Identification of Barrett's esophagus in endoscopic images using deep learning

BMC Gastroenterology

Jiali Wu¹  Muhan Lv²  Chao Liu³  Tao Ren³  Wen Pan⁴  Xujia Li⁵  Song Su⁵  Yong Tang⁶  Linjing Zhou⁷  Weijia Wang⁷ 

[1] Department of Anesthesiology, The Affiliated Hospital of Southwest Medical University, Taiping Street No.25, 646000, Luzhou, Sichuan, China;Department of Digestion, The Affiliated Hospital of Southwest Medical University, Taiping Street No.25, 646000, Luzhou, Sichuan, China;Department of Digestion, The Hospital of Chengdu Office of People’s Government of Tibetan Autonomous Region, Ximianqiao Street No.20, 610054, Chengdu, Sichuan, China;Department of Digestion, West China Hospital of Sichuan University, 610054, Chengdu, Sichuan, China;Department of Digestion, The Hospital of Chengdu Office of People’s Government of Tibetan Autonomous Region, Ximianqiao Street No.20, 610054, Chengdu, Sichuan, China;Department of General Surgery (Hepatobiliary Surgery), The Affiliated Hospital of Southwest Medical University, Taiping Street No.25, 646000, Luzhou, Sichuan, China;School of Computer Science and Engineering, University of Electronic Science and Technology of China, 4 North Jianshe Road, 610054, Chengdu, Sichuan, China;School of Information and Software Engineering, University of Electronic Science and Technology of China, 4 North Jianshe Road, 610054, Chengdu, Sichuan, China;

关键词: Barrett's esophagus;    Esophagoscope;    Deep learning;    Fully convolutional networks;    Segmentation;   

DOI  :  10.1186/s12876-021-02055-2

来源: Springer

【 摘 要 】

BackgroundDevelopment of a deep learning method to identify Barrett's esophagus (BE) scopes in endoscopic images.Methods443 endoscopic images from 187 patients of BE were included in this study. The gastroesophageal junction (GEJ) and squamous-columnar junction (SCJ) of BE were manually annotated in endoscopic images by experts. Fully convolutional neural networks (FCN) were developed to automatically identify the BE scopes in endoscopic images. The networks were trained and evaluated in two separate image sets. The performance of segmentation was evaluated by intersection over union (IOU).ResultsThe deep learning method was proved to be satisfying in the automated identification of BE in endoscopic images. The values of the IOU were 0.56 (GEJ) and 0.82 (SCJ), respectively.ConclusionsDeep learning algorithm is promising with accuracies of concordance with manual human assessment in segmentation of the BE scope in endoscopic images. This automated recognition method helps clinicians to locate and recognize the scopes of BE in endoscopic examinations.

【 授权许可】

CC BY