Retrospective Study
Copyright ©The Author(s) 2023. Published by Baishideng Publishing Group Inc. All rights reserved.
World J Gastroenterol. Feb 7, 2023; 29(5): 879-889
Published online Feb 7, 2023. doi: 10.3748/wjg.v29.i5.879
Convolutional neural network-based segmentation network applied to image recognition of angiodysplasias lesion under capsule endoscopy
Ye Chu, Fang Huang, Min Gao, Duo-Wu Zou, Jie Zhong, Wei Wu, Qi Wang, Xiao-Nan Shen, Ting-Ting Gong, Yuan-Yi Li, Li-Fu Wang
Ye Chu, Duo-Wu Zou, Jie Zhong, Wei Wu, Qi Wang, Xiao-Nan Shen, Ting-Ting Gong, Li-Fu Wang, Department of Gastroenterology, Shanghai Jiao Tong University School of Medicine, Ruijin Hospital, Shanghai 200025, China
Fang Huang, Min Gao, Yuan-Yi Li, Technology Platform Department, Jinshan Science & Technology (Group) Co., Ltd., Chongqing 401120, China
Author contributions: Chu Y read and reviewed capsule endoscopy imagines, and participated in the design, writing, and revision of the manuscript; Huang F performed AI algorithm research, designed the segmentation recognition protocol, and verified the algorithm; Gao M organized the experimental results, visualized the experiment, and wrote the draft of the paper; Zou DW designed and revised the protocol of the paper; Zhong J reviewed capsule endoscopy images; Wu W and Wang Q participated in the reading of CE and preparation of the material; Shen XN and Gong TT partial writing of the manuscript; Li YY contributed to the coding and debugging of interface between algorithm and software; Wang LF designed and modified the protocol of the paper.
Supported by the Chongqing Technological Innovation and Application Development Project, Key Technologies and Applications of Cross Media Analysis and Reasoning, No. cstc2019jscx-zdztzxX0037.
Institutional review board statement: The study was reviewed and approved by the Ruijin Hospital Ethics Committee, Shanghai Jiao Tong University School of Medicine [the certification number was (2017) provisional ethics review No. 138].
Informed consent statement: The informed consent statement was waived by the Ruijin Hospital Ethics Committee.
Conflict-of-interest statement: The authors declare that they have no competing interests.
Data sharing statement: Technical appendix, statistical code, and dataset available from the corresponding author at lifuwang@sjtu.edu.cn. Participants gave informed consent for data sharing.
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: Li-Fu Wang, MD, PhD, Chief Physician, Professor, Department of Gastroenterology, Shanghai Jiao Tong University School of Medicine, Ruijin Hospital, No. 197 Ruijin Er Road, Shanghai 200025, China. lifuwang@sjtu.edu.cn
Received: September 25, 2022
Peer-review started: September 25, 2022
First decision: October 18, 2022
Revised: November 26, 2022
Accepted: January 11, 2023
Article in press: January 11, 2023
Published online: February 7, 2023
Abstract
BACKGROUND

Small intestinal vascular malformations (angiodysplasias) are common causes of small intestinal bleeding. While capsule endoscopy has become the primary diagnostic method for angiodysplasia, manual reading of the entire gastrointestinal tract is time-consuming and requires a heavy workload, which affects the accuracy of diagnosis.

AIM

To evaluate whether artificial intelligence can assist the diagnosis and increase the detection rate of angiodysplasias in the small intestine, achieve automatic disease detection, and shorten the capsule endoscopy (CE) reading time.

METHODS

A convolutional neural network semantic segmentation model with a feature fusion method, which automatically recognizes the category of vascular dysplasia under CE and draws the lesion contour, thus improving the efficiency and accuracy of identifying small intestinal vascular malformation lesions, was proposed. Resnet-50 was used as the skeleton network to design the fusion mechanism, fuse the shallow and depth features, and classify the images at the pixel level to achieve the segmentation and recognition of vascular dysplasia. The training set and test set were constructed and compared with PSPNet, Deeplab3+, and UperNet.

RESULTS

The test set constructed in the study achieved satisfactory results, where pixel accuracy was 99%, mean intersection over union was 0.69, negative predictive value was 98.74%, and positive predictive value was 94.27%. The model parameter was 46.38 M, the float calculation was 467.2 G, and the time length to segment and recognize a picture was 0.6 s.

CONCLUSION

Constructing a segmentation network based on deep learning to segment and recognize angiodysplasias lesions is an effective and feasible method for diagnosing angiodysplasias lesions.

Keywords: Artificial intelligence, Image segmentation, Capsule endoscopy, Angiodysplasias

Core Tip: Small intestinal vascular malformation (vascular dysplasia) is a common cause of small intestinal bleeding. Herein, we proposed a semantic recognition segmentation network to recognize small intestinal vascular malformation lesions. This method can assist doctors in identifying lesions, improving the detection rate of intestinal vascular dysplasia, realizing automatic disease detection, and shortening the capsule endoscopy reading time.