BundleSeg: A versatile, reliable and reproducible approach to white matter bundle segmentation

TL;DR

BundleSeg is a fast, reliable, and reproducible method for white matter pathway segmentation that improves upon existing techniques in accuracy and speed, facilitating neuroimaging research.

Contribution

It introduces a novel segmentation approach combining iterative registration with a precise streamline search, eliminating the need for tractogram clustering.

Findings

Achieves higher repeatability and reproducibility than state-of-the-art methods.

Offers significant speed improvements in white matter segmentation.

Enhances sensitivity and specificity in tractography-based studies.

Abstract

This work presents BundleSeg, a reliable, reproducible, and fast method for extracting white matter pathways. The proposed method combines an iterative registration procedure with a recently developed precise streamline search algorithm that enables efficient segmentation of streamlines without the need for tractogram clustering or simplifying assumptions. We show that BundleSeg achieves improved repeatability and reproducibility than state-of-the-art segmentation methods, with significant speed improvements. The enhanced precision and reduced variability in extracting white matter connections offer a valuable tool for neuroinformatic studies, increasing the sensitivity and specificity of tractography-based studies of white matter pathways.