Endoscopy 2020; 52(12): 1077-1083
DOI: 10.1055/a-1194-8771
Original article

Artificial intelligence-based diagnostic system classifying gastric cancers and ulcers: comparison between the original and newly developed systems

Ken Namikawa
1   Department of Gastroenterology, Cancer Institute Hospital, Japanese Foundation for Cancer Research, Tokyo, Japan
,
Toshiaki Hirasawa
1   Department of Gastroenterology, Cancer Institute Hospital, Japanese Foundation for Cancer Research, Tokyo, Japan
2   Tada Tomohiro Institute of Gastroenterology and Proctology, Saitama, Japan
,
Kaoru Nakano
1   Department of Gastroenterology, Cancer Institute Hospital, Japanese Foundation for Cancer Research, Tokyo, Japan
3   Department of Pathology, Cancer Institute Hospital, Japanese Foundation for Cancer Research, Tokyo, Japan
,
Yohei Ikenoyama
1   Department of Gastroenterology, Cancer Institute Hospital, Japanese Foundation for Cancer Research, Tokyo, Japan
,
Mitsuaki Ishioka
1   Department of Gastroenterology, Cancer Institute Hospital, Japanese Foundation for Cancer Research, Tokyo, Japan
,
Sho Shiroma
1   Department of Gastroenterology, Cancer Institute Hospital, Japanese Foundation for Cancer Research, Tokyo, Japan
,
Yoshitaka Tokai
1   Department of Gastroenterology, Cancer Institute Hospital, Japanese Foundation for Cancer Research, Tokyo, Japan
,
Shoichi Yoshimizu
1   Department of Gastroenterology, Cancer Institute Hospital, Japanese Foundation for Cancer Research, Tokyo, Japan
,
Yusuke Horiuchi
1   Department of Gastroenterology, Cancer Institute Hospital, Japanese Foundation for Cancer Research, Tokyo, Japan
,
Akiyoshi Ishiyama
1   Department of Gastroenterology, Cancer Institute Hospital, Japanese Foundation for Cancer Research, Tokyo, Japan
,
Toshiyuki Yoshio
1   Department of Gastroenterology, Cancer Institute Hospital, Japanese Foundation for Cancer Research, Tokyo, Japan
2   Tada Tomohiro Institute of Gastroenterology and Proctology, Saitama, Japan
,
Tomohiro Tsuchida
1   Department of Gastroenterology, Cancer Institute Hospital, Japanese Foundation for Cancer Research, Tokyo, Japan
,
Junko Fujisaki
1   Department of Gastroenterology, Cancer Institute Hospital, Japanese Foundation for Cancer Research, Tokyo, Japan
,
Tomohiro Tada
2   Tada Tomohiro Institute of Gastroenterology and Proctology, Saitama, Japan
4   AI Medical Service Inc., Tokyo, Japan
5   Department of Surgical Oncology, Graduate School of Medicine, The University of Tokyo, Tokyo, Japan
› Author Affiliations
Trial Registration: Japan Medical Association Registration number (trial ID): JMA-IIA00283 Type of study: Single-center retrospective case-control study
Preview

Abstract

Background We previously reported for the first time the usefulness of artificial intelligence (AI) systems in detecting gastric cancers. However, the “original convolutional neural network (O-CNN)” employed in the previous study had a relatively low positive predictive value (PPV). Therefore, we aimed to develop an advanced AI-based diagnostic system and evaluate its applicability for the classification of gastric cancers and gastric ulcers.

Methods We constructed an “advanced CNN” (A-CNN) by adding a new training dataset (4453 gastric ulcer images from 1172 lesions) to the O-CNN, which had been trained using 13 584 gastric cancer and 373 gastric ulcer images. The diagnostic performance of the A-CNN in terms of classifying gastric cancers and ulcers was retrospectively evaluated using an independent validation dataset (739 images from 100 early gastric cancers and 720 images from 120 gastric ulcers) and compared with that of the O-CNN by estimating the overall classification accuracy.

Results The sensitivity, specificity, and PPV of the A-CNN in classifying gastric cancer at the lesion level were 99.0 % (95 % confidence interval [CI] 94.6 %−100 %), 93.3 % (95 %CI 87.3 %−97.1 %), and 92.5 % (95 %CI 85.8 %−96.7 %), respectively, and for classifying gastric ulcers were 93.3 % (95 %CI 87.3 %−97.1 %), 99.0 % (95 %CI 94.6 %−100 %), and 99.1 % (95 %CI 95.2 %−100 %), respectively. At the lesion level, the overall accuracies of the O- and A-CNN for classifying gastric cancers and gastric ulcers were 45.9 % (gastric cancers 100 %, gastric ulcers 0.8 %) and 95.9 % (gastric cancers 99.0 %, gastric ulcers 93.3 %), respectively.

Conclusion The newly developed AI-based diagnostic system can effectively classify gastric cancers and gastric ulcers.

Supplementary material



Publication History

Received: 13 August 2019

Accepted: 05 June 2020

Accepted Manuscript online:
05 June 2020

Article published online:
08 July 2020

© 2020. Thieme. All rights reserved.

Georg Thieme Verlag KG
Rüdigerstraße 14, 70469 Stuttgart, Germany