Endoscopy 2024; 56(04): 260-270
DOI: 10.1055/a-2189-7036
Original article

A real-time deep learning-based system for colorectal polyp size estimation by white-light endoscopy: development and multicenter prospective validation

Jing Wang
1   Department of Gastroenterology, Renmin Hospital of Wuhan University, Wuhan, China (Ringgold ID: RIN117921)
2   Hubei Provincial Clinical Research Center for Digestive Disease Minimally Invasive Incision, Renmin Hospital of Wuhan University, Wuhan, China (Ringgold ID: RIN117921)
3   Hubei Key Laboratory of Digestive System, Renmin Hospital of Wuhan University, Wuhan, China (Ringgold ID: RIN117921)
4   Engineering Research Center for Artificial Intelligence Endoscopy Interventional Treatment of Hubei Province, Renmin Hospital of Wuhan University, Wuhan, China (Ringgold ID: RIN117921)
,
Ying Li
5   Department of Endoscopy, Eighth Hospital of Wuhan, Wuhan, China
,
Boru Chen
1   Department of Gastroenterology, Renmin Hospital of Wuhan University, Wuhan, China (Ringgold ID: RIN117921)
2   Hubei Provincial Clinical Research Center for Digestive Disease Minimally Invasive Incision, Renmin Hospital of Wuhan University, Wuhan, China (Ringgold ID: RIN117921)
3   Hubei Key Laboratory of Digestive System, Renmin Hospital of Wuhan University, Wuhan, China (Ringgold ID: RIN117921)
4   Engineering Research Center for Artificial Intelligence Endoscopy Interventional Treatment of Hubei Province, Renmin Hospital of Wuhan University, Wuhan, China (Ringgold ID: RIN117921)
,
Du Cheng
1   Department of Gastroenterology, Renmin Hospital of Wuhan University, Wuhan, China (Ringgold ID: RIN117921)
2   Hubei Provincial Clinical Research Center for Digestive Disease Minimally Invasive Incision, Renmin Hospital of Wuhan University, Wuhan, China (Ringgold ID: RIN117921)
3   Hubei Key Laboratory of Digestive System, Renmin Hospital of Wuhan University, Wuhan, China (Ringgold ID: RIN117921)
4   Engineering Research Center for Artificial Intelligence Endoscopy Interventional Treatment of Hubei Province, Renmin Hospital of Wuhan University, Wuhan, China (Ringgold ID: RIN117921)
,
Fei Liao
1   Department of Gastroenterology, Renmin Hospital of Wuhan University, Wuhan, China (Ringgold ID: RIN117921)
2   Hubei Provincial Clinical Research Center for Digestive Disease Minimally Invasive Incision, Renmin Hospital of Wuhan University, Wuhan, China (Ringgold ID: RIN117921)
3   Hubei Key Laboratory of Digestive System, Renmin Hospital of Wuhan University, Wuhan, China (Ringgold ID: RIN117921)
4   Engineering Research Center for Artificial Intelligence Endoscopy Interventional Treatment of Hubei Province, Renmin Hospital of Wuhan University, Wuhan, China (Ringgold ID: RIN117921)
,
Tao Tan
6   Department of Endoscopy, Third People‘s Hospital of Hubei Province, Wuhan, China (Ringgold ID: RIN648671)
,
Qinghong Xu
5   Department of Endoscopy, Eighth Hospital of Wuhan, Wuhan, China
,
Zhifeng Liu
6   Department of Endoscopy, Third People‘s Hospital of Hubei Province, Wuhan, China (Ringgold ID: RIN648671)
,
Yuan Huang
5   Department of Endoscopy, Eighth Hospital of Wuhan, Wuhan, China
,
Ci Zhu
5   Department of Endoscopy, Eighth Hospital of Wuhan, Wuhan, China
,
Wenbing Cao
5   Department of Endoscopy, Eighth Hospital of Wuhan, Wuhan, China
,
Liwen Yao
1   Department of Gastroenterology, Renmin Hospital of Wuhan University, Wuhan, China (Ringgold ID: RIN117921)
2   Hubei Provincial Clinical Research Center for Digestive Disease Minimally Invasive Incision, Renmin Hospital of Wuhan University, Wuhan, China (Ringgold ID: RIN117921)
3   Hubei Key Laboratory of Digestive System, Renmin Hospital of Wuhan University, Wuhan, China (Ringgold ID: RIN117921)
4   Engineering Research Center for Artificial Intelligence Endoscopy Interventional Treatment of Hubei Province, Renmin Hospital of Wuhan University, Wuhan, China (Ringgold ID: RIN117921)
,
Zhifeng Wu
1   Department of Gastroenterology, Renmin Hospital of Wuhan University, Wuhan, China (Ringgold ID: RIN117921)
2   Hubei Provincial Clinical Research Center for Digestive Disease Minimally Invasive Incision, Renmin Hospital of Wuhan University, Wuhan, China (Ringgold ID: RIN117921)
3   Hubei Key Laboratory of Digestive System, Renmin Hospital of Wuhan University, Wuhan, China (Ringgold ID: RIN117921)
