Interpretable brain age prediction using linear latent variable models of functional connectivity

Age-related differences in structural and resting-state functional brain network organization across the adult lifespan: A cross-sectional study

We investigated age-related trends in the topology and hierarchical organization of brain structural and functional networks using diffusion-weighted imaging and resting-state fMRI data from a large cohort of healthy aging adults. At the cross-modal level, we explored age-related patterns in the RC involvement of different functional subsystems using a high-resolution functional parcellation. We further assessed age-related differences in the structure-function coupling as well as the network vulnerability to damage to rich club connectivity. Regardless of age, the structural and functional brain networks exhibited a rich club organization and small-world topology. In older individuals, we observed reduced integration and segregation within the frontal-occipital regions and the cerebellum along the brain's medial axis. Additionally, functional brain networks displayed decreased integration and increased segregation in the prefrontal, centrotemporal, and occipital regions, and the cerebellum. In older subjects, structural networks also exhibited decreased within-network and increased between-network RC connectivity. Furthermore, both within-network and between-network RC connectivity decreased in functional networks with age. An age-related decline in structure-function coupling was observed within sensory-motor, cognitive, and subcortical networks. The structural network exhibited greater vulnerability to damage to RC connectivity within the language-auditory, visual, and subcortical networks. Similarly, for functional networks, increased vulnerability was observed with damage to RC connectivity in the cerebellum, language-auditory, and sensory-motor networks. Overall, the network vulnerability decreased significantly in subjects older than 70 in both networks. Our findings underscore significant age-related differences in both brain functional and structural RC connectivity, with distinct patterns observed across the adult lifespan.

eXplainable Artificial Intelligence (XAI) in aging clock models

XAI is a rapidly progressing field of machine learning, aiming to unravel the predictions of complex models. XAI is especially required in sensitive applications, e.g. in health care, when diagnosis, recommendations and treatment choices might rely on the decisions made by artificial intelligence systems. AI approaches have become widely used in aging research as well, in particular, in developing biological clock models and identifying biomarkers of aging and age-related diseases. However, the potential of XAI here awaits to be fully appreciated. We discuss the application of XAI for developing the "aging clocks" and present a comprehensive analysis of the literature categorized by the focus on particular physiological systems.

Newborn DNA methylation age differentiates long-term weight trajectory: The Boston Birth Cohort

Background

Gestational age (GEAA) estimated by newborn DNA methylation (GAmAge) is associated with maternal prenatal exposures and immediate birth outcomes. However, the association of GAmAge with long-term overweight or obesity (OWO) trajectories is yet to be determined.

Methods

GAmAge was calculated for 831 children from a US predominantly urban, low-income, multi-ethnic birth cohort using Illumina EPIC array and cord-blood DNA samples. Repeated anthropometric measurements aligned with pediatric primary care schedule allowed us to calculate body-mass-index percentiles (BMIPCT) at specific age and to define long-term weight trajectories from birth to 18 years.

Results

Four BMIPCT trajectory groups described the long-term weight trajectories: stable (consistent OWO: "early OWO"; constant normal weight: "NW") or non-stable (OWO by year 1 of follow-up: "late OWO"; OWO by year 6 of follow-up: "NW to very late OWO") BMIPCT. were used GAmAge was a predictor of long-term obesity, differentiating between group with consistently high BMIPCT and group with normal BMIPCT patterns and groups with late OWO development. Such differentiation can be observed in the age periods of birth to 1year, 3years, 6years, 10years, and 14years (p<0.05 for all; multivariate models adjusted for GEAA, maternal smoking, delivery method, and child's sex). Birth weight was a mediator for the GAmAge effect on OWO status for specific groups at multiple age periods.

Conclusions

GAmAge is associated with BMI trajectories from birth to age 18 years, independent of GEAA and birth weight. If further confirmed, GAmAge may serve as an early biomarker for future OWO risk.

A Siamese Network With Node Convolution for Individualized Predictions Based on Connectivity Maps Extracted From Resting-State fMRI Data

Deep learning has demonstrated great potential for objective diagnosis of neuropsychiatric disorders based on neuroimaging data, which includes the promising resting-state functional magnetic resonance imaging (RS-fMRI). However, the insufficient sample size has long been a bottleneck for deep model training for the purpose. In this study, we proposed a Siamese network with node convolution (SNNC) for individualized predictions based on RS-fMRI data. With the involvement of Siamese network, which uses sample pair (rather than a single sample) as input, the problem of insufficient sample size can largely be alleviated. To adapt to connectivity maps extracted from RS-fMRI data, we applied node convolution to each of the two branches of the Siamese network. For regression purposes, we replaced the contrastive loss in classic Siamese network with the mean square error loss and thus enabled Siamese network to quantitatively predict label differences. The label of a test sample can be predicted based on any of the training samples, by adding the label of the training sample to the predicted label difference between them. The final prediction for a test sample in this study was made by averaging the predictions based on each of the training samples. The performance of the proposed SNNC was evaluated with age and IQ predictions based on a public dataset (Cam-CAN). The results indicated that SNNC can make effective predictions even with a sample size of as small as 40, and SNNC achieved state-of-the-art accuracy among a variety of deep models and standard machine learning approaches.

