Automatic three-dimensional segmentation of liver and tumors regions based on conditional generative adversarial networks.
10.7507/1001-5515.201912077
- Author:
Zelin ZHANG
1
;
Baoming LI
1
;
Jun XU
1
Author Information
1. Jiangsu Key Laboratory of Big Data Analysis, Nanjing University of Information Science and Technology, Nanjing 210044, P.R.China.
- Publication Type:Journal Article
- Keywords:
computed tomography;
conditional generative adversarial networks;
deep learning;
three-dimensional automatic segmentation of liver and tumor regions
- MeSH:
Humans;
Image Processing, Computer-Assisted;
Liver Neoplasms/diagnostic imaging*;
Tomography, X-Ray Computed
- From:
Journal of Biomedical Engineering
2021;38(1):80-88
- CountryChina
- Language:Chinese
-
Abstract:
The three-dimensional (3D) liver and tumor segmentation of liver computed tomography (CT) has very important clinical value for assisting doctors in diagnosis and prognosis. This paper proposes a tumor 3D conditional generation confrontation segmentation network (T3scGAN) based on conditional generation confrontation network (cGAN), and at the same time, a coarse-to-fine 3D automatic segmentation framework is used to accurately segment liver and tumor area. This paper uses 130 cases in the 2017 Liver and Tumor Segmentation Challenge (LiTS) public data set to train, verify and test the T3scGAN model. Finally, the average Dice coefficients of the validation set and test set segmented in the 3D liver regions were 0.963 and 0.961, respectively, while the average Dice coefficients of the validation set and test set segmented in the 3D tumor regions were 0.819 and 0.796, respectively. Experimental results show that the proposed T3scGAN model can effectively segment the 3D liver and its tumor regions, so it can better assist doctors in the accurate diagnosis and treatment of liver cancer.
