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
ARTICLE HIGHLIGHTS
Research background
The prevalence of endoscopic Barrett’s esophagus (BE) differs significantly from histological BE. We believe the endoscopic characteristics are similar with endoscopic BE and histological BE.
Research motivation
We want to train an artificial intelligence (AI) system to identified images of BE under endoscopic environments.
Research objectives
To construct an AI system for the detection of endoscopic images of histological BE.
Research methods
Endoscopic narrow-band images of 724 cases, were collected from two medical centers at central Taiwan, with 86 patients having pathological results. Images of endoscopic BE was classified using independent annotation by three senior endoscopists, who were instructing physicians of the Digestive Endoscopy Society of Taiwan. The test set consisted of 160 endoscopic images in 86 histological BE cases.
Research results
EfficientNetV2B2 [accuracy (ACC): 0.85] was selected as the backbone architecture from six training model due to better ACC result. In the final test, the AI system obtained 94.37%, 94.29%, and 94.44%, in ACC, sensitivity, and specificity respectively.
Research conclusions
Our AI prediction system can provide good prediction results after training with images of endoscopic BE.
Research perspectives
Our result implies that images of endoscopic BE share similar characteristics with images of histological BE even in the perspectives of AI system. The gap from endoscopic BE to histological BE maybe comes from biopsy or sampling bias. This opinion needs further prospective studies to confirm. Meanwhile, a better AI prediction system for endoscopic video BE detection is an ongoing task in the near future.
