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

arXiv: https://arxiv.org/abs/2601.13935 · HTML: https://mlsanity.com/paper/2601.13935/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 18 references that are in the map.
- First posted on arXiv 20 Jan 2026.

## Builds on (most cited first, 9 of 9)

- [Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modeling](https://mlsanity.com/paper/2111.14819/) (2021)
- [PointGPT: Auto-regressively Generative Pre-training from Point Clouds](https://mlsanity.com/paper/2305.11487/) (2023)
- [TractSeg - Fast and accurate white matter tract segmentation](https://mlsanity.com/paper/1805.07103/) (2018)
- [Filtering in tractography using autoencoders (FINTA)](https://mlsanity.com/paper/2010.04007/) (2020)
- [TractCloud: Registration-free tractography parcellation with a novel local-global streamline point cloud representation](https://mlsanity.com/paper/2307.09000/) (2023)
- [Generative Sampling in Bundle Tractography using Autoencoders (GESTA)](https://mlsanity.com/paper/2204.10891/) (2022)
- [FIESTA: Autoencoders for accurate fiber segmentation in tractography](https://mlsanity.com/paper/2212.00143/) (2022)
- [TractoEmbed: Modular Multi-level Embedding framework for white matter tract segmentation](https://mlsanity.com/paper/2411.08187/) (2024)
- [TractoGPT: A GPT architecture for White Matter Segmentation](https://mlsanity.com/paper/2501.15464/) (2025)

## Abstract (arXiv)

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.