| Unique ID issued by UMIN | UMIN000061816 |
|---|---|
| Receipt number | R000070699 |
| Scientific Title | Research and development of AI for landmark recognition in Esophagogastroduodenoscopy |
| Date of disclosure of the study information | 2026/06/15 |
| Last modified on | 2026/06/06 09:53:29 |
Development of an Artificial Intelligence System for Automatic Recognition of Anatomical Sites During Esophagogastroduodenoscopy
CAQ-EGD
Research and development of AI for landmark recognition in Esophagogastroduodenoscopy
CAQ-EGD
| Japan |
gastric cancer
| Gastroenterology |
Malignancy
NO
We will develop and validate an endoscopic AI system designed to ensure the comprehensiveness of imaging coverage during esophagogastroduodenoscopy (EGD). By providing physicians with feedback on imaging completeness, this AI is expected to reduce blind spots and decrease the rate of missed gastric cancers. We will evaluate the classification accuracy of the AI for standard anatomical imaging sites of the esophagus, stomach, and duodenum.
Efficacy
Classification accuracy of the AI for standard anatomical landmarks of the esophagus, stomach, and duodenum.
Performance of the image-quality assessment AI for filtering low-quality images; per-site classification accuracy.
Observational
| 18 | years-old | <= |
| Not applicable |
Male and Female
Patients 18 years of age or older who underwent EGD at Showa Medical University Northern Yokohama Hospital between January 1, 2020 and October 31, 2025, who did not opt out of the use of their AI-related information.
(1) Incomplete EGD; (2) limited visualization due to gastric residue; (3) history of esophageal, gastric, or duodenal surgery.
400
| 1st name | Masashi |
| Middle name | |
| Last name | Misawa |
SHOWA Medical University Northern Yokohama Hospital
Digestive Disease Center
2248503
35-1 Chigasaki-chuo, Tsuzuki-ku, Yokohama-shi, Kanagawa, Japan
0459497000
mmisawa@med.showa-u.ac.jp
| 1st name | Tomoya |
| Middle name | |
| Last name | Shibuya |
SHOWA Medical University Northern Yokohama Hospital
Digestive Disease Center
2248503
35-1 Chigasaki-chuo, Tsuzuki-ku, Yokohama-shi, Kanagawa, Japan
0459497000
tswork0603@gmail.com
SHOWA Medical University
SHOWA Medical University
Self funding
SHOWA Medical University Research Ethics Review Board
1-5-8 Hatanodai, Shinagawa-ku, Tokyo, Japan
03-3784-8129
m-rinri@ofc.showa-u.ac.jp
NO
| 2026 | Year | 06 | Month | 15 | Day |
Unpublished
496
No longer recruiting
| 2024 | Year | 07 | Month | 18 | Day |
| 2024 | Year | 10 | Month | 15 | Day |
| 2024 | Year | 10 | Month | 15 | Day |
| 2025 | Year | 10 | Month | 31 | Day |
Study design: Single-center retrospective observational study .
Recruitment method: All patients aged 18 years or older who underwent EGD at Showa Medical University Northern Yokohama Hospital between January 1, 2020 and October 31, 2025, who met the inclusion criteria and did not opt out of the use of their AI-related information.
Recruitment (data collection) period: January 1, 2020 to October 31, 2025.
Measured items: Classification accuracy of the AI for standard anatomical landmarks of the esophagus, stomach, and duodenum (using endoscopist-assigned labels as the reference standard); performance of the image-quality assessment AI for filtering low-quality images; per-site accuracy; sex; age.
| 2026 | Year | 06 | Month | 06 | Day |
| 2026 | Year | 06 | Month | 06 | Day |
Value
https://center6.umin.ac.jp/cgi-open-bin/icdr_e/ctr_view.cgi?recptno=R000070699