4   Engineering Research Center for Artificial Intelligence Endoscopy Interventional Treatment of Hubei Province, Renmin Hospital of Wuhan University, Wuhan, China (Ringgold ID: RIN117921)
,
Lianlian Wu
1   Department of Gastroenterology, Renmin Hospital of Wuhan University, Wuhan, China (Ringgold ID: RIN117921)
2   Hubei Provincial Clinical Research Center for Digestive Disease Minimally Invasive Incision, Renmin Hospital of Wuhan University, Wuhan, China (Ringgold ID: RIN117921)
3   Hubei Key Laboratory of Digestive System, Renmin Hospital of Wuhan University, Wuhan, China (Ringgold ID: RIN117921)
4   Engineering Research Center for Artificial Intelligence Endoscopy Interventional Treatment of Hubei Province, Renmin Hospital of Wuhan University, Wuhan, China (Ringgold ID: RIN117921)
,
Chenxia Zhang
1   Department of Gastroenterology, Renmin Hospital of Wuhan University, Wuhan, China (Ringgold ID: RIN117921)
2   Hubei Provincial Clinical Research Center for Digestive Disease Minimally Invasive Incision, Renmin Hospital of Wuhan University, Wuhan, China (Ringgold ID: RIN117921)
3   Hubei Key Laboratory of Digestive System, Renmin Hospital of Wuhan University, Wuhan, China (Ringgold ID: RIN117921)
4   Engineering Research Center for Artificial Intelligence Endoscopy Interventional Treatment of Hubei Province, Renmin Hospital of Wuhan University, Wuhan, China (Ringgold ID: RIN117921)
,
Bing Xiao
1   Department of Gastroenterology, Renmin Hospital of Wuhan University, Wuhan, China (Ringgold ID: RIN117921)
2   Hubei Provincial Clinical Research Center for Digestive Disease Minimally Invasive Incision, Renmin Hospital of Wuhan University, Wuhan, China (Ringgold ID: RIN117921)
3   Hubei Key Laboratory of Digestive System, Renmin Hospital of Wuhan University, Wuhan, China (Ringgold ID: RIN117921)
4   Engineering Research Center for Artificial Intelligence Endoscopy Interventional Treatment of Hubei Province, Renmin Hospital of Wuhan University, Wuhan, China (Ringgold ID: RIN117921)
,
Ming Xu
1   Department of Gastroenterology, Renmin Hospital of Wuhan University, Wuhan, China (Ringgold ID: RIN117921)
2   Hubei Provincial Clinical Research Center for Digestive Disease Minimally Invasive Incision, Renmin Hospital of Wuhan University, Wuhan, China (Ringgold ID: RIN117921)
3   Hubei Key Laboratory of Digestive System, Renmin Hospital of Wuhan University, Wuhan, China (Ringgold ID: RIN117921)
4   Engineering Research Center for Artificial Intelligence Endoscopy Interventional Treatment of Hubei Province, Renmin Hospital of Wuhan University, Wuhan, China (Ringgold ID: RIN117921)
,
Jun Liu
1   Department of Gastroenterology, Renmin Hospital of Wuhan University, Wuhan, China (Ringgold ID: RIN117921)
2   Hubei Provincial Clinical Research Center for Digestive Disease Minimally Invasive Incision, Renmin Hospital of Wuhan University, Wuhan, China (Ringgold ID: RIN117921)
3   Hubei Key Laboratory of Digestive System, Renmin Hospital of Wuhan University, Wuhan, China (Ringgold ID: RIN117921)
4   Engineering Research Center for Artificial Intelligence Endoscopy Interventional Treatment of Hubei Province, Renmin Hospital of Wuhan University, Wuhan, China (Ringgold ID: RIN117921)
,
Shuyu Li
6   Department of Endoscopy, Third People‘s Hospital of Hubei Province, Wuhan, China (Ringgold ID: RIN648671)
,
Honggang Yu
1   Department of Gastroenterology, Renmin Hospital of Wuhan University, Wuhan, China (Ringgold ID: RIN117921)
2   Hubei Provincial Clinical Research Center for Digestive Disease Minimally Invasive Incision, Renmin Hospital of Wuhan University, Wuhan, China (Ringgold ID: RIN117921)
3   Hubei Key Laboratory of Digestive System, Renmin Hospital of Wuhan University, Wuhan, China (Ringgold ID: RIN117921)
4   Engineering Research Center for Artificial Intelligence Endoscopy Interventional Treatment of Hubei Province, Renmin Hospital of Wuhan University, Wuhan, China (Ringgold ID: RIN117921)
› Author Affiliations
Supported by: the Fundamental Research Funds for the Central Universities 2042022kf1099
Science and Technology Achievement Transformation Platform Construction Project of Ministry of Education
Supported by: National Natural Science Foundation of China-Youth Science Fund Project 82202257
Supported by: Innovation Team Project of Health Commission of Hubei Province WJ2021C003
College-enterprise Deepening Reform Project of Wuhan University

