TractShapeNet: Efficient Multi-Shape Learning with 3D Tractography Point Clouds

TL;DR

This paper introduces TractShapeNet, a deep learning framework that efficiently computes brain white matter shape measures from tractography point clouds, outperforming traditional methods in speed and accuracy, and supporting cognitive prediction tasks.

Contribution

We propose a novel deep learning approach, TractShapeNet, for fast and accurate shape measure computation from tractography point clouds, improving over existing models and traditional tools.

Findings

Outperforms other point cloud models in correlation and error metrics

Faster inference compared to DSI-Studio

Shape measures are effective in cognitive prediction tasks

Abstract

Brain imaging studies have demonstrated that diffusion MRI tractography geometric shape descriptors can inform the study of the brain's white matter pathways and their relationship to brain function. In this work, we investigate the possibility of utilizing a deep learning model to compute shape measures of the brain's white matter connections. We introduce a novel framework, TractShapeNet, that leverages a point cloud representation of tractography to compute five shape measures: length, span, volume, total surface area, and irregularity. We assess the performance of the method on a large dataset including 1065 healthy young adults. Experiments for shape measure computation demonstrate that our proposed TractShapeNet outperforms other point cloud-based neural network models in both the Pearson correlation coefficient and normalized error metrics. We compare the inference runtime results with the conventional shape computation tool DSI-Studio. Our results demonstrate that a deep learning approach enables faster and more efficient shape measure computation. We also conduct experiments on two downstream language cognition prediction tasks, showing that shape measures from TractShapeNet perform similarly to those computed by DSI-Studio. Our code will be available at: https://github.com/SlicerDMRI/TractShapeNet.