Neuroimaging in aging: brain maintenance

Transformer-based approaches for neuroimaging: an in-depth review of their role in classification and regression tasks

In the ever-evolving landscape of deep learning (DL), the transformer model emerges as a formidable neural network architecture, gaining significant traction in neuroimaging-based classification and regression tasks. This paper presents an extensive examination of transformer's application in neuroimaging, surveying recent literature to elucidate its current status and research advancement. Commencing with an exposition on the fundamental principles and structures of the transformer model and its variants, this review navigates through the methodologies and experimental findings pertaining to their utilization in neuroimage classification and regression tasks. We highlight the transformer model's prowess in neuroimaging, showcasing its exceptional performance in classification endeavors while also showcasing its burgeoning potential in regression tasks. Concluding with an assessment of prevailing challenges and future trajectories, this paper proffers insights into prospective research directions. By elucidating the current landscape and envisaging future trends, this review enhances comprehension of transformer's role in neuroimaging tasks, furnishing valuable guidance for further inquiry.

Dissecting unique and common variance across body and brain health indicators using age prediction

Ageing is a heterogeneous multisystem process involving different rates of decline in physiological integrity across biological systems. The current study dissects the unique and common variance across body and brain health indicators and parses inter-individual heterogeneity in the multisystem ageing process. Using machine-learning regression models on the UK Biobank data set (N = 32,593, age range 44.6-82.3, mean age 64.1 years), we first estimated tissue-specific brain age for white and gray matter based on diffusion and T1-weighted magnetic resonance imaging (MRI) data, respectively. Next, bodily health traits, including cardiometabolic, anthropometric, and body composition measures of adipose and muscle tissue from bioimpedance and body MRI, were combined to predict 'body age'. The results showed that the body age model demonstrated comparable age prediction accuracy to models trained solely on brain MRI data. The correlation between body age and brain age predictions was 0.62 for the T1 and 0.64 for the diffusion-based model, indicating a degree of unique variance in brain and bodily ageing processes. Bayesian multilevel modelling carried out to quantify the associations between health traits and predicted age discrepancies showed that higher systolic blood pressure and higher muscle-fat infiltration were related to older-appearing body age compared to brain age. Conversely, higher hand-grip strength and muscle volume were related to a younger-appearing body age. Our findings corroborate the common notion of a close connection between somatic and brain health. However, they also suggest that health traits may differentially influence age predictions beyond what is captured by the brain imaging data, potentially contributing to heterogeneous ageing rates across biological systems and individuals.

When Age Tips the Balance: a Dual Mechanism Affecting Hemispheric Specialization for Language

Aging engenders neuroadaptations, generally reducing specificity and selectivity in functional brain responses. Our investigation delves into the functional specialization of brain hemispheres within language-related networks across adulthood. In a cohort of 728 healthy adults spanning ages 18 to 88, we modeled the trajectories of inter-hemispheric asymmetry concerning the principal functional gradient across 37 homotopic regions of interest (hROIs) of an extensive language network, known as the Language-and-Memory Network. Our findings reveal that over two-thirds of Language-and-Memory Network hROIs undergo asymmetry changes with age, falling into two main clusters. The first cluster evolves from left-sided specialization to right-sided tendencies, while the second cluster transitions from right-sided asymmetry to left-hemisphere dominance. These reversed asymmetry shifts manifest around midlife, occurring after age 50, and are associated with poorer language production performance. Our results provide valuable insights into the influence of functional brain asymmetries on language proficiency and present a dynamic perspective on brain plasticity during the typical aging process.

Hippocampal volume, and the anterior-posterior sub regions relates to recall and recognition over five years: Bidirectional brain-behaviour associations

Longitudinal studies of brain-behavior links between episodic memory (EM) and the hippocampus (HC), including anterior-posterior subregions, are few. This study assessed brain-cognition relationships between HC volumes, including the anterior-posterior subregions, item recall, and recognition, in 358 adults (52%♀; 20-80 yrs. at baseline, 221 returned at follow-up). Bivariate latent change score models assessed mean change, variance, and bidirectional associations between the hippocampal regions and the EM tasks. The influence of chronological age, sex, and education were included as covariates. The results showed that: larger baseline HC volume slowed subsequent decline in EM scores; higher associative memory scores at offset mitigated five-year HC volume loss; larger anterior HC volumes slowed decline in recognition memory, while larger posterior volumes mitigated decline in recall scores; the volume of the anterior HC was not associated with change in recall scores; and posterior HC volume did not predict change in recognition memory scores. The covariates examined - age, sex, and education- had some cross-sectional influence, but only limited longitudinal effects. The results explain the bidirectional associations in brain-cognition links, and how the distinct sub-regional HC correlates for recall and recognition, respectively. These results also shed light on potential links between maintained brain volumes and restored cognitive functions during the aging process.

Hydrogen sulfide-induced post-translational modification as a potential drug target

Hydrogen sulfide (H₂S) is one of the three known gas signal transducers, and since its potential physiological role was reported, the literature on H₂S has been increasing. H₂S is involved in processes such as vasodilation, neurotransmission, angiogenesis, inflammation, and the prevention of ischemia-reperfusion injury, and its mechanism remains to be further studied. At present, the role of post-translational processing of proteins has been considered as a possible mechanism for the involvement of H₂S in a variety of physiological processes. Current studies have shown that H₂S is involved in S-sulfhydration, phosphorylation, and S-nitrosylation of proteins, etc. This paper focuses on the effects of protein modification involving H₂S on physiological and pathological processes, looking forward to providing guidance for subsequent research.