Clinical Trial: Registration number (trial ID): ChiCTR2200059453, Trial registry: Chinese Clinical Trial Registry (http://www.chictr.org/), Type of Study: Prospective

Abstract

Background The choice of polypectomy device and surveillance intervals for colorectal polyps are primarily decided by polyp size. We developed a deep learning-based system (ENDOANGEL-CPS) to estimate colorectal polyp size in real time.

Methods ENDOANGEL-CPS calculates polyp size by estimating the distance from the endoscope lens to the polyp using the parameters of the lens. The depth estimator network was developed on 7297 images from five virtually produced colon videos and tested on 730 images from seven virtual colon videos. The performance of the system was first evaluated in nine videos of a simulated colon with polyps attached, then tested in 157 real-world prospective videos from three hospitals, with the outcomes compared with that of nine endoscopists over 69 videos. Inappropriate surveillance recommendations caused by incorrect estimation of polyp size were also analyzed.

Results The relative error of depth estimation was 11.3% (SD 6.0%) in successive virtual colon images. The concordance correlation coefficients (CCCs) between system estimation and ground truth were 0.89 and 0.93 in images of a simulated colon and multicenter videos of 157 polyps. The mean CCC of ENDOANGEL-CPS surpassed all endoscopists (0.89 vs. 0.41 [SD 0.29]; P<0.001). The relative accuracy of ENDOANGEL-CPS was significantly higher than that of endoscopists (89.9% vs. 54.7%; P<0.001). Regarding inappropriate surveillance recommendations, the system's error rate is also lower than that of endoscopists (1.5% vs. 16.6%; P<0.001).

Conclusions ENDOANGEL-CPS could potentially improve the accuracy of colorectal polyp size measurements and size-based surveillance intervals.

Supplementary Material



Publication History

Received: 27 May 2023

Accepted after revision: 11 October 2023

Accepted Manuscript online:
12 October 2023

Article published online:
05 December 2023

© 2023. Thieme. All rights reserved.

Georg Thieme Verlag KG
Rüdigerstraße 14, 70469 Stuttgart, Germany