# TractoGPT: A GPT architecture for White Matter Segmentation

arXiv: https://arxiv.org/abs/2501.15464 · HTML: https://mlsanity.com/paper/2501.15464/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 18 references that are in the map.
- First posted on arXiv 26 Jan 2025.

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

- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [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)

## Built on by (most cited first, 1 of 1)

- [TrackletGPT: A Language-like GPT Framework for White Matter Tract Segmentation](https://mlsanity.com/paper/2601.13935/) (2026)

## Abstract (arXiv)

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.