Robust liver vessel extraction using 3D U-Net with variant dice loss function.

Journal: Computers in biology and medicine
Published Date: Aug 18, 2018

Abstract

PURPOSE: Liver vessel extraction from CT images is essential in liver surgical planning. Liver vessel segmentation is difficult due to the complex vessel structures, and even expert manual annotations contain unlabeled vessels. This paper presents an automatic liver vessel extraction method using deep convolutional network and studies the impact of incomplete data annotation on segmentation accuracy evaluation.

Authors

  • Qing Huang
    Department of Environmental Health and Occupational Medicine,West China School of Public Health,Sichuan University,Chengdu 610041,China.
  • Jinfeng Sun
    Department of Biomedical Engineering, School of Medicine, Tsinghua University, Room C249, Beijing, 100084, China. Electronic address: sjf16@mails.tsinghua.edu.cn.
  • Hui Ding
    Medical School, Huanghe Science & Technology University, Zhengzhou 450063, PR China.
  • Xiaodong Wang
    Cardiovascular Department, TEDA International Cardiovascular Hospital, Tianjin, China.
  • Guangzhi Wang
    Department of Biomedical Engineering, School of Medicine, Tsinghua University, Room C249, Beijing, 100084, China. Electronic address: wgz-dea@tsinghua.edu.cn.

Keywords

External Resources

Popular Topics
Recent Journals