Computer-Aided Endoscopic Diagnosis Without Human-Specific Labeling.

Journal: IEEE transactions on bio-medical engineering
Published Date: Feb 15, 2016

Abstract

GOAL: Most state-of-the-art computer-aided endoscopic diagnosis methods require pixelwise labeled data to train various supervised machine learning models. However, it is a tedious and time-consuming work to collect sufficient precisely labeled image data. Fortunately, we can easily obtain huge endoscopic medical reports including the diagnostic text and images, which can be considered as weakly labeled data.

Authors

  • Shuai Wang
    Department of Intensive Care Unit, China-Japan Union Hospital of Jilin University, Changchun, China.
  • Yang Cong
    State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Nanta Street 114, Shenyang 110016, China.
  • Huijie Fan
  • Lianqing Liu
  • Xiaoqiu Li
  • Yunsheng Yang
    Department of Gastroenterology and Hepatology, Chinese PLA General Hospital, 28 Fuxing Road, Beijing 100000, China.
  • Yandong Tang
    State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Nanta Street 114, Shenyang 110016, China.
  • Huaici Zhao
    Key Laboratory of Image Understanding and Computer Vision, Shenyang Institute of Automation, Chinese Academy of Sciences, Nanta Street 114, Shenyang 110016, China.
  • Haibin Yu
    School of Electronics and Information, Hangzhou Dianzi University, Hangzhou 310018, China.

Keywords

External Resources

Popular Topics
Recent Journals