Predicting the future development of an anatomical shape from a single baseline observation is a challenging task. But it can be essential for clinical decision-making. Research has shown that it should be tackled in curved shape spaces, as (e.g., disease-related) shape changes frequently expose nonlinear characteristics. We thus propose a novel prediction method that encodes the whole shape in a Riemannian shape space. It then learns a simple prediction technique founded on hierarchical statistical modeling of longitudinal training data. When applied to predict the future development of the shape of the right hippocampus under Alzheimer's disease and to human body motion, it outperforms deep learning-supported variants as well as state-of-the-art.
@article{arxiv.2212.04740,
title = {Predicting Shape Development: a Riemannian Method},
author = {Doğa Türkseven and Islem Rekik and Christoph von Tycowicz and Martin Hanik},
journal= {arXiv preprint arXiv:2212.04740},
year = {2024}
}
Comments
new experiment with human motion data; fixed vertex-assignment bug in the prediction of the varifold-based method