Endoscopy 2019; 51(04): S4
DOI: 10.1055/s-0039-1681181
ESGE Days 2019 oral presentations
Friday, April 5, 2019 08:30 – 10:30: Artificial intelligence Club A
Georg Thieme Verlag KG Stuttgart · New York

COMPUTER-AIDED DIAGNOSIS (CAD) BASED ON CONVOLUTIONAL NEURAL NETWORK (CNN) SYSTEM USING ARTIFICIAL INTELLIGENCE (AI) FOR COLORECTAL POLYP CLASSIFICATION

Y Komeda
1   Gastroenterology and Hepatology, Kindai University Faculty of Medicine, Osaka, Japan
,
H Handa
2   Department of Informatics, RIST, Kindai University, Osaka, Japan
,
R Matsui
3   Graduate School of Science and Engineering, Kindai University, Osaka, Japan
,
H Kashida
1   Gastroenterology and Hepatology, Kindai University Faculty of Medicine, Osaka, Japan
,
T Watanabe
1   Gastroenterology and Hepatology, Kindai University Faculty of Medicine, Osaka, Japan
,
T Sakurai
1   Gastroenterology and Hepatology, Kindai University Faculty of Medicine, Osaka, Japan
,
M Kudo
1   Gastroenterology and Hepatology, Kindai University Faculty of Medicine, Osaka, Japan
› Author Affiliations
Further Information

Publication History

Publication Date:
18 March 2019 (online)

Also available at
 

Aims:

Computer-aided diagnosis (CAD) is becoming a next-generation tool for the diagnosis of human disease. CAD for colon polyps has been suggested as a particularly useful tool for trainee colonoscopists, as the use of a CAD system avoids the complications associated with unnecessary endoscopic resections. In addition to conventional CAD, a convolutional neural network (CNN) system utilizing artificial intelligence (AI) has been developing rapidly over the past 5 years. We firstly reported to generate a unique CNN-CAD system with an AI function that studied endoscopic images extracted from movies obtained with colonoscopes used in routine examinations (Komeda Y, Handa H et al Oncology 2017). Here, we attempted a pilot study of this novel CNN-CAD system for the diagnosis of colon polyps.

Methods:

A total of 92,571 images from cases of colonoscopy performed between January 2010 and December 2017 at Kindai University Hospital were used. These images were extracted from the video of actual endoscopic examinations. They were simply diagnosed as either an adenomatous or non-adenomatous polyp (hyperplastic polyp). The gold standard of endoscopic diagnosis is the pathological results. The number of images used by AI to learn to distinguish adenomatous polyp from non-adenomatous polyp (hyperplastic polyp) was 29,572: 62,999. The size of each image was adjusted to 256 × 256 pixels. A 10-hold cross-validation was carried out. We carried out a pilot study evaluating the 60 cases of colonic polyp that were not learned on AI function.

Results:

The rate of diagnosis of adenomatous polyps through white-light, NBI and chromoendoscopy observation were 97.5%, 94.8% and 90.1%, respectively. The rate of diagnosis of non-adenomatous polyp (hyperplastic polyps) through white light, NBI and chromoendoscopy observation were 97.9%, 96.5% and 99.5%, respectively.

Conclusions:

A CNN-CAD system using routine colonoscopy might be useful for the rapid diagnosis of colorectal polyp classification.