TractSeg - Fast and accurate white matter tract segmentation
TractSeg - Fast and accurate white matter tract segmentation
复制标题
DOI：
10.1016/j.neuroimage.2018.07.070
复制
发表时间：
2018-12-01
期刊：
影响因子：
5.7
通讯作者：
Maier-Hein, Klaus H.
中科院分区：
文献类型：
--
作者：
Wasserthal, Jakob;Neher, Peter;Maier-Hein, Klaus H.
白质纤维束的个体走向是分析健康和患病大脑白质特征的重要因素。扩散加权 MRI 纤维束成像与基于区域或基于聚类的流线选择相结合，是一种独特的工具组合，可以对解剖学上众所周知的纤维束进行体内描绘和分析。然而，目前这需要复杂的、计算密集型的处理管道，这需要花费大量时间来设置。 TractSeg 是一种基于卷积神经网络的新型方法，可直接在纤维取向分布函数 (fODF) 峰值领域对纤维束进行分割，而无需使用纤维束成像、图像配准或分割。我们使用人类连接组项目的 105 名受试者群体证明，所提出的方法比现有方法快得多，同时提供了前所未有的准确性。我们还展示了 TractSeg 能够推广到大多数捆绑包以不同方式获取的数据集的初步证据。代码和数据分别可在 https://github.com/MIC-DKFZ/TractSeg/ 和 https://doi.org/10.5281/zenodo.1088277 上公开获取。
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.