Retrospective Study
Copyright ©The Author(s) 2023. Published by Baishideng Publishing Group Inc. All rights reserved.
World J Gastroenterol. Jan 21, 2023; 29(3): 536-548
Published online Jan 21, 2023. doi: 10.3748/wjg.v29.i3.536
Magnetic resonance imaging-based deep learning model to predict multiple firings in double-stapled colorectal anastomosis
Zheng-Hao Cai, Qun Zhang, Zhan-Wei Fu, Abraham Fingerhut, Jing-Wen Tan, Lu Zang, Feng Dong, Shu-Chun Li, Shi-Lin Wang, Jun-Jun Ma
Zheng-Hao Cai, Zhan-Wei Fu, Abraham Fingerhut, Lu Zang, Feng Dong, Shu-Chun Li, Jun-Jun Ma, Department of General Surgery, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai 200025, China
Zheng-Hao Cai, Shanghai Minimally Invasive Surgery Center, Shanghai 200025, China
Qun Zhang, Shi-Lin Wang, School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai 201100, China
Jing-Wen Tan, Department of Radiology, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai 200025, China
Author contributions: Cai ZH, Zhang Q, Fu ZW, Fingerhut A, Tan JW, Zang L, Dong F, Li SC, Wang SL, Ma JJ contributed to the study conception and design; Cai ZH, Zhang Q, Zang L, Dong F, Li SC, Tan JW, and Ma JJ contributed to material preparation; Cai ZH, Fu ZW and Tan JW contributed to data collection; Fu ZW, Fingerhut A, and Li SC contributed to data analysis; The first draft of the manuscript was written by Cai ZH, Zhang Q, Wang SL, and Fu Z; The final version and revisions of the manuscript were performed by Cai ZH, Zang L, Tan JW, Zhang Q, Li SC, Ma JJ, Fu ZW, and Fingerhut A; All authors read and approved the final manuscript and accept to be responsible for the contents.
Supported by Shanghai Jiaotong University, No. YG2019QNB24.
Institutional review board statement: This study was reviewed and approved by Ruijin Hospital Ethics Committee (Approval No. 2019-82).
Informed consent statement: Informed consent was waived by Ruijin Hospital Ethics committee due to the retrospective nature of the study. 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: Technical appendix, statistical code, and dataset available from the corresponding author at marsnew1997@163.com. Consent was not obtained but the presented data are anonymized and risk of identification is low.
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: Jun-Jun Ma, MD, Doctor, Department of General Surgery, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, No. 197, Ruijin No. 2 Rd, Shanghai 200025, China. marsnew1997@163.com
Received: October 9, 2022
Peer-review started: October 9, 2022
First decision: November 18, 2022
Revised: November 29, 2022
Accepted: January 3, 2023
Article in press: January 3, 2023
Published online: January 21, 2023
Processing time: 95 Days and 6.6 Hours
ARTICLE HIGHLIGHTS
Research background

The need for multiple (≥ 3) linear stapler firings during double stapling technique (DST) is associated with an increased risk of anastomotic leakage (AL) after laparoscopic low anterior resection (LAR).

Research motivation

Current methods using clinical data cannot predict precisely the use of ≥ 3 linear stapler firings before surgery.

Research objectives

This study aimed to develop a pelvic magnetic resonance imaging (MRI)-based deep learning model to predict the multiple firings during DST anastomosis.

Research methods

Clinical data and 9476 MR images from 328 mid-low rectal cancer patients undergoing LAR with DST anastomosis were retrospectively collected. A pure-image model and a clinical-image integrated model were constructed using image-reading deep learning technologies, respectively.

Research results

The clinical-image integrated model showed better predictive performance compared with the clinical model and the pure image model with the highest accuracy (94.1%) and area under the curve (0.88).

Research conclusions

Our deep learning model might help determine the anastomosis strategy for mid-low rectal cancer patients (suggesting not to perform the DST when the risk for ≥ 3 linear stapler firings is high).

Research perspectives

The clinical value of this clinical-image integrated model will be validated in further prospective studies. The incidence of AL is expected to be decreased with this strategy.