Artificial Intelligence-Based Classification of Anatomical Sites in Esophagogastroduodenoscopy Images

Peng Yuan,1,* Zhong-Hua Ma,2,* Yan Yan,1,* Shi-Jie Li,2 Jing Wang,2 Qi Wu1 1State Key Laboratory of Holistic Integrative Management of Gastrointestinal Cancers, Beijing Key Laboratory of Carcinogenesis and Translational Research, Department of Endoscopy, Peking University Can...

Full description

Saved in:
Bibliographic Details
Main Authors: Yuan P, Ma ZH, Yan Y, Li SJ, Wang J, Wu Q
Format: Article
Language:English
Published: Dove Medical Press 2024-12-01
Series:International Journal of General Medicine
Subjects:
Online Access:https://www.dovepress.com/artificial-intelligence-based-classification-of-anatomical-sites-in-es-peer-reviewed-fulltext-article-IJGM
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846126582666625024
author Yuan P
Ma ZH
Yan Y
Li SJ
Wang J
Wu Q
author_facet Yuan P
Ma ZH
Yan Y
Li SJ
Wang J
Wu Q
author_sort Yuan P
collection DOAJ
description Peng Yuan,1,* Zhong-Hua Ma,2,* Yan Yan,1,* Shi-Jie Li,2 Jing Wang,2 Qi Wu1 1State Key Laboratory of Holistic Integrative Management of Gastrointestinal Cancers, Beijing Key Laboratory of Carcinogenesis and Translational Research, Department of Endoscopy, Peking University Cancer Hospital & Institute, Beijing, 100142, People’s Republic of China; 2Key Laboratory of Carcinogenesis and Translational Research (Ministry of Education), Department of Endoscopy, Peking University Cancer Hospital & Institute, Beijing, 100142, People’s Republic of China*These authors contributed equally to this workCorrespondence: Qi Wu, State Key Laboratory of Holistic Integrative Management of Gastrointestinal Cancers, Beijing Key Laboratory of Carcinogenesis and Translational Research, Department of Endoscopy, Peking University Cancer Hospital & Institute, Beijing, 100142, People’s Republic of China, Email wuqi1973@126.comBackground: A full examination of gastrointestinal tract is an essential prerequisite for effectively detecting gastrointestinal lesions. However, there is a lack of efficient tools to analyze and recognize gastric anatomy locations, preventing the complete portrayal of entire stomach. This study aimed to evaluate the effectiveness of artificial intelligence in identifying gastric anatomy sites by analyzing esophagogastroduodenoscopy images.Methods: Using endoscopic images, we proposed a system called the Artificial Intelligence of Medicine (AIMED) through convolutional neural networks and MobileNetV3-large. The performance of artificial intelligence in the recognition of anatomic sites in esophagogastroduodenoscopy images was evaluated by considering many cases. Primary outcomes included diagnostic accuracy, sensitivity, and specificity.Results: A total of 160,308 images from 27 categories of the upper endoscopy anatomy classification were included in this retrospective research. As a test group, 16031 esophagogastroduodenoscopy images with 27 categories were used to evaluate AIMED’s performance in identifying gastric anatomy sites. The convolutional neural network’s accuracy, sensitivity, and specificity were determined to be 99.40%, 91.85%, and 99.69%, respectively.Conclusion: The AIMED system achieved high accuracy with regard to recognizing gastric anatomy sites, and it could assist the operator in enhancing the quality control of the used endoscope. Moreover, it could contribute to a more standardized endoscopic performance. Overall, our findings prove that artificial-intelligence-based systems can be indispensable to the endoscopic revolution (Clinical trial registration number: NCT04384575 (12/05/2020)).Keywords: artificial intelligence, convolutional neural network, esophagogastroduodenoscopy, quality control
format Article
id doaj-art-923bdfd86c544c369dd88f57e01aac9f
institution Kabale University
issn 1178-7074
language English
publishDate 2024-12-01
publisher Dove Medical Press
record_format Article
series International Journal of General Medicine
