Open Access
CC BY-NC-ND 4.0 · Endosc Int Open 2020; 08(02): E139-E146
DOI: 10.1055/a-1036-6114
Original article
Owner and Copyright © Georg Thieme Verlag KG 2020

Feedback from artificial intelligence improved the learning of junior endoscopists on histology prediction of gastric lesions

Thomas K.L. Lui
1   Department of Medicine, Queen Mary Hospital, University of Hong Kong, Hong Kong, China
,
Kenneth K.Y. Wong
2   Department of Computer Science, University of Hong Kong, Hong Kong, China
,
Loey L.Y. Mak
1   Department of Medicine, Queen Mary Hospital, University of Hong Kong, Hong Kong, China
,
Elvis W.P. To
1   Department of Medicine, Queen Mary Hospital, University of Hong Kong, Hong Kong, China
,
Vivien W.M. Tsui
1   Department of Medicine, Queen Mary Hospital, University of Hong Kong, Hong Kong, China
,
Zijie Deng
3   Department of Medicine, University of Hong Kong-Shenzhen Hospital, Shenzhen, China
,
Jiaqi Guo
3   Department of Medicine, University of Hong Kong-Shenzhen Hospital, Shenzhen, China
,
Li Ni
3   Department of Medicine, University of Hong Kong-Shenzhen Hospital, Shenzhen, China
,
Michael K.S. Cheung
1   Department of Medicine, Queen Mary Hospital, University of Hong Kong, Hong Kong, China
3   Department of Medicine, University of Hong Kong-Shenzhen Hospital, Shenzhen, China
,
Wai K. Leung
1   Department of Medicine, Queen Mary Hospital, University of Hong Kong, Hong Kong, China
› Author Affiliations
Further Information

Publication History

submitted 25 June 2019

accepted after revision 09 October 2019

Publication Date:
22 January 2020 (online)

Preview

Abstract

Background and study aims Artificial intelligence (AI)-assisted image classification has been shown to have high accuracy on endoscopic diagnosis. We evaluated the potential effects of use of an AI-assisted image classifier on training of junior endoscopists for histological prediction of gastric lesions.

Methods An AI image classifier was built on a convolutional neural network with five convolutional layers and three fully connected layers A Resnet backbone was trained by 2,000 non-magnified endoscopic gastric images. The independent validation set consisted of another 1,000 endoscopic images from 100 gastric lesions. The first part of the validation set was reviewed by six junior endoscopists and the prediction of AI was then disclosed to three of them (Group A) while the remaining three (Group B) were not provided this information. All endoscopists reviewed the second part of the validation set independently.

Results The overall accuracy of AI was 91.0 % (95 % CI: 89.2–92.7 %) with 97.1 % sensitivity (95 % CI: 95.6–98.7%), 85.9 % specificity (95 % CI: 83.0–88.4 %) and 0.91 area under the ROC (AUROC) (95 % CI: 0.89–0.93). AI was superior to all junior endoscopists in accuracy and AUROC in both validation sets. The performance of Group A endoscopists but not Group B endoscopists improved on the second validation set (accuracy 69.3 % to 74.7 %; P = 0.003).

Conclusion The trained AI image classifier can accurately predict presence of neoplastic component of gastric lesions. Feedback from the AI image classifier can also hasten the learning curve of junior endoscopists in predicting histology of gastric lesions.