Deep self-organizing competitive neural network for magnetically controlled capsule endoscopy-based auxiliary diagnosis of clinically significant gastric lesions

doi:10.12998/wjcc.126704

Advanced Search

BPG is committed to discovery and dissemination of knowledge

Home / Archive / Volume 14, Issue 27

This Article

(2)

(0)

(44)

Peer-Review Report of This Article

CrossCheck and Google Search of This Article

Academic Rules and Norms of This Article

Citation of this article

Corresponding Author of This Article

Research Domain of This Article

Article-Type of This Article

Open-Access Policy of This Article

Times Cited Counts in Google of This Article

Journal Information of This Article

Publication Name

World Journal of Clinical Cases

ISSN

2307-8960

Publisher of This Article

Baishideng Publishing Group Inc, 7041 Koll Center Parkway, Suite 160, Pleasanton, CA 94566, USA

Retrospective Study

Copyright: ©Author(s) 2026. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution-NonCommercial (CC BY-NC 4.0) license. No commercial re-use. See permissions. Published by Baishideng Publishing Group Inc.

World J Clin Cases. Sep 26, 2026; 14(27): 126704
Published online Sep 26, 2026. doi: 10.12998/wjcc.126704

Deep self-organizing competitive neural network for magnetically controlled capsule endoscopy-based auxiliary diagnosis of clinically significant gastric lesions

Ying-Ying Song, Chun-Mei Wang, Zhao-Yu Chen, Peng-Jie Xu, Jing Zhang

Ying-Ying Song, Zhao-Yu Chen, Jing Zhang, Department of Gastroenterology, Shanghai Sixth People’s Hospital Affiliated to Shanghai Jiao Tong University School of Medicine, Shanghai 200233, China

Ying-Ying Song, Department of Infectious Diseases, Qingdao Municipal Hospital, Qingdao University, Qingdao 266011, Shandong Province, China

Chun-Mei Wang, Jing Zhang, Department of Gastroenterology, Shanghai Fengxian District Central Hospital, Shanghai Jiaotong University Affiliated Sixth People’s Hospital South Campus, Shanghai 201499, China

Peng-Jie Xu, School of Automation, Qingdao University, Qingdao 266011, Shandong Province, China

Co-corresponding authors: Peng-Jie Xu and Jing Zhang.

Author contributions: Song YY, Xu PJ and Zhang J conceptualized and designed the research; Song YY and Wang CM performed data analysis; Song YY, Xu PJ and Chen ZY drafted the manuscript; and all authors participated in data analysis and interpretation, figure plotting, and comprehensive literature search, prepared and submitted the current version of the manuscript, and have read and approved the final manuscript. Zhang J applied for and obtained the research funding for this project. Both Zhang J and Xu PJ conceptualized, designed, and supervised the whole process of the project. The collaboration between Zhang J and Xu PJ is crucial for the publication of this manuscript and other manuscripts in preparation. Therefore, they serve as co-corresponding authors.

AI contribution statement: The authors used AI-based tools solely for language refinement and submission-related assistance. Study design, data collection, data analysis, model development or training, statistical analysis, generation of results, interpretation of findings, or formulation of scientific conclusions are the authors’ own. The authors take full responsibility for the manuscript.

Supported by Shanghai Municipal Health Commission Seed Program for Medical New Technology Research and Translation, No. 2024ZZ2048; Public Sector Research Project in Fengxian District, Shanghai, No. FXKX-2025-006; Zhejiang University Education Foundation Project, No. 2025-KY-301(K); and Engineering Research Center for Big Data Application in Private Health Medicine of Fujian Universities, Putian University, Putian, Fujian 351100, China, No. MKF202406.

Institutional review board statement: The study was reviewed and approved by the Ethics Committee of Shanghai Sixth People’s Hospital (approval No.2026-YS-391).

Informed consent statement: Written informed consent was obtained from all participants prior to study inclusion.

Conflict-of-interest statement: All authors declare that they have no conflict of interest to disclose.

Data sharing statement: No additional data are available.

Corresponding author: Jing Zhang, Department of Gastroenterology, Shanghai Sixth People’s Hospital Affiliated to Shanghai Jiao Tong University School of Medicine, No. 600 Yishan Road, Shanghai 200233, China. jing5522724@vip.163.com

Received: August 20, 2026
Revised: September 18, 2026
Accepted: October 13, 2026
Published online: September 26, 2026
Processing time: 63 Days and 6.9 Hours

Abstract

BACKGROUND

Magnetically controlled capsule endoscopy (MCCE) is a well-tolerated alternative to invasive gastroscopy, but its diagnostic efficiency and consistency are limited by large data volume and physician-dependent diagnosis.

AIM

To construct a deep self-organizing competitive neural network (DSomNN) to enhance MCCE-based auxiliary diagnosis of clinically significant gastric lesions (CSGL).

METHODS

A total of 7425 MCCE patients were initially enrolled; after exclusion of 35 patients according to predefined inclusion/exclusion criteria, 7390 patients were analyzed. Demographic data, chief complaints, MCCE findings, and five key gastric lesions annotated by gastroenterologists were used for model training. The primary prediction endpoint is CSGL, defined as gastric cancer, intestinal metaplasia, atrophic gastritis, gastric ulcer, or gastric polyps. The DSomNN extracts variable associations and establishes CSGL risk criteria.

RESULTS

Results show close correlations between CSGL and clinical data. In the validation/test set, the error rate is < 5%. In conclusion, the DSomNN performs well in CSGL risk prediction, addresses MCCE limitations, and serves as a valuable auxiliary tool for clinical gastroenterology decision-making.

CONCLUSION

This study developed a DSomNN, integrating global vectors for word representation, Text convolutional neural network-based deep feature extraction, and self-organizing competitive learning for the auxiliary identification of CSGL using demographic characteristics, clinical symptoms, and MCCE findings.

Keywords: Auxiliary diagnosis; Magnetically controlled capsule endoscopy; Deep self-organizing competitive neural network; Text convolutional neural network; Clinically significant gastric lesions

Core Tip: Magnetically controlled capsule endoscopy (MCCE) is a well-tolerated alternative to invasive gastroscopy, but its diagnostic efficiency and consistency are limited by large data volume and physician-dependent diagnosis. This study constructs a deep self-organizing competitive neural network (DSomNN) to enhance MCCE-based diagnostic accuracy and efficiency, and the DSomNN performs well in gastric cancer risk prediction, addresses MCCE limitations, and serves as a valuable auxiliary tool for clinical gastroenterology decision-making.