Geometric deep learning reveals a structuro-temporal understanding of healthy and pathologic brain aging

Abstract

Background: Brain age has historically been investigated primarily at the whole brain level. The ability to deconstruct the brain into its composite parts and explore brain age at the sub-structure level offers unique advantages. These include the exploration of dynamic and interconnected relationships between different brain structures in healthy and pathologic aging. To achieve this, individual brain structures can be rendered as surface representations on which morphologic analysis is carried out. Combining the advantages of deep learning with the strengths of surface analysis, we investigate the aging process at the individual structure level with the hypothesis being that pathologic aging does not uniformly affect the aging process of individual structures.

Methods: MRI data, age at scan time and diagnosis of dementia were collected from seven publicly available data repositories. The data from 17,440 unique subjects were collected, representing a total of 26,276 T1-weighted MRI accounting for longitudinal acquisitions. Surfaces were extracted for the cortex and seven subcortical structures. Deep learning networks were trained to estimate a subject's age either using several structures together or a single structure. We conducted a cross-sectional analysis to assess the difference between the predicted and actual ages for all structures between healthy subjects, individuals with mild cognitive impairment (MCI) or Alzheimer's disease dementia (ADD). We then performed a longitudinal analysis to assess the difference in the aging pace for each structure between stable healthy controls and healthy controls converting to either MCI or ADD.

Findings: Using an independent cohort of healthy subjects, age was well estimated for all structures. Cross-sectional analysis identified significantly larger predicted age for all structures in patients with either MCI and ADD compared to healthy subjects. Longitudinal analysis revealed varying degrees of involvement of individual subcortical structures for both age difference across groups and aging pace across time. These findings were most notable in the whole brain, cortex, hippocampus and amygdala.

Conclusion: Although similar patterns of abnormal aging were found related to MCI and ADD, the involvement of individual subcortical structures varied greatly and was consistently more pronounced in ADD patients compared to MCI patients.

Keywords: Alzheimer’s disease; brain age; brain mapping; brain shape; dementia; geometric deep learning; human aging.

FIGURE 1

(A) Overall architecture of the network. (B) Detail of Residual Blocks. For each convolutional layer (red), the kernel size k is indicated.

FIGURE 2

Residuals of age predictions for all structures (cortex + subcortical) before and after bias correction. Bias correction effectively suppressed the effect of real age on the predicted age.

FIGURE 3

Accuracy of structure age prediction using the baseline acquisition of healthy subjects (95 CI: 95% confidence interval).

FIGURE 4

Effect of baseline diagnosis on structure age prediction (point estimate and 95% confidence intervals). The predicted age was significantly larger (p < 0.0001 FDR corrected) for all structures compared to healthy controls (group of reference, no effect) as well as between MCI and ADD groups.