Subscribe to RSS
DOI: 10.1055/a-2031-0691
Deep learning-based clinical decision support system for gastric neoplasms in real-time endoscopy: development and validation study
Supported by: 2020 Olympus Korea grant from the Korean Gastrointestinal Endoscopy Research Foundation 2020Trial Registration: ClinicalTrials.gov Registration number (trial ID): NCT05452473 Type of study: Randomized study
![](https://www.thieme-connect.de/media/endoscopy/202308/lookinside/thumbnails/22405_10-1055-a-2031-0691-1.jpg)
Abstract
Background Deep learning models have previously been established to predict the histopathology and invasion depth of gastric lesions using endoscopic images. This study aimed to establish and validate a deep learning-based clinical decision support system (CDSS) for the automated detection and classification (diagnosis and invasion depth prediction) of gastric neoplasms in real-time endoscopy.
Methods The same 5017 endoscopic images that were employed to establish previous models were used for the training data. The primary outcomes were: (i) the lesion detection rate for the detection model, and (ii) the lesion classification accuracy for the classification model. For performance validation of the lesion detection model, 2524 real-time procedures were tested in a randomized pilot study. Consecutive patients were allocated either to CDSS-assisted or conventional screening endoscopy. The lesion detection rate was compared between the groups. For performance validation of the lesion classification model, a prospective multicenter external test was conducted using 3976 novel images from five institutions.
Results The lesion detection rate was 95.6 % (internal test). On performance validation, CDSS-assisted endoscopy showed a higher lesion detection rate than conventional screening endoscopy, although statistically not significant (2.0 % vs. 1.3 %; P = 0.21) (randomized study). The lesion classification rate was 89.7 % in the four-class classification (advanced gastric cancer, early gastric cancer, dysplasia, and non-neoplastic) and 89.2 % in the invasion depth prediction (mucosa confined or submucosa invaded; internal test). On performance validation, the CDSS reached 81.5 % accuracy in the four-class classification and 86.4 % accuracy in the binary classification (prospective multicenter external test).
Conclusions The CDSS demonstrated its potential for real-life clinical application and high performance in terms of lesion detection and classification of detected lesions in the stomach.
Publication History
Received: 03 September 2022
Accepted after revision: 08 February 2023
Accepted Manuscript online:
08 February 2023
Article published online:
17 April 2023
© 2023. Thieme. All rights reserved.
Georg Thieme Verlag KG
Rüdigerstraße 14, 70469 Stuttgart, Germany
-
References
- 1 Cho BJ, Bang CS, Park SW. et al. Automated classification of gastric neoplasms in endoscopic images using a convolutional neural network. Endoscopy 2019; 51: 1121-1129
- 2 Cho BJ, Bang CS. Artificial intelligence for the determination of a management strategy for diminutive colorectal polyps: hype, hope, or help. Am J Gastroenterol 2020; 115: 70-72
- 3 Cho BJ, Bang CS, Lee JJ. et al. Prediction of submucosal invasion for gastric neoplasms in endoscopic images using deep-learning. J Clin Med 2020; 9: 1858
- 4 Park CH, Yang DH, Kim JW. et al. Clinical practice guideline for endoscopic resection of early gastrointestinal cancer. Clin Endosc 2020; 53: 142-166
- 5 Kaltenbach T, Anderson JC, Burke CA. et al. Endoscopic removal of colorectal lesions recommendations by the US Multi-society Task Force on Colorectal Cancer. Gastroenterology 2020; 158: 1095-1129
- 6 Bang CS, Lee JJ, Baik GH. Computer-aided diagnosis of esophageal cancer and neoplasms in endoscopic images: a systematic review and meta-analysis of diagnostic test accuracy. Gastrointest Endosc 2020; 93: 1006-1015.e13
- 7 Bang CS, Lee JJ, Baik GH. Artificial intelligence for the prediction of Helicobacter pylori infection in endoscopic images: systematic review and meta-analysis of diagnostic test accuracy. J Med Internet Res 2020; 22: e21983
- 8 Berzin TM, Parasa S, Wallace MB. et al. Position statement on priorities for artificial intelligence in GI endoscopy: a report by the ASGE Task Force. Gastrointest Endosc 2020; 92: 951-959
- 9 Yang YJ, Bang CS. Application of artificial intelligence in gastroenterology. World J Gastroenterol 2019; 25: 1666-1683
- 10 Bang CS. Deep learning in upper gastrointestinal disorders: status and future perspectives. Korean J Gastroenterol 2020; 75: 120-131
- 11 Bang CS AJ, Kim JH, Kim YI. et al. Establishing machine learning models to predict curative resection in early gastric cancer with undifferentiated histology: development and usability study. J Med Internet Res 2021; 23: e25053
- 12 Bang CS LH, Jeong HM, Hwang SH. Use of endoscopic images in the prediction of submucosal invasion of gastric neoplasms: automated deep learning model development and usability study. J Med Internet Res 2021; 23: e25167
- 13 Abadir AP, Ali MF, Karnes W. et al. Artificial intelligence in gastrointestinal endoscopy. Clin Endosc 2020; 53: 132-141
- 14 Hasan SMK, Linte CA. A modified U-Net Convolutional Network featuring a nearest-neighbor re-sampling-based elastic-transformation for brain tissue characterization and segmentation. Proc IEEE West N Y Image Signal Process Workshop 2018; DOI: 10.1109/WNYIPW.2018.8576421.
- 15 Huang G, Liu Z, Weinberger KQ. Densely connected convolutional networks. Computing Research Repository 2016; DOI: 10.48550/arXiv.1608.06993.
- 16 van Rossum G, Drake Jr. FL. Python reference manual. 1995 Available at (Accessed: 02.03.2023): https://ir.cwi.nl/pub/5008
- 17 Hipp RD. SQLite. 2020 Available at (Accessed 20.02.2023): https://www.sqlite.org/index.html
- 18 Redmon J, Farhadi AJapa. Yolov3: An incremental improvement. 2018 Available at (Accessed 02.03.2023): https://arxiv.org/pdf/1804.02767.pdf
- 19 Tan M, Le Q. EfficientNet: Rethinking model scaling for convolutional neural networks. International Conference on Machine Learning. 2019 Available at (Accessed 02.03.2023): https://arxiv.org/pdf/1905.11946.pdf
- 20 He K, Zhang X, Ren S. et al. Deep residual learning for image recognition. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 27–30 June 2016. 2016
- 21 Pedregosa F, Varoquaux G, Gramfort A. et al. Scikit-learn: Machine Learning in Python. J Mach Learn Res 2011; 12: 2825-2830
- 22 Li YD, Li HZ, Chen SS. et al. Correlation of the detection rate of upper GI cancer with artificial intelligence score: results from a multicenter trial (with video). Gastrointest Endosc 2022; 95: 1138-1146.e2
- 23 Schulz KF, Altman DG, Moher D. CONSORT 2010 Statement: updated guidelines for reporting parallel group randomised trials. Trials 2010; 11: 32
- 24 Jang ES, Park SM, Park YS. et al. Work-life conflict and its health effects on Korean gastroenterologists according to age and sex. Dig Dis Sci 2020; 65: 86-95