Cognitive and MRI trajectories for prediction of Alzheimer's disease

The concept of Mild Cognitive Impairment (MCI) is used to describe the early stages of Alzheimer's disease (AD), and identification and treatment before further decline is an important clinical task. We selected longitudinal data from the ADNI database to investigate how well normal function (HC, n= 134) vs. conversion to MCI (cMCI, n= 134) and stable MCI (sMCI, n=333) vs. conversion to AD (cAD, n= 333) could be predicted from cognitive tests, and whether the predictions improve by adding information from magnetic resonance imaging (MRI) examinations. Features representing trajectories of change in the selected cognitive and MRI measures were derived from mixed effects models and used to train ensemble machine learning models to classify the pairs of subgroups based on a subset of the data set. Evaluation in an independent test set showed that the predictions for HC vs. cMCI improved substantially when MRI features were added, with an increase in [Formula: see text]-score from 60 to 77%. The [Formula: see text]-scores for sMCI vs. cAD were 77% without and 78% with inclusion of MRI features. The results are in-line with findings showing that cognitive changes tend to manifest themselves several years after the Alzheimer's disease is well-established in the brain.

Occupational Physical Stress Is Negatively Associated With Hippocampal Volume and Memory in Older Adults

Our jobs can provide intellectually and socially enriched environments but also be the source of major psychological and physical stressors. As the average full-time worker spends >8 h at work per weekday and remains in the workforce for about 40 years, occupational experiences must be important factors in cognitive and brain aging. Therefore, we studied whether occupational complexity and stress are associated with hippocampal volume and cognitive ability in 99 cognitively normal older adults. We estimated occupational complexity, physical stress, and psychological stress using the Work Design Questionnaire (Morgeson and Humphrey, 2006), Quantitative Workload Inventory and Interpersonal Conflict at Work Scale (Spector and Jex, 1998). We found that physical stress, comprising physical demands and work conditions, was associated with smaller hippocampal volume and poorer memory performance. These associations were independent of age, gender, brain size, socioeconomic factors (education, income, and job title), duration of the job, employment status, leisure physical activity and general stress. This suggests that physical demands at work and leisure physical activity may have largely independent and opposite effects on brain and cognitive health. Our findings highlight the importance of considering midlife occupational experiences, such as work physical stress, in understanding individual trajectories of cognitive and brain aging.

Lateral ventricle volume trajectories predict response inhibition in older age-A longitudinal brain imaging and machine learning approach

Objective

In a three-wave 6 yrs longitudinal study we investigated if the expansion of lateral ventricle (LV) volumes (regarded as a proxy for brain tissue loss) predicts third wave performance on a test of response inhibition (RI).

Participants and methods

Trajectories of left and right lateral ventricle volumes across the three waves were quantified using the longitudinal stream in Freesurfer. All participants (N = 74;48 females;mean age 66.0 yrs at the third wave) performed the Color-Word Interference Test (CWIT). Response time on the third condition of CWIT, divided into fast, medium and slow, was used as outcome measure in a machine learning framework. Initially, we performed a linear mixed-effect (LME) analysis to describe subject-specific trajectories of the left and right LV volumes (LVV). These features were input to a multinomial logistic regression classification procedure, predicting individual belongings to one of the three RI classes. To obtain results that might generalize, we evaluated the significance of a k-fold cross-validated f1-score with a permutation test, providing a p-value that approximates the probability that the score would be obtained by chance. We also calculated a corresponding confusion matrix.

Results

The LME-model showed an annual ∼ 3.0% LVV increase. Evaluation of a cross-validated score using 500 permutations gave an f1-score of 0.462 that was above chance level (p = 0.014). 56% of the fast performers were successfully classified. All these were females, and typically older than 65 yrs at inclusion. For the true slow performers, those being correctly classified had higher LVVs than those being misclassified, and their ages at inclusion were also higher.

Conclusion

Major contributions were: (i) a longitudinal design, (ii) advanced brain imaging and segmentation procedures with longitudinal data analysis, and (iii) a data driven machine learning approach including cross-validation and permutation testing to predict behaviour, solely from the individual’s brain “signatures” (LVV trajectories).

Development and Decline of the Hippocampal Long-Axis Specialization and Differentiation During Encoding and Retrieval of Episodic Memories

Change in hippocampal function is a major factor in life span development and decline of episodic memory. Evidence indicates a long-axis specialization where anterior hippocampus is more engaged during encoding than during retrieval, and posterior more engaged during retrieval than during encoding. We tested the life span trajectory of hippocampal long-axis episodic memory-related activity and functional connectivity (FC) in 496 participants (6.8–80.8 years) encoding and retrieving associative memories. We found evidence for a long-axis encoding–retrieval specialization that declined linearly during development and aging, eventually vanishing in the older adults. This was mainly driven by age effects on retrieval, which was associated with gradually lower activity from childhood to adulthood, followed by positive age relationships until 70 years. This pattern of age effects characterized task engagement regardless of memory success or failure. Especially for retrieval, children engaged posterior hippocampus more than anterior, while anterior was relatively more activated already in teenagers. Significant intrahippocampal connectivity was found during task, which declined with age. The results suggest that hippocampal long-axis differentiation and communication during episodic memory tasks develop rapidly during childhood, are different in older compared with younger adults, and that the age effects are related to task engagement, not the successful retrieval of episodic memories specifically.