Anatomical Predictions using Subject-Specific Medical Data

Changes in brain anatomy can provide important insight for treatment design or scientific analyses. We present a method that predicts how brain anatomy for an individual will change over time. We model these changes through a diffeomorphic deformation field, and design a predictive function using convolutional neural networks. Given a predicted deformation field, a baseline scan can be warped to give a prediction of the brain scan at a future time. We demonstrate the method using the ADNI cohort, and analyze how performance is affected by model variants and the type of subject-specific information provided. We show that the model provides good predictions and that external clinical data can improve predictions.