Randomised controlled trial of WISENSE, a real-time quality improving system for monitoring blind spots during esophagogastroduodenoscopy
Lianlian Wu, Jun Zhang, Wei Zhou, Ping An, Lei Shen, Jun Liu, Xiaoda Jiang, Xu Huang, Ganggang Mu, Xinyue Wan, Xiaoguang Lv, Juan Gao, Ning Cui, Shan Hu, Yiyun Chen, Xiao Hu, Jiangjie Li, Di Chen, Dexin Gong, Xinqi He, Qianshan Ding, Xiaoyun Zhu, Suqin Li, Xiao Wei, Xia Li, Xuemei Wang, Jie Zhou, Mengjiao Zhang, Hong Gang Yu, Lianlian Wu, Jun Zhang, Wei Zhou, Ping An, Lei Shen, Jun Liu, Xiaoda Jiang, Xu Huang, Ganggang Mu, Xinyue Wan, Xiaoguang Lv, Juan Gao, Ning Cui, Shan Hu, Yiyun Chen, Xiao Hu, Jiangjie Li, Di Chen, Dexin Gong, Xinqi He, Qianshan Ding, Xiaoyun Zhu, Suqin Li, Xiao Wei, Xia Li, Xuemei Wang, Jie Zhou, Mengjiao Zhang, Hong Gang Yu
Abstract
Objective: Esophagogastroduodenoscopy (EGD) is the pivotal procedure in the diagnosis of upper gastrointestinal lesions. However, there are significant variations in EGD performance among endoscopists, impairing the discovery rate of gastric cancers and precursor lesions. The aim of this study was to construct a real-time quality improving system, WISENSE, to monitor blind spots, time the procedure and automatically generate photodocumentation during EGD and thus raise the quality of everyday endoscopy.
Design: WISENSE system was developed using the methods of deep convolutional neural networks and deep reinforcement learning. Patients referred because of health examination, symptoms, surveillance were recruited from Renmin hospital of Wuhan University. Enrolled patients were randomly assigned to groups that underwent EGD with or without the assistance of WISENSE. The primary end point was to ascertain if there was a difference in the rate of blind spots between WISENSE-assisted group and the control group.
Results: WISENSE monitored blind spots with an accuracy of 90.40% in real EGD videos. A total of 324 patients were recruited and randomised. 153 and 150 patients were analysed in the WISENSE and control group, respectively. Blind spot rate was lower in WISENSE group compared with the control (5.86% vs 22.46%, p<0.001), and the mean difference was -15.39% (95% CI -19.23 to -11.54). There was no significant adverse event.
Conclusions: WISENSE significantly reduced blind spot rate of EGD procedure and could be used to improve the quality of everyday endoscopy.
Trial registration number: ChiCTR1800014809; Results.
Keywords: endoscopy.
Conflict of interest statement
Competing interests: None declared.
© Author(s) (or their employer(s)) 2019. Re-use permitted under CC BY-NC. No commercial re-use. See rights and permissions. Published by BMJ.
Figures
References
- Bisschops R, Areia M, Coron E, et al. . Performance measures for upper gastrointestinal endoscopy: a European Society of Gastrointestinal Endoscopy (ESGE) Quality Improvement Initiative. Endoscopy 2016;48:843–64. 10.1055/s-0042-113128
- Rutter MD, Rees CJ. Quality in gastrointestinal endoscopy. Endoscopy 2014;46:526–8. 10.1055/s-0034-1365738
- Gado AS, Ebeid BA, Axon AT. Quality assurance in gastrointestinal endoscopy: An Egyptian experience. Arab J Gastroenterol 2016;17:153–8. 10.1016/j.ajg.2016.11.002
- Zhang JG, Liu HF. Functional imaging and endoscopy. World J Gastroenterol 2011;17:4277–82. 10.3748/wjg.v17.i38.4277
- Di L, Wu H, Zhu R, et al. . Multi-disciplinary team for early gastric cancer diagnosis improves the detection rate of early gastric cancer. BMC Gastroenterol 2017;17:147 10.1186/s12876-017-0711-9
- Faigel DO. Quality, competency and endosonography. Endoscopy 2006;38(Suppl 1):65–9. 10.1055/s-2006-946657
- Malheiro R, de Monteiro-Soares M, Hassan C, et al. . Methodological quality of guidelines in gastroenterology. Endoscopy 2014;46:513–25. 10.1055/s-0034-1365394
- Faigel DO, Pike IM, Baron TH, et al. . Quality indicators for gastrointestinal endoscopic procedures: an introduction. Am J Gastroenterol 2006;101:866–72. 10.1111/j.1572-0241.2006.00677.x
- Park WG, Cohen J. Quality measurement and improvement in upper endoscopy. Tech Gastrointest Endosc 2012;14:13–20. 10.1016/j.tgie.2011.10.003
- Cohen J, Safdi MA, Deal SE, et al. . Quality indicators for esophagogastroduodenoscopy. Gastrointest Endosc 2006;63(4 Suppl):S10–15. 10.1016/j.gie.2006.02.018
- Yao K. The endoscopic diagnosis of early gastric cancer. Ann Gastroenterol 2013;26:11.