spelling doaj-art-923bdfd86c544c369dd88f57e01aac9f2024-12-12T16:44:08ZengDove Medical PressInternational Journal of General Medicine1178-70742024-12-01Volume 176127613898297Artificial Intelligence-Based Classification of Anatomical Sites in Esophagogastroduodenoscopy ImagesYuan PMa ZHYan YLi SJWang JWu QPeng Yuan,1,* Zhong-Hua Ma,2,* Yan Yan,1,* Shi-Jie Li,2 Jing Wang,2 Qi Wu1 1State Key Laboratory of Holistic Integrative Management of Gastrointestinal Cancers, Beijing Key Laboratory of Carcinogenesis and Translational Research, Department of Endoscopy, Peking University Cancer Hospital & Institute, Beijing, 100142, People’s Republic of China; 2Key Laboratory of Carcinogenesis and Translational Research (Ministry of Education), Department of Endoscopy, Peking University Cancer Hospital & Institute, Beijing, 100142, People’s Republic of China*These authors contributed equally to this workCorrespondence: Qi Wu, State Key Laboratory of Holistic Integrative Management of Gastrointestinal Cancers, Beijing Key Laboratory of Carcinogenesis and Translational Research, Department of Endoscopy, Peking University Cancer Hospital & Institute, Beijing, 100142, People’s Republic of China, Email wuqi1973@126.comBackground: A full examination of gastrointestinal tract is an essential prerequisite for effectively detecting gastrointestinal lesions. However, there is a lack of efficient tools to analyze and recognize gastric anatomy locations, preventing the complete portrayal of entire stomach. This study aimed to evaluate the effectiveness of artificial intelligence in identifying gastric anatomy sites by analyzing esophagogastroduodenoscopy images.Methods: Using endoscopic images, we proposed a system called the Artificial Intelligence of Medicine (AIMED) through convolutional neural networks and MobileNetV3-large. The performance of artificial intelligence in the recognition of anatomic sites in esophagogastroduodenoscopy images was evaluated by considering many cases. Primary outcomes included diagnostic accuracy, sensitivity, and specificity.Results: A total of 160,308 images from 27 categories of the upper endoscopy anatomy classification were included in this retrospective research. As a test group, 16031 esophagogastroduodenoscopy images with 27 categories were used to evaluate AIMED’s performance in identifying gastric anatomy sites. The convolutional neural network’s accuracy, sensitivity, and specificity were determined to be 99.40%, 91.85%, and 99.69%, respectively.Conclusion: The AIMED system achieved high accuracy with regard to recognizing gastric anatomy sites, and it could assist the operator in enhancing the quality control of the used endoscope. Moreover, it could contribute to a more standardized endoscopic performance. Overall, our findings prove that artificial-intelligence-based systems can be indispensable to the endoscopic revolution (Clinical trial registration number: NCT04384575 (12/05/2020)).Keywords: artificial intelligence, convolutional neural network, esophagogastroduodenoscopy, quality controlhttps://www.dovepress.com/artificial-intelligence-based-classification-of-anatomical-sites-in-es-peer-reviewed-fulltext-article-IJGMartificial intelligenceconvolutional neural networkesophagogastroduodenoscopyquality control
spellingShingle Yuan P
Ma ZH
Yan Y
Li SJ
Wang J
Wu Q
Artificial Intelligence-Based Classification of Anatomical Sites in Esophagogastroduodenoscopy Images
International Journal of General Medicine
artificial intelligence
convolutional neural network
esophagogastroduodenoscopy
quality control
title Artificial Intelligence-Based Classification of Anatomical Sites in Esophagogastroduodenoscopy Images
title_full Artificial Intelligence-Based Classification of Anatomical Sites in Esophagogastroduodenoscopy Images
title_fullStr Artificial Intelligence-Based Classification of Anatomical Sites in Esophagogastroduodenoscopy Images
title_full_unstemmed Artificial Intelligence-Based Classification of Anatomical Sites in Esophagogastroduodenoscopy Images
title_short Artificial Intelligence-Based Classification of Anatomical Sites in Esophagogastroduodenoscopy Images
title_sort artificial intelligence based classification of anatomical sites in esophagogastroduodenoscopy images
topic artificial intelligence
convolutional neural network
esophagogastroduodenoscopy
quality control
url https://www.dovepress.com/artificial-intelligence-based-classification-of-anatomical-sites-in-es-peer-reviewed-fulltext-article-IJGM
work_keys_str_mv AT yuanp artificialintelligencebasedclassificationofanatomicalsitesinesophagogastroduodenoscopyimages
AT mazh artificialintelligencebasedclassificationofanatomicalsitesinesophagogastroduodenoscopyimages
AT yany artificialintelligencebasedclassificationofanatomicalsitesinesophagogastroduodenoscopyimages
AT lisj artificialintelligencebasedclassificationofanatomicalsitesinesophagogastroduodenoscopyimages
AT wangj artificialintelligencebasedclassificationofanatomicalsitesinesophagogastroduodenoscopyimages
AT wuq artificialintelligencebasedclassificationofanatomicalsitesinesophagogastroduodenoscopyimages