TransforMesh: A Transformer Network for Longitudinal modeling of Anatomical Meshes

TL;DR

TransforMesh is a novel transformer-based network that models longitudinal 3D anatomical mesh changes, improving shape trajectory prediction and anomaly detection in neurodegenerative disease studies.

Contribution

This work introduces the first combination of transformer and mesh networks for medical image analysis, specifically for modeling neuroanatomical changes over time.

Findings

TransforMesh outperforms baseline models in shape trajectory modeling.

It effectively detects hippocampal anomalies related to Alzheimer's disease.

The approach demonstrates potential for longitudinal neuroimaging analysis.

Abstract

The longitudinal modeling of neuroanatomical changes related to Alzheimer's disease (AD) is crucial for studying the progression of the disease. To this end, we introduce TransforMesh, a spatio-temporal network based on transformers that models longitudinal shape changes on 3D anatomical meshes. While transformer and mesh networks have recently shown impressive performances in natural language processing and computer vision, their application to medical image analysis has been very limited. To the best of our knowledge, this is the first work that combines transformer and mesh networks. Our results show that TransforMesh can model shape trajectories better than other baseline architectures that do not capture temporal dependencies. Moreover, we also explore the capabilities of TransforMesh in detecting structural anomalies of the hippocampus in patients developing AD.