TY - JOUR
T1 - Volumetric segmentation of white matter tracts with label embedding
AU - Liu, Wan
AU - Lu, Qi
AU - Zhuo, Zhizheng
AU - Li, Yuxing
AU - Duan, Yunyun
AU - Yu, Pinnan
AU - Qu, Liying
AU - Ye, Chuyang
AU - Liu, Yaou
N1 - Publisher Copyright:
© 2022
PY - 2022/4/15
Y1 - 2022/4/15
N2 - Convolutional neural networks have achieved state-of-the-art performance for white matter (WM) tract segmentation based on diffusion magnetic resonance imaging (dMRI). However, the segmentation can still be difficult for challenging WM tracts with thin bodies or complicated shapes; the segmentation is even more problematic in challenging scenarios with reduced data quality or domain shift between training and test data, which can be easily encountered in clinical settings. In this work, we seek to improve the segmentation of WM tracts, especially for challenging WM tracts in challenging scenarios. In particular, our method is based on volumetric WM tract segmentation, where voxels are directly labeled without performing tractography. To improve the segmentation, we exploit the characteristics of WM tracts that different tracts can cross or overlap and revise the network design accordingly. Specifically, because multiple tracts can co-exist in a voxel, we hypothesize that the different tract labels can be correlated. The tract labels at a single voxel are concatenated as a label vector, the length of which is the number of tract labels. Due to the tract correlation, this label vector can be projected into a lower-dimensional space—referred to as the embedded space—for each voxel, which allows the segmentation network to solve a simpler problem. By predicting the coordinate in the embedded space for the tracts at each voxel and subsequently mapping the coordinate to the label vector with a reconstruction module, the segmentation result can be achieved. To facilitate the learning of the embedded space, an auxiliary label reconstruction loss is integrated with the segmentation accuracy loss during network training, and network training and inference are end-to-end. Our method was validated on two dMRI datasets under various settings. The results show that the proposed method improves the accuracy of WM tract segmentation, and the improvement is more prominent for challenging tracts in challenging scenarios.
AB - Convolutional neural networks have achieved state-of-the-art performance for white matter (WM) tract segmentation based on diffusion magnetic resonance imaging (dMRI). However, the segmentation can still be difficult for challenging WM tracts with thin bodies or complicated shapes; the segmentation is even more problematic in challenging scenarios with reduced data quality or domain shift between training and test data, which can be easily encountered in clinical settings. In this work, we seek to improve the segmentation of WM tracts, especially for challenging WM tracts in challenging scenarios. In particular, our method is based on volumetric WM tract segmentation, where voxels are directly labeled without performing tractography. To improve the segmentation, we exploit the characteristics of WM tracts that different tracts can cross or overlap and revise the network design accordingly. Specifically, because multiple tracts can co-exist in a voxel, we hypothesize that the different tract labels can be correlated. The tract labels at a single voxel are concatenated as a label vector, the length of which is the number of tract labels. Due to the tract correlation, this label vector can be projected into a lower-dimensional space—referred to as the embedded space—for each voxel, which allows the segmentation network to solve a simpler problem. By predicting the coordinate in the embedded space for the tracts at each voxel and subsequently mapping the coordinate to the label vector with a reconstruction module, the segmentation result can be achieved. To facilitate the learning of the embedded space, an auxiliary label reconstruction loss is integrated with the segmentation accuracy loss during network training, and network training and inference are end-to-end. Our method was validated on two dMRI datasets under various settings. The results show that the proposed method improves the accuracy of WM tract segmentation, and the improvement is more prominent for challenging tracts in challenging scenarios.
KW - Convolutional neural network
KW - Diffusion magnetic resonance imaging
KW - Label embedding
KW - White matter tract segmentation
UR - http://www.scopus.com/inward/record.url?scp=85123728691&partnerID=8YFLogxK
U2 - 10.1016/j.neuroimage.2022.118934
DO - 10.1016/j.neuroimage.2022.118934
M3 - Article
C2 - 35091078
AN - SCOPUS:85123728691
SN - 1053-8119
VL - 250
JO - NeuroImage
JF - NeuroImage
M1 - 118934
ER -