Neuroimaging-derived brain age has been identified as a promising biomarker for accelerated brain age; however, the ageing process is highly heterogeneous and there is a need to further study the different brain ageing trajectories. In this study, we implemented a variational autoencoder (VAE) based model coupled with regression to identify different age-related patterns. Additionally, we correlated the patterns obtained, using a linear regression approach, with dementia-related risk factors. The model was evaluated in different cohorts, UK Biobank and ALFA+, to assess the robustness of the approach. The results showed a feasible strategy for detecting and validating brain age-related trajectories to identify possible early deviations using morphological brain data.