Copyright
©The Author(s) 2023. Published by Baishideng Publishing Group Inc. All rights reserved.
Artificial intelligence system for the detection of Barrett’s esophagus
Ming-Chang Tsai, Hsu-Heng Yen, Hui-Yu Tsai, Yu-Kai Huang, Yu-Sin Luo, Edy Kornelius, Wen-Wei Sung, Chun-Che Lin, Ming-Hseng Tseng, Chi-Chih Wang
Ming-Chang Tsai, Chun-Che Lin, Chi-Chih Wang, Division of Gastroenterology and Hepatology, Department of Internal Medicine, Chung Shan Medical University Hospital, Taichung 402, Taiwan
Ming-Chang Tsai, Edy Kornelius, Wen-Wei Sung, Chun-Che Lin, Chi-Chih Wang, School of Medicine, Chung Shan Medical University, Taichung 402, Taiwan
Hsu-Heng Yen, Division of Gastroenterology, Changhua Christian Hospital, Changhua 500, Taiwan
Hsu-Heng Yen, Artificial Intelligence Development Center, Changhua Christian Hospital, Changhua 500, Taiwan
Hsu-Heng Yen, Department of Post-Baccalaureate Medicine, College of Medicine, National Chung Hsing University, Taichung 400, Taiwan
Hui-Yu Tsai, Ming-Hseng Tseng, Department of Medical Informatics, Chung Shan Medical University, Taichung 402, Taiwan
Yu-Kai Huang, Yu-Sin Luo, Department of Internal Medicine, Chung Shan Medical University Hospital, Taichung 402, Taiwan
Edy Kornelius, Department of Endocrinology and Metabolism, Chung-Shan Medical University Hospital, Taichung 402, Taiwan
Wen-Wei Sung, Department of Urology, Chung Shan Medical University Hospital, Taichung 402, Taiwan
Ming-Hseng Tseng, Information Technology Office, Chung Shan Medical University Hospital, Taichung 402, Taiwan
Co-corresponding authors: Chi-Chih Wang and Ming-Hseng Tseng.
Author contributions: Tsai MC and Wang CC were responsible for the conception and design of the study; Yen HH, Tsai HY, Huang YK, Luo YS, Sung WW, and Tseng MH were responsible for the acquisition, analysis, or interpretation of data; Tsai MC and Wang CC were responsible for drafting the manuscript; Edy Kornelius and Lin CC were responsible for critically revising the manuscript for important intellectual content; Tsai HY and Tseng MH were responsible for the statistical analyses; Tseng MH and Sung WW were responsible for obtaining the funding; Tseng MH and Wang CC were responsible for supervising the study; Wang CC and Tseng MH contributed equally to this work as co-corresponding authors. The reasons for designating Wang CC and Tseng MH as co-corresponding authors are as follows. The research was performed as a collaborative effort, and the designation of co-corresponding authorship accurately reflects the distribution of responsibilities and burdens associated with the time and effort required to complete the study and the resultant paper. This also ensures effective communication and management of post-submission matters, ultimately enhancing the paper's quality and reliability. The overall research team encompassed authors with a variety of expertise and this also promotes the most comprehensive and in-depth examination of the research topic, ultimately enriching readers' understanding by offering various expert perspectives. Wang CC contributed to the study design, endoscopic image collection, and endoscopic image interpretation while Tseng MH constructed the AI model. The choice of these researchers as co-corresponding authors acknowledges and respects this equal contribution, while recognizing the spirit of teamwork and collaboration of this study. In summary, we believe that designating Wang CC and Tseng MH as co-corresponding authors of is fitting for our manuscript as it accurately reflects our team's collaborative spirit, equal contributions, and diversity.
Institutional review board statement: The collection of clinical data was reviewed and approved by the institutional review board (IRB) with IRB number CS1–20075 and conducted under IRB regulations to ensure the rights and welfare of the participants.
Informed consent statement: The institutional review board (IRB) has agreed to waive informed consent.
Conflict-of-interest statement: The authors have no conflicts of interest to declare.
Data sharing statement: Dataset available from the corresponding author.
Open-Access: This article is an open-access article that was selected by an in-house editor and fully peer-reviewed by external reviewers. It is distributed in accordance with the Creative Commons Attribution NonCommercial (CC BY-NC 4.0) license, which permits others to distribute, remix, adapt, build upon this work non-commercially, and license their derivative works on different terms, provided the original work is properly cited and the use is non-commercial. See:
https://creativecommons.org/Licenses/by-nc/4.0/ Corresponding author: Chi-Chih Wang, MD, PhD, Associate Professor, Director, Division of Gastroenterology and Hepatology, Department of Internal Medicine, Chung Shan Medical University Hospital, No. 110 Sec. 1, Jianguo N. Rd., South Dist., Taichung 402, Taiwan. bananaudwang@gmail.com
Received: September 3, 2023
Peer-review started: September 3, 2023
First decision: November 1, 2023
Revised: November 13, 2023
Accepted: December 12, 2023
Article in press: December 12, 2023
Published online: December 28, 2023
BACKGROUND
Barrett’s esophagus (BE), which has increased in prevalence worldwide, is a precursor for esophageal adenocarcinoma. Although there is a gap in the detection rates between endoscopic BE and histological BE in current research, we trained our artificial intelligence (AI) system with images of endoscopic BE and tested the system with images of histological BE.
AIM
To assess whether an AI system can aid in the detection of BE in our setting.
METHODS
Endoscopic narrow-band imaging (NBI) was collected from Chung Shan Medical University Hospital and Changhua Christian Hospital, resulting in 724 cases, with 86 patients having pathological results. Three senior endoscopists, who were instructing physicians of the Digestive Endoscopy Society of Taiwan, independently annotated the images in the development set to determine whether each image was classified as an endoscopic BE. The test set consisted of 160 endoscopic images of 86 cases with histological results.
RESULTS
Six pre-trained models were compared, and EfficientNetV2B2 (accuracy [ACC]: 0.8) was selected as the backbone architecture for further evaluation due to better ACC results. In the final test, the AI system correctly identified 66 of 70 cases of BE and 85 of 90 cases without BE, resulting in an ACC of 94.37%.
CONCLUSION
Our AI system, which was trained by NBI of endoscopic BE, can adequately predict endoscopic images of histological BE. The ACC, sensitivity, and specificity are 94.37%, 94.29%, and 94.44%, respectively.
Core Tip: The prevalence of Barrett’s esophagus (BE) diagnosed by endoscopy significantly differs from BE diagnosed by histology (7.8% vs 1.3%). Current research showed that image-enhanced endoscopy can only increase the detection ability for dysplasia lesions in BE. Our artificial intelligence prediction system, which was trained by endoscopic BE images with the Olympus narrow-band imaging system, still provided good prediction results for images of histological BE. The accuracy, sensitivity, and specificity are 94.37%, 94.29%, and 94.44%, respectively, in the final test, which indicates that endoscopic BE images have characteristics similar to images of histological BE.
