on a large adult lifespan sample (N = 2354, age 19-82), we found that multimodal data improves brain-based age prediction, resulting in a mean absolute prediction error of 4.29 years. Furthermore, we found that the discrepancy between predicted age and chronological age captures cognitive impairment. Importantly, the brain-age measure was robust to confounding effects: head motion did not drive brain-based age prediction and our models generalized reasonably to an independent dataset acquired at a different site (N = 475). Generalization performance was increased by training models on a larger and more heterogeneous dataset. The robustness of multimodal brain-age prediction to confounds, generalizability across sites, and sensitivity to clinically-relevant impairments, suggests promising future application to the early prediction of neurocognitive disorders.


2020 ◽  
Vol 16 (S5) ◽  
Author(s):  
Pradeep Lam ◽  
Alyssa Zhu ◽  
Lauren Salminen ◽  
Sophia I Thomopoulos ◽  
Joanna Bright ◽  
...  

Sign in / Sign up

Export Citation Format

Share Document