Expert-level classification of gastritis by endoscopy using deep learning: a multicenter diagnostic trial

Abstract

Background and study aims Endoscopy plays a crucial role in diagnosis of gastritis. Endoscopists have low accuracy in diagnosing atrophic gastritis with white-light endoscopy (WLE). High-risk factors (such as atrophic gastritis [AG]) for carcinogenesis demand early detection. Deep learning (DL)-based gastritis classification with WLE rarely has been reported. We built a system for improving the accuracy of diagnosis of AG with WLE to assist with this common gastritis diagnosis and help lessen endoscopist fatigue.

Methods We collected a total of 8141 endoscopic images of common gastritis, other gastritis, and non-gastritis in 4587 cases and built a DL -based system constructed with UNet + + and Resnet-50. A system was developed to sort common gastritis images layer by layer: The first layer included non-gastritis/common gastritis/other gastritis, the second layer contained AG/non-atrophic gastritis, and the third layer included atrophy/intestinal metaplasia and erosion/hemorrhage. The convolutional neural networks were tested with three separate test sets.

Results Rates of accuracy for classifying non-atrophic gastritis/AG, atrophy/intestinal metaplasia, and erosion/hemorrhage were 88.78 %, 87.40 %, and 93.67 % in internal test set, 91.23 %, 85.81 %, and 92.70 % in the external test set ,and 95.00 %, 92.86 %, and 94.74 % in the video set, respectively. The hit ratio with the segmentation model was 99.29 %. The accuracy for detection of non-gastritis/common gastritis/other gastritis was 93.6 %.

Conclusions The system had decent specificity and accuracy in classification of gastritis lesions.DL has great potential in WLE gastritis classification for assisting with achieving accurate diagnoses after endoscopic procedures.