The older adult brain is less modular, more integrated, and less efficient at rest: A systematic review of large-scale resting-state functional brain networks in aging

The literature on large-scale resting-state functional brain networks across the adult lifespan was systematically reviewed. Studies published between 1986 and July 2021 were retrieved from PubMed. After reviewing 2938 records, 144 studies were included. Results on 11 network measures were summarized and assessed for certainty of the evidence using a modified GRADE method. The evidence provides high certainty that older adults display reduced within-network and increased between-network functional connectivity. Older adults also show lower segregation, modularity, efficiency and hub function, and decreased lateralization and a posterior to anterior shift at rest. Higher-order functional networks reliably showed age differences, whereas primary sensory and motor networks showed more variable results. The inflection point for network changes is often the third or fourth decade of life. Age effects were found with moderate certainty for within- and between-network altered patterns and speed of dynamic connectivity. Research on within-subject bold variability and connectivity using glucose uptake provides low certainty of age differences but warrants further study. Taken together, these age-related changes may contribute to the cognitive decline often seen in older adults.

Brain Connectivity Based Graph Convolutional Networks and Its Application to Infant Age Prediction

Infancy is a critical period for the human brain development, and brain age is one of the indices for the brain development status associated with neuroimaging data. The difference between the predicted age based on neuroimaging and the chronological age can provide an important early indicator of deviation from the normal developmental trajectory. In this study, we utilize the Graph Convolutional Network (GCN) to predict the infant brain age based on resting-state fMRI data. The brain connectivity obtained from rs-fMRI can be represented as a graph with brain regions as nodes and functional connections as edges. However, since the brain connectivity is a fully connected graph with features on edges, current GCN cannot be directly used for it is a node-based method for sparse graphs. Hence, we propose an edge-based Graph Path Convolution (GPC) method, which aggregates the information from different paths and can be naturally applied on dense graphs. We refer the whole model as Brain Connectivity Graph Convolutional Networks (BC-GCN). Further, two upgraded network structures are proposed by including the residual and attention modules, referred as BC-GCN-Res and BC-GCN-SE to emphasize the information of the original data and enhance influential channels. Moreover, we design a two-stage coarse-to-fine framework, which determines the age group first and then predicts the age using group-specific BC-GCN-SE models. To avoid accumulated errors from the first stage, a cross-group training strategy is adopted for the second stage regression models. We conduct experiments on infant fMRI scans from 6 to 811 days of age. The coarse-to-fine framework shows significant improvements when being applied to several models (reducing error over 10 days). Comparing with state-of-the-art methods, our proposed model BC-GCN-SE with coarse-to-fine framework reduces the mean absolute error of the prediction from >70 days to 49.9 days. The code is now available at https://github.com/SCUT-Xinlab/BC-GCN.

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.

Explanations of Machine Learning Models in Repeated Nested Cross-Validation: An Application in Age Prediction Using Brain Complexity Features

SHAP (Shapley additive explanations) is a framework for explainable AI that makes explanations locally and globally. In this work, we propose a general method to obtain representative SHAP values within a repeated nested cross-validation procedure and separately for the training and test sets of the different cross-validation rounds to assess the real generalization abilities of the explanations. We applied this method to predict individual age using brain complexity features extracted from MRI scans of 159 healthy subjects. In particular, we used four implementations of the fractal dimension (FD) of the cerebral cortex—a measurement of brain complexity. Representative SHAP values highlighted that the most recent implementation of the FD had the highest impact over the others and was among the top-ranking features for predicting age. SHAP rankings were not the same in the training and test sets, but the top-ranking features were consistent. In conclusion, we propose a method—and share all the source code—that allows a rigorous assessment of the SHAP explanations of a trained model in a repeated nested cross-validation setting.

A guided multiverse study of neuroimaging analyses

For most neuroimaging questions the range of possible analytic choices makes it unclear how to evaluate conclusions from any single analytic method. One possible way to address this issue is to evaluate all possible analyses using a multiverse approach, however, this can be computationally challenging and sequential analyses on the same data can compromise predictive power. Here, we establish how active learning on a low-dimensional space capturing the inter-relationships between pipelines can efficiently approximate the full spectrum of analyses. This approach balances the benefits of a multiverse analysis without incurring the cost on computational and predictive power. We illustrate this approach with two functional MRI datasets (predicting brain age and autism diagnosis) demonstrating how a multiverse of analyses can be efficiently navigated and mapped out using active learning. Furthermore, our presented approach not only identifies the subset of analysis techniques that are best able to predict age or classify individuals with autism spectrum disorder and healthy controls, but it also allows the relationships between analyses to be quantified.

Correlation Constraints for Regression Models: Controlling Bias in Brain Age Prediction

In neuroimaging, the difference between chronological age and predicted brain age, also known as brain age delta, has been proposed as a pathology marker linked to a range of phenotypes. Brain age delta is estimated using regression, which involves a frequently observed bias due to a negative correlation between chronological age and brain age delta. In brain age prediction models, this correlation can manifest as an overprediction of the age of young brains and an underprediction for elderly ones. We show that this bias can be controlled for by adding correlation constraints to the model training procedure. We develop an analytical solution to this constrained optimization problem for Linear, Ridge, and Kernel Ridge regression. The solution is optimal in the least-squares sense i.e., there is no other model that satisfies the correlation constraints and has a better fit. Analyses on the PAC2019 competition data demonstrate that this approach produces optimal unbiased predictive models with a number of advantages over existing approaches. Finally, we introduce regression toolboxes for Python and MATLAB that implement our algorithm.