This paper is only available as a PDF. To read, Please Download here.
Abstract
Background and Aims
Although narrow band imaging (NBI) has been a useful modality for detecting and delineating
esophageal squamous cell carcinoma (ESCC), there is a risk of incorrectly determining
the margins of some lesions even with NBI. This study aimed to develop an artificial
intelligence (AI) system for detecting superficial ESCC and precancerous lesions and
delineating the extent of lesions under NBI.
Methods
Nonmagnified NBI images from four hospitals were collected and annotated. Internal
and external image test datasets were used to evaluate the detection and delineation
performance of the system. The delineation performance of the system was compared
with that of endoscopists. Furthermore, the system was directly integrated into the
endoscopy equipment, and its real-time diagnostic capability was prospectively estimated.
Results
The system was trained and tested using 10047 still images and 140 videos from 1112
patients and 1183 lesions. In the image testing, the accuracy of the system in detecting
lesions in internal and external tests was 92.4% and 89.9%, respectively. The accuracy
of the system in delineating extents in internal and external tests was 88.9% and
87.0%, respectively. The delineation performance of the system was superior to that
of junior endoscopists and similar to that of senior endoscopists. In the prospective
clinical evaluation, the system exhibited satisfactory performance, with an accuracy
of 91.4% in detecting lesions and an accuracy of 85.9% in delineating extents.
Conclusion
The proposed AI system could accurately detect superficial ESCC and precancerous lesions
and delineate the extent of lesions under NBI.
Acronyms:
Narrow band imaging (NBI), Esophageal squamous cell carcinoma (ESCC), Artificial intelligence (AI), Endoscopic resection (ER), Deep convolutional neural network (DCNN), White light endoscopy (WLE), West China Hospital of Sichuan University (WCHSCU), Endoscopic submucosal dissection (ESD), Positive predictive value (PPV), Negative predictive value (NPV), Mean intersection over union (mIoU), True positive (TP), False positive (FP), False negative (FN)To read this article in full you will need to make a payment
Purchase one-time access:
Academic & Personal: 24 hour online accessCorporate R&D Professionals: 24 hour online accessOne-time access price info
- For academic or personal research use, select 'Academic and Personal'
- For corporate R&D use, select 'Corporate R&D Professionals'
Subscribe:
Subscribe to Gastrointestinal EndoscopyAlready a print subscriber? Claim online access
Already an online subscriber? Sign in
Register: Create an account
Institutional Access: Sign in to ScienceDirect
Article info
Publication history
Accepted:
December 1,
2022
Received in revised form:
November 4,
2022
Received:
July 31,
2022
Publication stage
In Press Journal Pre-ProofFootnotes
Funding:
National Natural Science Foundation of China (Grant No: 82170675) and 1·3·5 project for disciplines of excellence, West China Hospital, Sichuan University (Grant No: ZYJC21011)
Conflict of interest statement: All authors disclosed no conflicts of interests.
Author contributions:
Study design: Bing Hu, Xiang-Lei Yuan, and Xian-Hui Zeng.
Data collection and preparation: Xiang-Lei Yuan, Xian-Hui Zeng, Wei Liu, Yi Mou, Wan-Hong Zhang, Zheng-Duan Zhou, Xin Chen, and Yan-Xing Hu.
Data analysis and interpretation: Xiang-Lei Yuan and Xian-Hui Zeng
Manuscript writing: Xiang-Lei Yuan.
Revised advisor: Bing Hu and Xian-Hui Zeng.
Final approval of manuscript: All authors
Identification
Copyright
© 2022 by the American Society for Gastrointestinal Endoscopy
