Clinical and Translational Research
Copyright ©The Author(s) 2021. Published by Baishideng Publishing Group Inc. All rights reserved.
World J Gastroenterol. Aug 21, 2021; 27(31): 5232-5246
Published online Aug 21, 2021. doi: 10.3748/wjg.v27.i31.5232
Establishment and validation of a computer-assisted colonic polyp localization system based on deep learning
Sheng-Bing Zhao, Wei Yang, Shu-Ling Wang, Peng Pan, Run-Dong Wang, Xin Chang, Zhong-Qian Sun, Xing-Hui Fu, Hong Shang, Jian-Rong Wu, Li-Zhu Chen, Jia Chang, Pu Song, Ying-Lei Miao, Shui-Xiang He, Lin Miao, Hui-Qing Jiang, Wen Wang, Xia Yang, Yuan-Hang Dong, Han Lin, Yan Chen, Jie Gao, Qian-Qian Meng, Zhen-Dong Jin, Zhao-Shen Li, Yu Bai
Sheng-Bing Zhao, Changhai Hospital, Second Military Medical University/Naval Medical University, Shanghai 200433, China
Wei Yang, Zhong-Qian Sun, Xing-Hui Fu, Hong Shang, Tencent AI Lab, National Open Innovation Platform for Next Generation Artificial Intelligence on Medical Imaging, Shenzhen 518063, Guangdong Province, China
Shu-Ling Wang, Peng Pan, Run-Dong Wang, Xin Chang, Yuan-Hang Dong, Han Lin, Yan Chen, Jie Gao, Qian-Qian Meng, Zhen-Dong Jin, Zhao-Shen Li, Yu Bai, Department of Gastroenterology, Changhai Hospital, Second Military Medical University/Naval Medical University, Shanghai 200433, China
Jian-Rong Wu, Li-Zhu Chen, Jia Chang, Pu Song, Tencent Healthcare (Shenzhen) Co. LTD., Shenzhen 518063, Guangdong Province, China
Ying-Lei Miao, Department of Gastroenterology, The First Affiliated Hospital of Kunming Medical University, Kunming 650000, Yunnan Province, China
Shui-Xiang He, Department of Gastroenterology, The First Affiliated Hospital of Xi'an Jiaotong University, Xi'an 710061, Shaanxi Province, China
Lin Miao, Institute of Digestive Endoscopy and Medical Center for Digestive Disease, The Second Affiliated Hospital of Nanjing Medical University, Nanjing 210011, Jiangsu Province, China
Hui-Qing Jiang, Department of Gastroenterology, The Second Hospital of Hebei Medical University, Hebei Key Laboratory of Gastroenterology, Hebei Institute of Gastroenterology, Shijiazhuang 050000, Hebei Province, China
Wen Wang, Department of Gastroenterology, 900th Hospital of Joint Logistics Support Force, Fuzhou 350025, Fujian Province, China
Xia Yang, Department of Gastroenterology, No. 905 Hospital of The Chinese People's Liberation Army, Shanghai 200050, China
Author contributions: Zhao SB, Yang W and Wang SL contributed equally to this work; Zhao SB, Yang W, Li ZS and Bai Y contributed to the study concept and design; Zhao SB, Wang RD, Chang X, Miao YL, He SX, Miao L, Jiang HQ, Wang W, Dong YH, Lin H, Chen Y, Gao J, Meng QQ, Chen LZ, Chang J and Song P contributed to the acquisition of data; Zhao SB, Yang W, Wang SL, Pan P, Sun ZQ, Fu XH and Shang H contributed to the analysis and interpretation of data; Zhao SB contributed to the drafting of the manuscript; Zhao SB, Bai Y, Yang X, Wang SL and Pan P contributed to the critical revision of the manuscript for important intellectual content; Zhao SB and Bai Y contributed to the statistical analysis; Li ZS, Bai Y and Chen LZ contributed to the administrative, technical, or material support; Jin ZD, Li ZS and Bai Y contributed to the study supervision.
Supported by the National Key R&D Program of China, No. 2018YFC1313103; the National Natural Science Foundation of China, No. 81670473 and No. 81873546; the “Shu Guang” Project of Shanghai Municipal Education Commission and Shanghai Education Development Foundation, No. 19SG30; and the Key Area Research and Development Program of Guangdong Province, China, No.2018B010111001.
Institutional review board statement: The study was reviewed and approved by the ethics committees of Changhai Hospital.
Clinical trial registration statement: ClinicalTrials.gov, identifier NCT03761771.
Informed consent statement: Written informed consent was provided for all participants.
Conflict-of-interest statement: Wu JR, Chen LZ, Chang J and Song P were staff of Tencent Healthcare (Shenzhen) Co. LTD, which supported the work with provision of research grants, prototype software, prototype PC and GPU units. The other authors have no conflicts of interest to declare. The sponsor had no involvement in the design and conduct of the study; the collection, management, analysis, and interpretation of the data; the preparation, review, and approval of the manuscript; or the decision to submit the manuscript for publication.
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: http://creativecommons.org/Licenses/by-nc/4.0/
Corresponding author: Yu Bai, MD, PhD, Associate Professor, Department of Gastroenterology, Changhai Hospital, Second Military Medical University/Naval Medical University, No. 168 Changhai Road, Shanghai 200433, China. baiyu1998@hotmail.com
Received: February 19, 2021
Peer-review started: February 19, 2021
First decision: March 28, 2021
Revised: April 10, 2021
Accepted: July 20, 2021
Article in press: July 20, 2021
Published online: August 21, 2021
Processing time: 180 Days and 5.1 Hours
Abstract
BACKGROUND

