Geometric Deep Learning on Anatomical Meshes for the Prediction of Alzheimer's Disease

TL;DR

This paper evaluates four geometric deep learning methods on hippocampal meshes to predict Alzheimer's disease, finding template-based approaches more accurate and efficient, highlighting the potential of mesh representations in neuroimaging.

Contribution

The study compares recent mesh-based geometric deep learning approaches for Alzheimer's prediction, emphasizing the advantages of template-based methods over template-free ones.

Findings

Template-based methods outperform in accuracy and speed.

Meshes provide richer anatomical information than point clouds.

Automated template creation is feasible with existing neuroimaging tools.

Abstract

Geometric deep learning can find representations that are optimal for a given task and therefore improve the performance over pre-defined representations. While current work has mainly focused on point representations, meshes also contain connectivity information and are therefore a more comprehensive characterization of the underlying anatomical surface. In this work, we evaluate four recent geometric deep learning approaches that operate on mesh representations. These approaches can be grouped into template-free and template-based approaches, where the template-based methods need a more elaborate pre-processing step with the definition of a common reference template and correspondences. We compare the different networks for the prediction of Alzheimer's disease based on the meshes of the hippocampus. Our results show advantages for template-based methods in terms of accuracy, number of learnable parameters, and training speed. While the template creation may be limiting for some applications, neuroimaging has a long history of building templates with automated tools readily available. Overall, working with meshes is more involved than working with simplistic point clouds, but they also offer new avenues for designing geometric deep learning architectures.