Guardado en:
Detalles Bibliográficos
Autores principales: Goel, Anoushkrit, Singh, Simroop, Joshi, Ankita, Jha, Ranjeet Ranjan, Ahuja, Chirag, Nigam, Aditya, Bhavsar, Arnav
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:https://arxiv.org/abs/2601.13935
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866914266261487616
author Goel, Anoushkrit
Singh, Simroop
Joshi, Ankita
Jha, Ranjeet Ranjan
Ahuja, Chirag
Nigam, Aditya
Bhavsar, Arnav
author_facet Goel, Anoushkrit
Singh, Simroop
Joshi, Ankita
Jha, Ranjeet Ranjan
Ahuja, Chirag
Nigam, Aditya
Bhavsar, Arnav
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2601_13935
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle TrackletGPT: A Language-like GPT Framework for White Matter Tract Segmentation
Goel, Anoushkrit
Singh, Simroop
Joshi, Ankita
Jha, Ranjeet Ranjan
Ahuja, Chirag
Nigam, Aditya
Bhavsar, Arnav
Computer Vision and Pattern Recognition
Machine Learning
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.
title TrackletGPT: A Language-like GPT Framework for White Matter Tract Segmentation
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2601.13935