TrackletGPT: A Language-like GPT Framework for White Matter Tract Segmentation

TL;DR

TrackletGPT introduces a novel GPT-based framework for white matter tract segmentation that leverages sequential tracklet information, achieving superior accuracy and generalization across datasets.

Contribution

It presents a new language-like GPT model that encodes tractography data as tracklets, improving segmentation performance and robustness over existing methods.

Findings

Outperforms state-of-the-art methods on multiple datasets.

Achieves higher DICE, Overlap, and Overreach scores.

Demonstrates strong generalization across datasets.

Abstract

White Matter Tract Segmentation is imperative for studying brain structural connectivity, neurological disorders and neurosurgery. This task remains complex, as tracts differ among themselves, across subjects and conditions, yet have similar 3D structure across hemispheres and subjects. To address these challenges, we propose TrackletGPT, a language-like GPT framework which reintroduces sequential information in tokens using tracklets. TrackletGPT generalises seamlessly across datasets, is fully automatic, and encodes granular sub-streamline segments, Tracklets, scaling and refining GPT models in Tractography Segmentation. Based on our experiments, TrackletGPT outperforms state-of-the-art methods on average DICE, Overlap and Overreach scores on TractoInferno and HCP datasets, even on inter-dataset experiments.