Retrospective Study
Copyright ©The Author(s) 2025. Published by Baishideng Publishing Group Inc. All rights reserved.
World J Gastroenterol. Jun 7, 2025; 31(21): 107601
Published online Jun 7, 2025. doi: 10.3748/wjg.v31.i21.107601
Classification of pediatric video capsule endoscopy images for small bowel abnormalities using deep learning models
Yi-Hsuan Huang, Qian Lin, Xin-Yan Jin, Chih-Yi Chou, Jia-Jie Wei, Jiao Xing, Hong-Mei Guo, Zhi-Feng Liu, Yan Lu
Yi-Hsuan Huang, Qian Lin, Jia-Jie Wei, Jiao Xing, Hong-Mei Guo, Zhi-Feng Liu, Yan Lu, Department of Gastroenterology, Children’s Hospital of Nanjing Medical University, Nanjing 210008, Jiangsu Province, China
Xin-Yan Jin, School of Electronic Science and Engineering, Nanjing University, Nanjing 210023, Jiangsu Province, China
Chih-Yi Chou, College of Medicine, National Taiwan University, Taipei 100, Taiwan
Co-first authors: Yi-Hsuan Huang and Qian Lin.
Co-corresponding authors: Zhi-Feng Liu and Yan Lu.
Author contributions: Huang YH and Lin Q performed the study, collected the data, carried out the initial analyses, and drafted the original manuscript; Jin XY performed the analysis and interpretation of the data, trained the deep learning models, and revised the manuscript for the intellectual session; Chou CY revised and edited each iteration of the manuscript; Wei JJ, Xing J, and Guo HM collected and interpreted the data; Lu Y and Liu ZF contributed to the design of the study, and critically reviewed and revised the manuscript; All authors have read and approve the final manuscript.
Institutional review board statement: The study protocol was reviewed and approved by the Institutional Review Board of the Children’s Hospital of Nanjing Medical University (No. 202409001-1).
Informed consent statement: The need for patient consent was waived due to the retrospective nature of the study.
Conflict-of-interest statement: The authors declare that they have no conflict of interest.
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: Yan Lu, PhD, Associate Research Scientist, Department of Gastroenterology, Children’s Hospital of Nanjing Medical University, No. 8 Jiangdong South Road, Jianye District, Nanjing 210008, Jiangsu Province, China. luyan_cpu@163.com
Received: March 30, 2025
Revised: April 14, 2025
Accepted: May 19, 2025
Published online: June 7, 2025
Processing time: 68 Days and 22.2 Hours
Core Tip

Core Tip: This study addresses the challenges clinicians face in manually reviewing video capsule endoscopy (VCE) images, a process that is both time-consuming and labor-intensive. To alleviate this burden, we utilize deep learning models, including DenseNet121, Visual geometry group-16, ResNet50, and vision transformer, to automatically classify small bowel lesions in pediatric VCE images. Our models effectively distinguished between normal tissue, erosions/erythema, ulcers, and polyps with high accuracy. This approach significantly enhances the efficiency and accuracy of diagnosing lesions in pediatric VCE, offering a promising tool for clinical applications.