Logo image
Back
Fast segmentation with the NextBrain histological atlas
Journal article   Peer reviewed

Fast segmentation with the NextBrain histological atlas

Oula Puonti, Jackson Nolan, Robert Dicamillo, Yael Balbastre, Adria Casamitjana, Matteo Mancini, Eleanor Robinson, Loic Peter, Roberto Annunziata, Juri Althonayan, …
Imaging neuroscience (Cambridge, Mass.), Vol.4, pp.1-20
05/26/2026
DOI: 10.1162/IMAG.a.1244
PMCID: PMC13214569
PMID: 42212221

View Online

Abstract

Structural brain analysis at the subregion level offers critical insights into healthy aging and neurodegenerative diseases. The NextBrain histological atlas was recently introduced to support such fine-grained investigations, but its existing Bayesian segmentation framework remains computationally prohibitive, particularly for large-scale studies. We present a new, open-source tool that dramatically accelerates segmentation using a hybrid approach combining: machine learning, contrast-adaptive segmentation; target-specific image synthesis; and fast diffeomorphic registration (all three with GPU support). Our method enables highly granular segmentation of brain MRI scans of any resolution and contrast ( ) at a fraction of the computational cost of the original method ( 5 minutes on a GPU). We validate our tool on four different modalities ( MRI, MRI, HiP-CT, and photography) across a total of approximately 4,000 brain scans. Our results demonstrate that the accelerated approach achieves comparable accuracy to the original method in terms of Dice scores, while reducing runtime by over an order of magnitude. This work enables high-resolution anatomical analysis at unprecedented scale and flexibility, providing a practical solution for large neuroimaging studies. Our tool is publicly available in FreeSurfer ( ).
 brain MRI segmentation domain-agnostic neuroimaging histological atlas Software Toolbox

Details

Metrics

1 Record Views
Logo image