Multiscale unsupervised domain adaptation for automatic pancreas segmentation in CT volumes using adversarial learning.

Journal: Medical physics
Published Date:

Abstract

PURPOSE: Computer-aided automatic pancreas segmentation is essential for early diagnosis and treatment of pancreatic diseases. However, the annotation of pancreas images requires professional doctors and considerable expenditure. Due to imaging differences among various institution population, scanning devices, imaging protocols, and so on, significant degradation in the performance of model inference results is prone to occur when models trained with domain-specific (usually institution-specific) datasets are directly applied to new (other centers/institutions) domain data. In this paper, we propose a novel unsupervised domain adaptation method based on adversarial learning to address pancreas segmentation challenges with the lack of annotations and domain shift interference.

Authors

  • Yan Zhu
    Department of Chemistry, Xixi Campus, Zhejiang University, Hangzhou, 310028, China. Electronic address: zhuyan@zju.edu.cn.
  • Peijun Hu
    School of Mathematical Sciences, Zhejiang University, Hangzhou, 310027, China.
  • Xiang Li
    Department of Radiology, Massachusetts General Hospital and Harvard Medical School, Boston, MA, United States.
  • Yu Tian
    Key Laboratory of Development and Maternal and Child Diseases of Sichuan Province, Department of Pediatrics, Sichuan University, Chengdu, China.
  • Xueli Bai
  • Tingbo Liang
    Department of Hepatobiliary and Pancreatic Surgery of the First Affiliated Hospital, State Key Laboratory of Modern Optical Instrumentation, Zhejiang University School of Medicine, Hangzhou 310003, China.
  • Jingsong Li
    Research Center for Healthcare Data Science, Zhejiang Lab, Hangzhou, China.