English

Automated Segmentation of Brain Gray Matter Nuclei on Quantitative Susceptibility Mapping Using Deep Convolutional Neural Network

Image and Video Processing 2020-08-04 v1 Computer Vision and Pattern Recognition

Abstract

Abnormal iron accumulation in the brain subcortical nuclei has been reported to be correlated to various neurodegenerative diseases, which can be measured through the magnetic susceptibility from the quantitative susceptibility mapping (QSM). To quantitively measure the magnetic susceptibility, the nuclei should be accurately segmented, which is a tedious task for clinicians. In this paper, we proposed a double-branch residual-structured U-Net (DB-ResUNet) based on 3D convolutional neural network (CNN) to automatically segment such brain gray matter nuclei. To better tradeoff between segmentation accuracy and the memory efficiency, the proposed DB-ResUNet fed image patches with high resolution and the patches with low resolution but larger field of view into the local and global branches, respectively. Experimental results revealed that by jointly using QSM and T1_\text{1} weighted imaging (T1_\text{1}WI) as inputs, the proposed method was able to achieve better segmentation accuracy over its single-branch counterpart, as well as the conventional atlas-based method and the classical 3D-UNet structure. The susceptibility values and the volumes were also measured, which indicated that the measurements from the proposed DB-ResUNet are able to present high correlation with values from the manually annotated regions of interest.

Keywords

Cite

@article{arxiv.2008.00901,
  title  = {Automated Segmentation of Brain Gray Matter Nuclei on Quantitative Susceptibility Mapping Using Deep Convolutional Neural Network},
  author = {Chao Chai and Pengchong Qiao and Bin Zhao and Huiying Wang and Guohua Liu and Hong Wu and E Mark Haacke and Wen Shen and Chen Cao and Xinchen Ye and Zhiyang Liu and Shuang Xia},
  journal= {arXiv preprint arXiv:2008.00901},
  year   = {2020}
}

Comments

submitted to IEEE Transactions on Medical Imaging

R2 v1 2026-06-23T17:36:12.668Z