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 Gastroenterol. Aug 14, 2026; 32(30): 121592
Published online Aug 14, 2026. doi: 10.3748/wjg.121592
Published online Aug 14, 2026. doi: 10.3748/wjg.121592
Deep-learning-based object detection of pelvic autonomic nerves during total mesorectal excision
Qiao Zhang, Jin Li, Zhi-Fen Chen, Xing-Rong Lu, Department of Colorectal Surgery, Fujian Medical University Union Hospital, Fuzhou 350001, Fujian Province, China
Qiao Zhang, Tao Meng, Department of Gastrointestinal Surgery, Bariatric & Metabolic Surgery and Hernia Surgery, The First Affiliated Hospital of Henan Medical University, Xinxiang 453100, Henan Province, China
Xue-Zhi Zhou, The School of Medical Engineering, Henan Medical University, Xinxiang 453003, Henan Province, China
Author contributions: Zhang Q, Zhou XZ, and Lu XR contributed to conception and design; Meng T and Chen ZF provided administrative support; Zhang Q, Li J, and Lu XR supplied the study materials or surgical videos; Zhang Q, Meng T, and Chen ZF contributed to data collection and assembly; Li J, Zhou XZ, and Lu XR contributed to data analysis and interpretation; all authors participated in manuscript writing and gave final approval of the manuscript.
AI contribution statement: The authors declare that no AI tools were used in the development or writing of this manuscript and take full responsibility for its integrity, accuracy, and originality.
Supported by The Natural Science Foundation of Fujian Province, No. 2023J01122895.
Institutional review board statement: This study was approved by the Ethics Committee of Fujian Medical University Union Hospital (approval No. 2024KY150) and conducted in accordance with the Declaration of Helsinki (2013 revision).
Informed consent statement: Informed consent was waived due to the retrospective and anonymized nature of the data.
Conflict-of-interest statement: The authors declare that they have no conflict of interest.
Data sharing statement: The data supporting the findings of this study are available from Fujian Medical University Union Hospital. Restrictions apply to the availability of these data, which are not publicly accessible. However, upon reasonable request and with the permission of Fujian Medical University Union Hospital, the relevant data can be obtained from the corresponding author.
Corresponding author: Xing-Rong Lu, MD, Professor, Department of Colorectal Surgery, Fujian Medical University Union Hospital, No. 29 Xinquan Road, Fuzhou 350001, Fujian Province, China. lynxlxr18@163.com
Received: March 30, 2026
Revised: April 22, 2026
Accepted: June 3, 2026
Published online: August 14, 2026
Processing time: 117 Days and 19.8 Hours
Revised: April 22, 2026
Accepted: June 3, 2026
Published online: August 14, 2026
Processing time: 117 Days and 19.8 Hours
Core Tip
Core Tip: In this study, a deep learning model was developed to recognize five categories of pelvic autonomic nerves during total mesorectal excision. The model was trained, validated and tested on surgical video images, and its performance was compared with surgeons at different levels. The model achieved precision and speed comparable to senior surgeons, with consistent pathological confirmation of all 7 sampled nerve specimens. Ultimately, this model was confirmed to be reliable and may assist nerve preservation and shorten the learning curve for junior surgeons.