Feedback from artificial intelligence improved the learning of junior endoscopists on histology prediction of gastric lesions

Abstract

Background and study aims Artificial intelligence (AI)-assisted image classification has been shown to have high accuracy on endoscopic diagnosis. We evaluated the potential effects of use of an AI-assisted image classifier on training of junior endoscopists for histological prediction of gastric lesions.

Methods An AI image classifier was built on a convolutional neural network with five convolutional layers and three fully connected layers A Resnet backbone was trained by 2,000 non-magnified endoscopic gastric images. The independent validation set consisted of another 1,000 endoscopic images from 100 gastric lesions. The first part of the validation set was reviewed by six junior endoscopists and the prediction of AI was then disclosed to three of them (Group A) while the remaining three (Group B) were not provided this information. All endoscopists reviewed the second part of the validation set independently.

Results The overall accuracy of AI was 91.0 % (95 % CI: 89.2–92.7 %) with 97.1 % sensitivity (95 % CI: 95.6–98.7%), 85.9 % specificity (95 % CI: 83.0–88.4 %) and 0.91 area under the ROC (AUROC) (95 % CI: 0.89–0.93). AI was superior to all junior endoscopists in accuracy and AUROC in both validation sets. The performance of Group A endoscopists but not Group B endoscopists improved on the second validation set (accuracy 69.3 % to 74.7 %; P = 0.003).

Conclusion The trained AI image classifier can accurately predict presence of neoplastic component of gastric lesions. Feedback from the AI image classifier can also hasten the learning curve of junior endoscopists in predicting histology of gastric lesions.

• References

• 1 Fitzmaurice C, Allen C, Barber RM. et al. Global, regional, and national cancer incidence, mortality, years of life lost, years lived with disability, and disability-adjusted life-years for 32 cancer groups, 1990 to 2015: a systematic analysis for the global burden of disease study global burden. JAMA Oncol 2017; 3: 524-548
• 2 Yokota T, Ishiyama S, Saito T. et al. Lymph node metastasis as a significant prognostic factor in gastric cancer: A multiple logistic regression analysis. Scand J Gastroenterol 2004; 39: 380-384
• 3 Zheng Z, Liu Y, Bu Z. et al. Prognostic role of lymph node metastasis in early gastric cancer. Chinese J Cancer Res 2014; 26: 192-199
• 4 Kaise M. Advanced endoscopic imaging for early gastric cancer. Green J. (ed.) Best Pract Res Clin Gastroenterol 2015; 29: 575-587
• 5 Wang L, Huang W, Du J. et al. Diagnostic yield of the light blue crest sign in gastric intestinal metaplasia: A meta-analysis. PLoS One 2014; 9: e92874
• 6 Dinis-Ribeiro M, DaCosta-Pereira A, Lopes C. et al. Magnification chromoendoscopy for the diagnosis of gastric intestinal metaplasia and dysplasia. Gastrointest Endosc 2003; 57: 498-504
• 7 Morales TG, Bhattacharyya A, Camargo E. et al. Methylene blue staining for intestinal metaplasia of the gastric cardia with follow-up for dysplasia. Gastrointest Endosc 1998; 48: 26-32
• 8 Yao K, Anagnostopoulos GK, Ragunath K. Magnifying endoscopy for diagnosing and delineating early gastric cancer. Endoscopy 2009; 41: 462-467
• 9 Chai N-L, Ling-Hu E-Q, Morita Y. et al. Magnifying endoscopy in upper gastroenterology for assessing lesions before completing endoscopic removal. World J Gastroenterol 2012; 18: 1295-1307
• 10 Gotoda T, Ho K-Y, Soetikno R. et al. Gastric ESD: current status and future directions of devices and training. Gastrointest Endosc Clin N Am 2014; 24: 213-233
• 11 Maekawa A, Kato M, Nakamura T. et al. Incidence of gastric adenocarcinoma among lesions diagnosed as low‐grade adenoma/dysplasia on endoscopic biopsy: A multicenter, prospective, observational study. Dig Endosc 2018; 30: 228-235
• 12 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: 653-660
• 13 Zhu Y, Wang Q-C, Xu M-D. et al. Application of convolutional neural network in the diagnosis of the invasion depth of gastric cancer based on conventional endoscopy. Gastrointest Endosc 2019; 89: 806-815.e1
• 14 Lui T, Wong K, Mak L. et al. Endoscopic prediction of deeply submucosal invasive carcinoma with use of artificial intelligence. Endosc Int Open 2019; 07: E514-E520
• 15 Brambilla E, Travis WD, Colby TV. et al. The new World Health Organization classification of lung tumours. Eur Respir J 2001; 18: 1059-1068
• 16 Rahwan I, Cebrian M, Obradovich N. et al. Machine behaviour. Nature 2019; 568: 477-486
• 17 Coiera E, Kocaballi B, Halamaka J. et al. The price of artificial intelligence. IMIA Yearb Med Informatics 2019; 1: 1-2
• 18 Yao K, Anagnostopoulos GK, Ragunath K. Magnifying endoscopy for diagnosing and delineating early gastric cancer. Endoscopy 2009; 41: 462-467
• 19 Goda K, Dobashi A, Yoshimura N. et al. Dual-focus versus conventional magnification endoscopy for the diagnosis of superficial squamous neoplasms in the pharynx and esophagus: A randomized trial. Endoscopy 2016; 48: 321-329
• 20 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
• 21 Mori Y, Kudo SE, Misawa M. et al. Real-time use of artificial intelligence in identification of diminutive polyps during colonoscopy a prospective study. Ann Intern Med 2018; 169: 357-366