Assessing distinct patterns of cognitive aging using tissue-specific brain age prediction based on diffusion tensor imaging and brain morphometry

Abstract

1Multimodal imaging enables sensitive measures of the architecture and integrity of the human 2 brain, but the high-dimensional nature of advanced brain imaging features poses inherent 3 challenges for the analyses and interpretations. Multivariate age prediction reduces the 4 dimensionality to one biologically informative summary measure with potential for assessing 5 deviations from normal lifespan trajectories. A number of studies documented remarkably 6 accurate age prediction, but the differential age trajectories and the cognitive sensitivity of 7 distinct brain tissue classes have to a lesser extent been characterized. 8Exploring differential brain age models driven by tissue-specific classifiers provides a 9 hitherto unexplored opportunity to disentangle independent sources of heterogeneity in brain 10 biology. We trained machine-learning models to estimate brain age using various 11 combinations of FreeSurfer based morphometry and diffusion tensor imaging based indices of 12 white matter microstructure in 612 healthy controls aged 18-87 years. To compare the tissue-13 specific brain ages and their cognitive sensitivity we applied each of the 11 models in an 14 independent and cognitively well-characterized sample (n=265, 20-88 years). Correlations 15 between true and estimated age in our test sample were highest for the most comprehensive 16 brain morphometry (r=0.83, CI:0.78-0.86) and white matter microstructure (r=0.79, CI:0.74-17 0.83) models, confirming sensitivity and generalizability. The deviance from the 18 chronological age were sensitive to performance on several cognitive tests for various models, 19including spatial Stroop and symbol coding, indicating poorer performance in individuals 20 with an over-estimated age. Tissue-specific brain age models provide sensitive measures of 21 brain integrity, with implications for the study of a range of brain disorders. 22 23 24 25 26 27 28 29 30 31 32 33 TISSUE-SPECIFIC BRAIN AGE PREDICTION 3 multiple sclerosis (Kaufmann et al. 2018) and cardiovascular risk factors (Franke et al. 2013; 58 Habes et al. 2016). Indeed, while individuals with brains estimated as younger than their 59 chronological age have been shown to be more physically active (Steffener et al. 2016), 60 augmented brain age has been associated with poor health (Ronan et al. 2016), poor cognitive 61 performance (Liem et al. 2017), early neurodegenerative diseases (Gaser et al. 2013), and 62 increased mortality (Cole et al. 2017a).Less is known about the regional heterogeneity, i.e. to 63 which degree different brain regions, systems or compartments show differential aging 64 patterns and sensitivity to cognitive performance. Brain gray and white matter compartments, 65 which can be assessed and quantified using T1-weighted imaging and diffusion tensor 66 TISSUE-SPECIFIC BRAIN AGE PREDICTION 4 imaging (DTI), respectively, comprise distinct tissue classes with largely differential 67 biological and environmental modifiers and age trajectories (Bennett et al. 2010; Cao et al. 68 2017; Fje...

Brain aging comprises many modes of structural and functional change with distinct genetic and biophysical associations

“…Similarly, [Vinke et al, 2018] included data from several modalities, and studied aging trajectories in di erent measures from di erent modalities, but did not go as far as brain age (or brain-age delta) modelling, or attempt to identify latent modes of aging. Several modalities were also used in [Richard et al, 2018], with 11 groups of distinct measures used to form 11 estimates of brain age, each of which was then separately investigated for cognitive associations; one central methodological distinction to the work presented here is that the 11 models were hand curated according to di erent types of features from di erent modalities, as opposed to (in our case) pooling all modalities' features together before using data-driven decomposition (ICA) to identify distinct aging modes that could naturally span across feature types and modalities. In contrast, [Kessler et al, 2016] used single-modality features (resting fMRI edge strengths) fed into ICA to identify multiple modes of early-life maturation.…”

“…The imaging feature set can be derived from more than one imaging modality, in which case it can contain information not just about the structural geometric layout of the brain, but also, for example, structural connectivity, white matter microstructure, functional connectivity, iron deposition, and cognitive task activation [Groves et al, 2012, Brown et al, 2012, Liem et al, 2017, Vinke et al, 2018, Richard et al, 2018. Such "multimodal" data allows for brain age modelling to take advantage of a richer range of structural and functional measures of change in the brain, but it is still the case that most brain-age modelling only estimates a single overall brain age per individual.…”

“…These di erent factors will likely a ect di erent aspects of the brain's structure and function, as viewed through multiple imaging modalities. Further, di erent factors a ecting brain aging could well have di erent age dependence -population-averaged aging curves for the di erent factors could be quite distinct (e.g., with respect to strength and linearity of the age dependence) [Groves et al, 2012, Brown et al, 2012, Douaud et al, 2014, Kessler et al, 2016, Vinke et al, 2018, Richard et al, 2018. Di erent biological factors of brain aging might well also be expected to show distinct genetic influence.…”

Towards an optimised processing pipeline for diffusion magnetic resonance imaging data: Effects of artefact corrections on diffusion metrics and their age associations in UK Biobank

“…On the contrary, the UKB pipeline demonstrated a higher number of significant voxels for DKI metrics. Although subtle, pipeline related global and spatially varying differences in diffusion metrics will have consequences for subsequent analyses, for example, for machine‐learning‐based age prediction or diagnostic classification or prediction of clinical traits (Alnaes et al, ; Doan et al, ; Kuhn et al, ; Richard et al, ).…”

Towards an optimised processing pipeline for diffusion MRI data: Effects of artefact corrections on diffusion metrics and their age associations in UK Biobank

“…Although subtle, pipeline related global and spatially varying differences in diffusion metrics will have consequences for subsequent analyses, for example, for machine-learning based age prediction or diagnostic classification or prediction of clinical traits (Alnaes et al, 2018;Doan et al, 2017;Kuhn at al., 2018;Richards et al, 2018).…”