Deep learning as a novel method for endoscopic diagnosis of chronic atrophic gastritis: a prospective nested case-control study.

Journal: BMC gastroenterology
Published Date:

Abstract

BACKGROUND AND AIMS: Chronic atrophic gastritis (CAG) is a precancerous disease that often leads to the development of gastric cancer (GC) and is positively correlated with GC morbidity. However, the sensitivity of the endoscopic diagnosis of CAG is only 42%. Therefore, we developed a real-time video monitoring model for endoscopic diagnosis of CAG based on U-Net deep learning (DL) and conducted a prospective nested case-control study to evaluate the diagnostic evaluation indices of the model and its consistency with pathological diagnosis.

Authors

  • Quchuan Zhao
    Department of Gastroenterology, Xuanwu Hospital of Capital Medical University, 45 Chang-chun Street, Beijing, 100053, China.
  • Qing Jia
    Department of Anesthesiology, Guang'anmen Hospital China Academy of Chinese Medical Sciences, 5 North Court Street, Beijing, 100053, China. jiaqing_hosp@163.com.
  • Tianyu Chi
    Department of Gastroenterology, Xuanwu Hospital of Capital Medical University, 45 Chang-chun Street, Beijing, 100053, China. xiaoyu800524.student@sina.com.