Artificial intelligence in colonoscopy is an emerging field, and its application may help colonoscopists improve inspection quality and reduce the rate of missed polyps and adenomas. Several deep learning-based computer-assisted detection (CADe) techniques were established from small single-center datasets, and unrepresentative learning materials might confine their application and generalization in wide practice. Although CADes have been reported to identify polyps in colonoscopic images and videos in real time, their diagnostic performance deserves to be further validated in clinical practice.

AIM

To train and test a CADe based on multicenter high-quality images of polyps and preliminarily validate it in clinical colonoscopies.

METHODS

With high-quality screening and labeling from 55 qualified colonoscopists, a dataset consisting of over 71000 images from 20 centers was used to train and test a deep learning-based CADe. In addition, the real-time diagnostic performance of CADe was tested frame by frame in 47 unaltered full-ranged videos that contained 86 histologically confirmed polyps. Finally, we conducted a self-controlled observational study to validate the diagnostic performance of CADe in real-world colonoscopy with the main outcome measure of polyps per colonoscopy in Changhai Hospital.

RESULTS

The CADe was able to identify polyps in the test dataset with 95.0% sensitivity and 99.1% specificity. For colonoscopy videos, all 86 polyps were detected with 92.2% sensitivity and 93.6% specificity in frame-by-frame analysis. In the prospective validation, the sensitivity of CAD in identifying polyps was 98.4% (185/188). Folds, reflections of light and fecal fluid were the main causes of false positives in both the test dataset and clinical colonoscopies. Colonoscopists can detect more polyps (0.90 vs 0.82, P < 0.001) and adenomas (0.32 vs 0.30, P = 0.045) with the aid of CADe, particularly polyps < 5 mm and flat polyps (0.65 vs 0.57, P < 0.001; 0.74 vs 0.67, P = 0.001, respectively). However, high efficacy is not realized in colonoscopies with inadequate bowel preparation and withdrawal time (P = 0.32; P = 0.16, respectively).

CONCLUSION

CADe is feasible in the clinical setting and might help endoscopists detect more polyps and adenomas, and further confirmation is warranted.

Keywords: Computer-assisted detection; Artificial intelligence; Deep learning; Colonoscopy; Clinical validation; Colorectal polyp

Core Tip: Our study indicated that the deep learning-based computer-assisted detection system trained from the dataset consisting of the largest number of polyps achieved high diagnostic performance on the test dataset of images, colonoscopy videos and clinical validation. This system might aid colonoscopists in finding more polyps and adenomas and deserves to be further validated in multicenter randomized trials.