TractSeg - Fast and accurate white matter tract segmentation

• Published in: NeuroImage (Orlando, Fla.) Vol. 183; pp. 239 - 253
• Main Authors: Wasserthal, Jakob, Neher, Peter, Maier-Hein, Klaus H.
• Format: Journal Article
• Language: English
• Published: United States Elsevier Inc 01.12.2018; Elsevier Limited
• Subjects: Autism; Collaboration; Data collection; Data exchange; Datasets; Deep learning; Diffusion-weighted imaging; Fiber tractography; Image processing; Informatics; Machine learning; Magnetic resonance imaging; Medical imaging; Methods; Morphology; Neural networks; Neurosciences; Registration; Schizophrenia; Segmentation; Substantia alba; Diffusion-weighted imaging; Deep learning; Fiber tractography; Segmentation; Machine learning
• ISSN: 1053-8119; 1095-9572
• DOI: 10.1016/j.neuroimage.2018.07.070

The individual course of white matter fiber tracts is an important factor for analysis of white matter characteristics in healthy and diseased brains. Diffusion-weighted MRI tractography in combination with region-based or clustering-based selection of streamlines is a unique combination of tools which enables the in-vivo delineation and analysis of anatomically well-known tracts. This, however, currently requires complex, computationally intensive processing pipelines which take a lot of time to set up. TractSeg is a novel convolutional neural network-based approach that directly segments tracts in the field of fiber orientation distribution function (fODF) peaks without using tractography, image registration or parcellation. We demonstrate that the proposed approach is much faster than existing methods while providing unprecedented accuracy, using a population of 105 subjects from the Human Connectome Project. We also show initial evidence that TractSeg is able to generalize to differently acquired data sets for most of the bundles. The code and data are openly available at https://github.com/MIC-DKFZ/TractSeg/ and https://doi.org/10.5281/zenodo.1088277, respectively. •Fast white matter tract segmentation with high accuracy.•No need for additional techniques like registration, tractography or parcellation.•Extensive evaluation for 72 tracts with comparison to six other segmentation methods.•Openly available dataset of reference tract delineations.•Openly available code with pretrained model.