# DeepBundle: Fiber Bundle Parcellation with Graph Convolution Neural Networks

## TL;DR

DeepBundle introduces a registration-free fiber parcellation method using graph convolution neural networks to accurately classify brain white matter tracts based on their geometric features, bypassing the need for atlas registration.

## Contribution

It presents a novel deep learning approach employing GCNNs for fiber parcellation that eliminates the reliance on traditional registration-based methods.

## Key findings

- Effective fiber parcellation demonstrated on Human Connectome Project data.
- GCNNs successfully extract geometric features for accurate tract classification.
- Outperforms traditional registration-dependent methods.

## Abstract

Parcellation of whole-brain tractography streamlines is an important step for tract-based analysis of brain white matter microstructure. Existing fiber parcellation approaches rely on accurate registration between an atlas and the tractograms of an individual, however, due to large individual differences, accurate registration is hard to guarantee in practice. To resolve this issue, we propose a novel deep learning method, called DeepBundle, for registration-free fiber parcellation. Our method utilizes graph convolution neural networks (GCNNs) to predict the parcellation label of each fiber tract. GCNNs are capable of extracting the geometric features of each fiber tract and harnessing the resulting features for accurate fiber parcellation and ultimately avoiding the use of atlases and any registration method. We evaluate DeepBundle using data from the Human Connectome Project. Experimental results demonstrate the advantages of DeepBundle and suggest that the geometric features extracted from each fiber tract can be used to effectively parcellate the fiber tracts.