Huang YH, Lin Q, Jin XY, Chou CY, Wei JJ, Xing J, Guo HM, Liu ZF, Lu Y. Classification of pediatric video capsule endoscopy images for small bowel abnormalities using deep learning models. World J Gastroenterol 2025; 31(21): 107601 [DOI: 10.3748/wjg.v31.i21.107601]
Corresponding Author of This Article
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
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. 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
Abstract
BACKGROUND
Video capsule endoscopy (VCE) is a noninvasive technique used to examine small bowel abnormalities in both adults and children. However, manual review of VCE images is time-consuming and labor-intensive, making it crucial to develop deep learning methods to assist in image analysis.
AIM
To employ deep learning models for the automatic classification of small bowel lesions using pediatric VCE images.
METHODS
We retrospectively analyzed VCE images from 162 pediatric patients who underwent VCE between January 2021 and December 2023 at the Children's Hospital of Nanjing Medical University. A total of 2298 high-resolution images were extracted, including normal mucosa and lesions (erosions/erythema, ulcers, and polyps). The images were split into training and test datasets in a 4:1 ratio. Four deep learning models: DenseNet121, Visual geometry group-16, ResNet50, and vision transformer were trained using 5-fold cross-validation, with hyperparameters adjusted for optimal classification performance. The models were evaluated based on accuracy, precision, recall, F1-score, and area under the receiver operating curve (AU-ROC). Lesion visualization was performed using gradient-weighted class activation mapping.
RESULTS
Abdominal pain was the most common indication for VCE, accounting for 62% of cases, followed by diarrhea, vomiting, and gastrointestinal bleeding. Abnormal lesions were detected in 93 children, with 38 diagnosed with inflammatory bowel disease. Among the deep learning models, DenseNet121 and ResNet50 demonstrated excellent classification performance, achieving accuracies of 90.6% [95% confidence interval (CI): 89.2-92.0] and 90.5% (95%CI: 89.9-91.2), respectively. The AU-ROC values for these models were 93.7% (95%CI: 92.9-94.5) for DenseNet121 and 93.4% (95%CI: 93.1-93.8) for ResNet50.
CONCLUSION
Our deep learning-based diagnostic tool developed in this study effectively classified lesions in pediatric VCE images, contributing to more accurate diagnoses and increased diagnostic efficiency.
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.