• References

• 1 Bray F, Ferlay J, Soerjomataram I. et al. Global cancer statistics 2018: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA Cancer J Clin 2018; 68: 394-424
• 2 Banks M, Graham D, Jansen M. et al. British Society of Gastroenterology guidelines on the diagnosis and management of patients at risk of gastric adenocarcinoma. Gut 2019; 68: 1545-1575
• 3 Correa P. Human Gastric Carcinogenesis: A Multistep and Multifactorial Process—First American Cancer Society Award Lecture on Cancer Epidemiology and Prevention. Cancer Research 1992; 52: 6735
• 4 Rugge M, Meggio A, Pravadelli C. et al. Gastritis staging in the endoscopic follow-up for the secondary prevention of gastric cancer: a 5-year prospective study of 1755 patients. Gut 2019; 68: 11-17
• 5 Leung WK, Ho HJ, Lin J-T. et al. Prior gastroscopy and mortality in patients with gastric cancer: a matched retrospective cohort study. Gastrointest Endosc 2018; 87: 119-127.e113
• 6 Pimentel-Nunes P, Libânio D, Marcos-Pinto R. et al. Management of epithelial precancerous conditions and lesions in the stomach (MAPS II): European Society of Gastrointestinal Endoscopy (ESGE), European Helicobacter and Microbiota Study Group (EHMSG), European Society of Pathology (ESP), and Sociedade Portuguesa de Endoscopia Digestiva (SPED) guideline update 2019. Endoscopy 2019; 51: 365-388
• 7 Du Y, Bai Y, Xie P. et al. Chronic gastritis in China: a national multi-center survey. BMC Gastroenterology 2014; 14: 21
• 8 Guimaraes P, Keller A, Fehlmann T. et al. Deep-learning based detection of gastric precancerous conditions. Gut 2020; 69: 4-6
• 9 Zhang Y, Li F, Yuan F. et al. Diagnosing chronic atrophic gastritis by gastroscopy using artificial intelligence. Dig Liver Dis 2020; 52: 566-572
• 10 Kimura K, Takemoto T. An Endoscopic Recognition of the Atrophic Border and its Significance in Chronic Gastritis. Endoscopy 1969; 1: 87-97
• 11 Rugge M, Meggio A, Pennelli G. et al. Gastritis staging in clinical practice: the OLGA staging system. Gut 2007; 56: 631-636
• 12 Sugano K, Tack J, Kuipers EJ. et al. Kyoto global consensus report on Helicobacter pylori gastritis. Gut 2015; 64: 1353-1367
• 13 TYTGAT GNJ. Endoscopic appearances in gastritis/duodenitis. The Sydney System: Endoscopic division 1991; 6: 223-234
• 14 Jin EH, Chung SJ, Lim JH. et al. Training Effect on the inter-observer agreement in endoscopic diagnosis and grading of atrophic gastritis according to level of endoscopic experience. J Korean Med Sci 2018; 33: e117
• 15 Ono S, Dohi O, Yagi N. et al. Accuracies of endoscopic diagnosis of helicobacter pylori-gastritis: multicenter prospective study using white light imaging and linked color imaging. Digestion 2020; 101: 624-630
• 16 Dutta AK, Sajith KG, Pulimood AB. et al. Narrow band imaging versus white light gastroscopy in detecting potentially premalignant gastric lesions: a randomized prospective crossover study. Ind J Gastroenterol 2013; 32: 37-42
• 17 Esteva A, Kuprel B, Novoa RA. et al. Dermatologist-level classification of skin cancer with deep neural networks. Nature 2017; 542: 115-118
• 18 Martin DR, Hanson JA, Gullapalli RR. et al. A deep learning convolutional neural network can recognize common patterns of injury in gastric pathology. Arch Pathol Lab Med 2020; 144: 370-378
• 19 Togo R, Yamamichi N, Mabe K. et al. Detection of gastritis by a deep convolutional neural network from double-contrast upper gastrointestinal barium X-ray radiography. J Gastroenterol 2019; 54: 321-329
• 20 Itoh T, Kawahira H, Nakashima H. et al. Deep learning analyzes Helicobacter pylori infection by upper gastrointestinal endoscopy images. Endosc Int Open 2018; 6: E139-E144
• 21 Nakahira H, Ishihara R, Aoyama K. et al. Stratification of gastric cancer risk using a deep neural network. 2020; 4: 466-471
• 22 Wu L, Zhang J, Zhou W. et al. Randomised controlled trial of WISENSE, a real-time quality improving system for monitoring blind spots during esophagogastroduodenoscopy. Gut 2019; 68: 2161-2169
• 23 Wu L, Zhou W, Wan X. et al. A deep neural network improves endoscopic detection of early gastric cancer without blind spots. Endoscopy 2019; 51: 522-531
• 24 Chen D, Wu L, Li Y. et al. Comparing blind spots of unsedated ultrafine, sedated, and unsedated conventional gastroscopy with and without artificial intelligence: a prospective, single-blind, 3-parallel-group, randomized, single-center trial. Gastrointest Endosc 2020; 91: 332-339.e333
• 25 Ruiz B, Garay J, Correa P. et al. Morphometric evaluation of gastric antral atrophy: improvement after cure of Helicobacter pylori infection. Am J Gastroenterol 2001; 96: 3281-3287
• 26 Genta RM. Recognizing atrophy: another step toward a classification of gastritis. Am J Surg Path 1996; 20: S23-S30
• 27 Rugge M, Genta RM. Staging and grading of chronic gastritis. Hum Pathol 2005; 36: 228-233
• 28 He K, Zhang X, Ren S. et al. Deep Residual Learning for Image Recognition. IEEE Conference on Computer Vision & Pattern Recognition; 2016
• 29 Zhou Z, Siddiquee MMR, Tajbakhsh N. et al. UNet++: Redesigning skip connections to exploit multiscale features in image segmentation. IEEE Transact Med Imaging 2019;
• 30 Shao L, Zhu F, Li X. Transfer learning for visual categorization: a survey. IEEE Transact Neural Net Learning Sys 2015; 26: 1019-1034
• 31 You WC, Li JY, Blot WJ. et al. Evolution of precancerous lesions in a rural Chinese population at high risk of gastric cancer. Int J Cancer 1999; 83: 615-619
• 32 Blaser MJ. Type B gastritis, aging, and Campylobacter pylori. Arch Int Med 1988; 148: 1021-1022
• 33 Uemura N, Okamoto S, Yamamoto S. et al. Helicobacter pylori infection and the development of gastric cancer. N Engl J Med 2001; 345: 784-789
• 34 Yamamoto Y, Fujisaki J, Omae M. et al. Helicobacter pylori-negative gastric cancer: characteristics and endoscopic findings. Dig Endosc 2015; 27: 551-561