Automated Segmentation and Tractography of Brainstem and Subcortical White Matter
- 1Vanderbilt University Institute of Imaging Science, Vanderbilt University Medical Center, Nashville, TN, United States; Department of Radiology and Radiological
Abstract
Diffusion MRI enables noninvasive mapping of human white matter pathways, but automated segmentation methods have largely focused on large association, projection, and commissural bundles. Brainstem and subcortical pathways supporting basal ganglia, cerebellar, limbic/reward, sensory, and homeostatic functions remain underrepresented in large-scale connectomic analyses. To address this gap, we adapted BundleParc, a recently introduced bundle-parcellation architecture, into an automated pipeline for direct segmentation and along-tract parcellation of 97 subcortical and brainstem white matter pathways. The model was trained on a curated reference dataset derived from Human Connectome Project diffusion MRI using anatomy-guided tractography, explicit inclusion and exclusion criteria, automated outlier filtering, and manual quality assurance. Operating directly on native-space fiber orientation distributions, the algorithm successfully recovers these intricate anatomical trajectories and ordered parcellations. We show the model generalizes to diverse external datasets spanning development, aging, and clinical cohorts, with performance varying across cohorts and acquisition protocols. The released container, trained model, population atlas, reference streamlines, and quality assurance outputs provide a resource for quantitative studies of brainstem and subcortical pathways.
Related
- Mapping Mesolimbic Dopamine Projections to Subcortical Circuits Underlying Adaptive Behavior: A Human 7T Diffusion Tractography Atlas
- Altered hemispheric lateralization of white matter pathways in developmental dyslexia: Evidence from spherical deconvolution tractography
- Test-Retest Reproducibility of Single- and Cross-Population White Matter Atlases in Diffusion MRI Tractography
- Fully automated diaphragm segmentation on routine 2D-cine and 3D thoracic MRI: multireader validation
- Organotchi: an open-source tool for the automated segmentation, morphological characterization, and longitudinal tracking of organoids
BibTeX
@misc{schilling2026automated,
title = {{Automated Segmentation and Tractography of Brainstem and Subcortical White Matter}},
author = {K. G. Schilling and G. Rudravaram and A. Theberge and M. Amandola and M. E. Kim and K. L. Humphreys and L. Cutting and D. Archer and T. J. Hohman and A. L. Jefferson and L. L. Beason Held and M. Bilgel and Alzheimers Disease Neuroimaging Initiative and The BIOCARD Study Team and M. Chamberland and M. Descoteaux and L. Petit and F. Rheault and B. Landman},
howpublished = {bioRxiv},
year = {2026},
month = jun,
doi = {10.64898/2026.06.09.731210},
url = {https://www.biorxiv.org/content/10.64898/2026.06.09.731210v2},
note = {CC BY},
}
RIS
TY - UNPB
TI - Automated Segmentation and Tractography of Brainstem and Subcortical White Matter
AU - K. G. Schilling
AU - G. Rudravaram
AU - A. Theberge
AU - M. Amandola
AU - M. E. Kim
AU - K. L. Humphreys
AU - L. Cutting
AU - D. Archer
AU - T. J. Hohman
AU - A. L. Jefferson
AU - L. L. Beason Held
AU - M. Bilgel
AU - Alzheimers Disease Neuroimaging Initiative
AU - The BIOCARD Study Team
AU - M. Chamberland
AU - M. Descoteaux
AU - L. Petit
AU - F. Rheault
AU - B. Landman
PY - 2026
DA - 2026/06/09
PB - bioRxiv
DO - 10.64898/2026.06.09.731210
UR - https://www.biorxiv.org/content/10.64898/2026.06.09.731210v2
AB - Diffusion MRI enables noninvasive mapping of human white matter pathways, but automated segmentation methods have largely focused on large association, projection, and commissural bundles. Brainstem and subcortical pathways supporting basal ganglia, cerebellar, limbic/reward, sensory, and homeostatic functions remain underrepresented in large-scale connectomic analyses. To address this gap, we adapted BundleParc, a recently introduced bundle-parcellation architecture, into an automated pipeline for direct segmentation and along-tract parcellation of 97 subcortical and brainstem white matter pathways. The model was trained on a curated reference dataset derived from Human Connectome Project diffusion MRI using anatomy-guided tractography, explicit inclusion and exclusion criteria, automated outlier filtering, and manual quality assurance. Operating directly on native-space fiber orientation distributions, the algorithm successfully recovers these intricate anatomical trajectories and ordered parcellations. We show the model generalizes to diverse external datasets spanning development, aging, and clinical cohorts, with performance varying across cohorts and acquisition protocols. The released container, trained model, population atlas, reference streamlines, and quality assurance outputs provide a resource for quantitative studies of brainstem and subcortical pathways.
ER -