Alzheimer’s disease (AD) studies revealed that abnormal deposition of tau spreads in a specific spatial pattern, namely Braak stage. However, Braak staging is based on post mortem brains, each of which represents the cross-section of the tau trajectory in disease progression, and numerous studies were reported that does not conform to this model. This study aimed to identify the tau trajectory and additionally quantify the tau progress in a data-driven approach using the continuous latent space learned by variational autoencoder (VAE).
1080 [18F]Flortaucipir brain PET images were collected from Alzheimer’s Disease Neuroimaging Initiative database. VAE was built to compress the hidden features from tau images in latent space. Hierarchical clustering and minimum spanning tree were applied to organize the features and calibrate them to the tau progression, thus deriving pseudo-time. The image-level tau trajectory was inferred by continuously sampling across the calibrated latent features. We assessed the pseudo-time with regards to tau standardized uptake value ratio (SUVr) in AD-vulnerable regions, amyloid deposit, glucose metabolism, cognitive scores and clinical diagnosis.
We identified 4 clusters that plausibly capture certain stages of AD and organized the clusters in the latent space. The inferred tau trajectory agreed with the Braak staging. According to the derived pseudo-time, tau first deposits in the parahippocampal and amygdala, and then spreads to fusiform, inferior temporal lobe, and posterior cingulate. Prior to the regional tau deposition, amyloid accumulates first.
The spatiotemporal trajectory of tau progression inferred in this study was consistent with Braak staging, and the profile of other biomarkers in disease progression agreed well with previous findings. We addressed that this approach additionally carries a potential to quantify tau progression as a continuous variable taking a whole-brain tau image into account.