Tractogpt: A GPT Architecture for White Matter Tract Segmentation
Anoushkrit Goel, Simroop Singh, Ankita Joshi, Ranjeet Ranjan Jha, Chirag Kamal Ahuja, Aditya Nigam, Arnav V. Bhavsar · 2025
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, sub-ject 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 datasets.