E-DU: Deep neural network for multimodal medical image segmentation based on semantic gap compensation.

Journal: Computers in biology and medicine
Published Date: Oct 12, 2022

Abstract

BACKGROUND: U-Net includes encoder, decoder and skip connection structures. It has become the benchmark network in medical image segmentation. However, the direct fusion of low-level and high-level convolution features with semantic gaps by traditional skip connections may lead to problems such as fuzzy generated feature maps and target region segmentation errors.

Authors

  • Haojia Wang
    Department of Health Statistics, College of Preventive Medicine, Army Medical University, NO.30 Gaotanyan Street, Shapingba District, Chongqing, 400038, China.
  • Xicheng Chen
    Department of Health Statistics, College of Preventive Medicine, Army Medical University, NO.30 Gaotanyan Street, Shapingba District, Chongqing, 400038, China.
  • Rui Yu
    Beijing Institute of Biotechnology, 20 Dongdajie Street, Fengtai District, Beijing, China.
  • Zeliang Wei
    Department of Health Statistics, College of Preventive Medicine, Army Medical University, NO.30 Gaotanyan Street, Shapingba District, Chongqing, 400038, China.
  • Tianhua Yao
    Department of Health Statistics, College of Preventive Medicine, Army Medical University, NO.30 Gaotanyan Street, Shapingba District, Chongqing, 400038, China.
  • Chengcheng Gao
    Department of Health Statistics, College of Preventive Medicine, Army Medical University, NO.30 Gaotanyan Street, Shapingba District, Chongqing, 400038, China.
  • Yang Li
    Occupation of Chinese Center for Disease Control and Prevention, Beijing, China.
  • Zhenyan Wang
    Department of Health Statistics, College of Preventive Medicine, Army Medical University, NO.30 Gaotanyan Street, Shapingba District, Chongqing, 400038, China.
  • Dong Yi
    Department of Health Statistics, College of Preventive Medicine, Army Medical University, NO.30 Gaotanyan Street, Shapingba District, Chongqing, 400038, China. Electronic address: yidong@tmmu.edu.cn.
  • Yazhou Wu
    Department of Health Statistics, College of Preventive Medicine, Army Medical University, NO.30 Gaotanyan Street, Shapingba District, Chongqing, 400038, China. Electronic address: asiawu@tmmu.edu.cn.

Keywords

External Resources

Popular Topics
Recent Journals