Retrospective Study
Copyright ©The Author(s) 2022. Published by Baishideng Publishing Group Inc. All rights reserved.
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
Abstract
BACKGROUND

Endoscopy artifacts are widespread in real capsule endoscopy (CE) images but not in high-quality standard datasets.

AIM

To improve the segmentation performance of polyps from CE images with artifacts based on ensemble learning.

METHODS

We collected 277 polyp images with CE artifacts from 5760 h of videos from 480 patients at Guangzhou First People’s Hospital from January 2016 to December 2019. Two public high-quality standard external datasets were retrieved and used for the comparison experiments. For each dataset, we randomly segmented the data into training, validation, and testing sets for model training, selection, and testing. We compared the performance of the base models and the ensemble model in segmenting polyps from images with artifacts.

RESULTS

The performance of the semantic segmentation model was affected by artifacts in the sample images, which also affected the results of polyp detection by CE using a single model. The evaluation based on real datasets with artifacts and standard datasets showed that the ensemble model of all state-of-the-art models performed better than the best corresponding base learner on the real dataset with artifacts. Compared with the corresponding optimal base learners, the intersection over union (IoU) and dice of the ensemble learning model increased to different degrees, ranging from 0.08% to 7.01% and 0.61% to 4.93%, respectively. Moreover, in the standard datasets without artifacts, most of the ensemble models were slightly better than the base learner, as demonstrated by the IoU and dice increases ranging from -0.28% to 1.20% and -0.61% to 0.76%, respectively.

CONCLUSION

Ensemble learning can improve the segmentation accuracy of polyps from CE images with artifacts. Our results demonstrated an improvement in the detection rate of polyps with interference from artifacts.

Keywords: Artifacts; Capsule endoscopy; Polyps; Ensemble learning; Segmentation; Robustness

Core Tip: Artificial intelligence has been widely used in capsule endoscopy to detect gastrointestinal polyps; however, it is often impaired by artifacts in clinical practice. At present, clear and high-quality images without artifacts are usually selected for research, which has not yet produced practical assistance regarding artifact interference. In this study, we demonstrated that ensemble learning can improve the segmentation performance of polyps under the interference of artifacts, which has a significant auxiliary role in the detection of polyps in clinical practice.