Zhou JX, Yang Z, Xi DH, Dai SJ, Feng ZQ, Li JY, Xu W, Wang H. Enhanced segmentation of gastrointestinal polyps from capsule endoscopy images with artifacts using ensemble learning. World J Gastroenterol 2022; 28(41): 5931-5943 [PMID: 36405108 DOI: 10.3748/wjg.v28.i41.5931]
Corresponding Author of This Article
Hong Wang, MD, Chief Physician, Department of Gastroenterology and Hepatology, Guangzhou First People’s Hospital, No. 1 Panfu Road, Yuexiu District, Guangzhou 510180, Guangdong Province, China. wong.hong@163.com
Research Domain of This Article
Gastroenterology & Hepatology
Article-Type of This Article
Retrospective Study
Open-Access Policy of This Article
This article is an open-access article which was selected by an in-house editor and fully peer-reviewed by external reviewers. It is distributed in accordance with the Creative Commons Attribution Non Commercial (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: http://creativecommons.org/licenses/by-nc/4.0/
World J Gastroenterol. Nov 7, 2022; 28(41): 5931-5943 Published online Nov 7, 2022. doi: 10.3748/wjg.v28.i41.5931
Enhanced segmentation of gastrointestinal polyps from capsule endoscopy images with artifacts using ensemble learning
Jun-Xiao Zhou, Zhan Yang, Ding-Hao Xi, Shou-Jun Dai, Zhi-Qiang Feng, Jun-Yan Li, Wei Xu, Hong Wang
Jun-Xiao Zhou, Shou-Jun Dai, Zhi-Qiang Feng, Jun-Yan Li, Hong Wang, Department of Gastroenterology and Hepatology, Guangzhou First People’s Hospital, Guangzhou 510180, Guangdong Province, China
Zhan Yang, Ding-Hao Xi, Wei Xu, School of Information, Renmin University of China, Beijing 100872, China
Author contributions: Zhou JX collected and compiled the data; Yang Z and Xi DH were responsible for coding the model; Zhou JX, Yang Z, and Li J drafted the manuscript; Dai SJ, Feng ZQ, and Wang H performed the capsule endoscopy examinations and reviewed the images; Xu W and Wang H contributed to the study design and manuscript writing.
Institutional review board statement: This study was reviewed and approved by the Ethics Committee of the Guangzhou First People’s Hospital.
Informed consent statement: Patients were not required to give informed consent to the study because the analysis used anonymous clinical data that were obtained after each patient agreed to treatment by written consent.
Conflict-of-interest statement: All the authors report no relevant conflicts of interest for this article.
Data sharing statement: No additional data are available.
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: Hong Wang, MD, Chief Physician, Department of Gastroenterology and Hepatology, Guangzhou First People’s Hospital, No. 1 Panfu Road, Yuexiu District, Guangzhou 510180, Guangdong Province, China. wong.hong@163.com
Received: June 29, 2022 Peer-review started: June 29, 2022 First decision: August 19, 2022 Revised: August 31, 2022 Accepted: October 19, 2022 Article in press: October 19, 2022 Published online: November 7, 2022 Processing time: 127 Days and 14.1 Hours
ARTICLE HIGHLIGHTS
Research background
Artificial intelligence (AI)-assisted capsule endoscopy (CE) can improve the detection rate of gastrointestinal polyps and reduce the incidence of gastrointestinal cancer.
Research motivation
Most previous studies ignored the serious impact of the existence of a large number of artifacts in the real world on the detection ability of existing AI models for polyps in CE images.
Research objectives
In this study, semantic segmentation and ensemble learning methods were combined to analyze polyp images of CE with artifacts, proving that ensemble learning methods can better solve the impact of artifacts in the real world.
Research methods
This study retrospectively analyzed CE images of patients at our research center from January 2016 to December 2019. Polyp images with artifacts were selected and randomly divided into a training set (195 images), a validation set (41 images), and a test set (41 images). Further validation was performed on two public datasets with good background quality.
Research results
Compared with the corresponding optimal base model, intersection over union and dice are improved by 0.08%-7.01% and 0.61%-4.93%, respectively. For public datasets with good background quality, the segmentation performance of most ensemble learning models was better than that of a single model.
Research conclusions
The ensemble learning method can improve the performance of semantic segmentation of polyps in CE images with artifacts.
Research perspectives
We will validate other digestive tract lesions and other medical images and perform real-time detection during endoscopic and surgical procedures.