- Bretthauer M, Aabakken L, Dekker E, et al. . Requirements and standards facilitating quality improvement for reporting systems in gastrointestinal endoscopy: European Society of Gastrointestinal Endoscopy (ESGE) Position Statement. Endoscopy 2016;48:291–4. 10.1055/s-0042-100186
- Torkamani A, Andersen KG, Steinhubl SR, et al. . High-definition medicine. Cell 2017;170:828–43. 10.1016/j.cell.2017.08.007
- LeCun Y, Bengio Y, Hinton G. Deep learning. Nature 2015;521:436–44. 10.1038/nature14539
- Hirasawa T, Aoyama K, Tanimoto T, et al. . Application of artificial intelligence using a convolutional neural network for detecting gastric cancer in endoscopic images. Gastric Cancer 2018;21:653–60. 10.1007/s10120-018-0793-2
- Byrne MF, Chapados N, Soudan F, et al. . Real-time differentiation of adenomatous and hyperplastic diminutive colorectal polyps during analysis of unaltered videos of standard colonoscopy using a deep learning model. Gut 2019;68:94–100. 10.1136/gutjnl-2017-314547
- Tobin J, Fong R, Ray A, et al. . Domain randomization for transferring deep neural networks from simulation to the real world. IEEE 2017:23–30.
- Silver D, Huang A, Maddison CJ, et al. . Mastering the game of Go with deep neural networks and tree search. Nature 2016;529:484–9. 10.1038/nature16961
- Mnih V, Kavukcuoglu K, Silver D, et al. . Human-level control through deep reinforcement learning. Nature 2015;518:529–33. 10.1038/nature14236
- Mnih V, Kavukcuoglu K, Silver D, et al. . Playing atari with deep reinforcement learning. arXiv preprint arXiv 2013;1312:5602.
- Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv 2014;1409:1556.
- Wen Z, Li B, Ramamohanarao K, et al. . Improving Efficiency of SVM k-Fold Cross-Validation by Alpha Seeding. AAAI 2017:2768–74.
- Glimcher PW. Understanding dopamine and reinforcement learning: the dopamine reward prediction error hypothesis. Proc Natl Acad Sci U S A 2011;108(Suppl 3):15647–54. 10.1073/pnas.1014269108
- Fang M, Li Y, Cohn T. Learning how to active learn. arXiv preprint arXiv 2017;1708:02383.
- Li J, Chai T, Lewis FL, et al. . Off-policy interleaved Q-learning: optimal control for affine nonlinear discrete-time systems. IEEE Trans Neural Netw Learn Syst 2018:1–13. 10.1109/TNNLS.2018.2861945
- Leung WK, Wu MS, Kakugawa Y, et al. . Screening for gastric cancer in Asia: current evidence and practice. Lancet Oncol 2008;9:279–87. 10.1016/S1470-2045(08)70072-X
- Van Cutsem E, Sagaert X, Topal B, et al. . Gastric cancer. The Lancet 2016;388:2654–64. 10.1016/S0140-6736(16)30354-3
- Miot HA. Sample size in clinical and experimental trials. J Vasc Bras 2011;10:275–8.
- Huang Q, Shi J, Sun Q, et al. . Clinicopathological characterisation of small (2cm or less) proximal and distal gastric carcinomas in a Chinese population. Pathology 2015;47:526–32. 10.1097/PAT.0000000000000276
- Teh JL, Tan JR, Lau LJF, et al. . Longer examination time improves detection of gastric cancer during diagnostic upper gastrointestinal endoscopy. Clin Gastroenterol Hepatol 2015;13:480–7. 10.1016/j.cgh.2014.07.059
- Olympus Global. Olympus annual report 3. 2018.
- Fujifilm Holding Corporation. Fujifilm holding corporation annual report. 2016.
- Chang P, Grinband J, Weinberg BD, et al. . Deep-learning convolutional neural networks accurately classify genetic mutations in gliomas. AJNR Am J Neuroradiol 2018;39:1201–7. 10.3174/ajnr.A5667
- Urban G, Tripathi P, Alkayali T, et al. . Deep learning localizes and identifies polyps in real time with 96% accuracy in screening colonoscopy. Gastroenterology 2018;155:1069–78. 10.1053/j.gastro.2018.06.037
Source: PubMed