White matter bundle segmentation is crucial for studying brain structural connectivity, neurosurgical planning, and neurological disorders. White Matter Segmentation remains challenging due to structural similarity in streamlines, subject variability, symmetry in 2 hemispheres, etc. To address these challenges, we propose TractoGPT, a GPT-based architecture trained on streamline, cluster, and fusion data representations separately. TractoGPT is a fully-automatic method that generalizes across datasets and retains shape information of the white matter bundles. Experiments also show that TractoGPT outperforms state-of-the-art methods on average DICE, Overlap and Overreach scores. We use TractoInferno and 105HCP datasets and validate generalization across dataset.
@article{arxiv.2501.15464,
title = {TractoGPT: A GPT architecture for White Matter Segmentation},
author = {Anoushkrit Goel and Simroop Singh and Ankita Joshi and Ranjeet Ranjan Jha and Chirag Ahuja and Aditya Nigam and Arnav Bhavsar},
journal= {arXiv preprint arXiv:2501.15464},
year = {2025}
}
Comments
Accepted as a conference paper at 23rd IEEE International Symposium on Biomedical Imaging 2025. IEEE holds the copyright for this publication