TractSeg - Fast and accurate white matter tract segmentation
This work addresses the need for efficient and accurate white matter tract analysis in neuroimaging, particularly for researchers studying brain health and disease, by providing a fast and open-source tool that simplifies a previously tedious process.
The paper tackles the problem of white matter tract segmentation in brain MRI, which traditionally requires complex and slow pipelines, by introducing TractSeg, a convolutional neural network that directly segments tracts from fiber orientation data without tractography. The result is a method that is much faster than existing approaches while achieving unprecedented accuracy, as demonstrated on 105 subjects from the Human Connectome Project.
The individual course of white matter fiber tracts is an important key for analysis of white matter characteristics in healthy and diseased brains. Uniquely, diffusion-weighted MRI tractography in combination with region-based or clustering-based selection of streamlines allows for the in-vivo delineation and analysis of anatomically well known tracts. This, however, currently requires complex, computationally intensive and tedious-to-set-up processing pipelines. TractSeg is a novel convolutional neural network-based approach that directly segments tracts in the field of fiber orientation distribution function (fODF) peaks without requiring tractography, image registration or parcellation. We demonstrate in 105 subjects from the Human Connectome Project that the proposed approach is much faster than existing methods while providing unprecedented accuracy. The code and data are openly available at https://github.com/MIC-DKFZ/TractSeg/ and https://doi.org/10.5281/zenodo.1088277, respectively.