Improved U-Net Based on Mixed Loss Function for Liver Medical Image Segmentation

Yongjia Huang; Zaifeng Shi; Zhongqi Wang; Zhe Wang

doi:10.3788/LOP57.221003

Laser & Optoelectronics Progress, Volume. 57, Issue 22, 221003(2020)

Improved U-Net Based on Mixed Loss Function for Liver Medical Image Segmentation

Yongjia Huang¹, Zaifeng Shi^1,2、*, Zhongqi Wang¹, and Zhe Wang¹

Author Affiliations

¹School of Microelectronics, Tianjin University, Tianjin 300072, China

²Tianjin Key Laboratory of Microelectronic Technology for Imaging and Sensing, Tianjin 300072, China

show less

Abstract Get PDF(in Chinese)

Figures & Tables(13)

Fig. 1. Structure of proposed network

Download full size

Fig. 2. Improved U-Net structure

Download full size

Fig. 3. Residual refine module of network structure. (a) General residual refine module; (b) improved residual refine module

Download full size

Fig. 4. Training error and test accuracy of improved U-Net. (a) Liver tumor segmentation; (b) liver segmentation

Download full size

Fig. 5. Segmentation results of liver images obtained by different networks

Download full size

Fig. 6. Box plot of Dice coefficient of liver segmentation

Download full size

Fig. 7. Segmentation results of liver tumor images obtained by different networks

Download full size

Fig. 8. Box plot of Dice coefficient of liver tumor segmentation

Download full size

Fig. 9. Segmentation results of big nodules

Download full size

Fig. 10. Segmentation results of small nodules

Download full size

Table 1. Performance comparison of different networks for liver image segmentation

View table

Table 1. Performance comparison of different networks for liver image segmentation

Network	Dice coefficient	VOE /%	RVD /%	SEN	Jaccard coefficient
FCN-8s	88.38	19.62	-1.25	86.49	0.88
UNet	82.78	24.79	-2.72	81.46	0.83
H-DenseUNet^[5]	96.50	7.40	1.80
2D FCN^[14]	94.30	10.70	-1.40
BS UNet^[15]	96.10	7.50	2
Proposed network	96.26	7.90	0.80	95.96	0.92

Table 2. Performance comparison of different networks for liver tumor image segmentation

View table

Table 2. Performance comparison of different networks for liver tumor image segmentation

Network	Dice coefficient	VOE /%	RVD /%	SEN	Jaccard coefficient
FCN-8s	75 .57	71.43	-14.25	70.29	0.52
U-Net	72.23	67.62	-18.72	66.87	0.40
KC-SVM^[16]	84	28.22			0.73
RA-UNet^[17]	83	30.61			0.74
Edge-SVM^[18]	82	36.70			0.69
Proposed network	83.32	11.62	-15.98	79.88	0.72

Table 3. Performance comparison of different networks
View table
Table 3. Performance comparison of different networks
Network Dice coefficient SEN Jaccard coefficient
FCN-8s 73.32 79.83 0.64
U-Net 71.17 76.96 0.71
CDP-ResNet+IWS^[19] 81.85 87.30
DB-ResNet^[20] 82.74 89.35
CF-CNN+Scale^[21] 78.55 86.01
Proposed network 79.23 86.49 0.78

Tools

Get Citation

Copy Citation Text

Yongjia Huang, Zaifeng Shi, Zhongqi Wang, Zhe Wang. Improved U-Net Based on Mixed Loss Function for Liver Medical Image Segmentation[J]. Laser & Optoelectronics Progress, 2020, 57(22): 221003

Download Citation

EndNote(RIS)BibTex Plain Text

Set citation alerts for article

Save article for my favorites

Paper Information

Category: Image Processing

Received: Feb. 21, 2020

Accepted: Mar. 27, 2020

Published Online: Nov. 5, 2020

The Author Email: Zaifeng Shi (shizaifeng@tju.edu.cn)

DOI:10.3788/LOP57.221003

Topics

laser devices and laser physics

Lasers and Laser Optics

Laser physics

laser manufacturing

Instrumentation, Measurement and Metrology

Table 1. Performance comparison of different networks for liver image segmentation

Table 1. Performance comparison of different networks for liver image segmentation

Table 2. Performance comparison of different networks for liver tumor image segmentation

Table 2. Performance comparison of different networks for liver tumor image segmentation

Table 3. Performance comparison of different networks

Table 3. Performance comparison of different networks