Predicting Shape Development: a Riemannian Method
This addresses a clinical problem for medical decision-making in diseases like Alzheimer's, though it appears incremental as it builds on existing shape space approaches.
The paper tackles predicting anatomical shape development from a single baseline observation by proposing a Riemannian method that encodes shapes in curved spaces and uses hierarchical statistical modeling. It outperforms deep learning and state-of-the-art methods in predicting hippocampus shape under Alzheimer's disease and human body motion, with concrete performance gains implied.
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.