Disentangled Representation of Longitudinal Β-Amyloid for AD Via Sequential Graph Variational Autoencoder with Supervision

The emergence of Positron Emission Tomography (PET) imaging allows us to quantify the burden of amyloid plaques in-vivo, which is one of the hallmarks of Alzheimer’s disease (AD). However, the invasive exposure to radiation and high imaging cost significantly restrict the application of PET in characterizing the evolution of pathology burden which often requires longitudinal PET image sequences. In this regard, we propose a proof-of-concept solution to generate the complete trajectory of pathological events throughout the brain based on very limited number of PET scans. We present a novel variational autoencoder model to learn a latent population-level representation of neurodegeneration process based on the longitudinal β-amyloid measurements at each brain region and longitudinal diagnostic stages. As the propagation of pathological burdens follow the topology of brain connectome, we further cast our neural network into a supervised sequential graph VAE, where we use the brain network to guide the representation learning. Experiments show that the disentangled representation can capture disease-related dynamics of amyloid and forecast the level of amyloid depositions at future time points.