Background and Aims
Insufficient validation limits the generalizability of deep learning in diagnosing
Helicobacter pylori infection with endoscopic images. The aim of this study was to develop a deep learning
model for the diagnosis of H pylori infection using endoscopic images and validate the model with internal and external
datasets.
Methods
A convolutional neural network (CNN) model was developed based on a training dataset
comprising 13,403 endoscopic images from 952 patients who underwent endoscopy at Seoul
National University Hospital Gangnam Center. Internal validation was performed using
a separate dataset comprised of images of 411 individuals of Korean descent and 131
of non-Korean descent. External validation was performed with the images of 160 patients
in Gangnam Severance Hospital. Gradient-weighted class activation mapping was performed
to visually explain the model.
Results
In predicting H pylori ever-infected status, the sensitivity, specificity, and accuracy of internal validation
for people of Korean descent were .96 (95% confidence interval [CI], .93-.98), .90
(95% CI, .85-.95), and .94 (95% CI, .91-.96), respectively. In the internal validation
for people of non-Korean descent, the sensitivity, specificity, and accuracy in predicting
H pylori ever-infected status were .92 (95% CI, .86-.98), .79 (95% CI, .67-.91), and .88 (95%
CI, .82-.93), respectively. In the external validation cohort, sensitivity, specificity,
and accuracy were .86 (95% CI, .80-.93), .88 (95% CI, .79-.96), and .87 (95% CI, .82-.92),
respectively, when performing 2-group categorization. Gradient-weighted class activation
mapping showed that the CNN model captured the characteristic findings of each group.
Conclusions
This CNN model for diagnosing H pylori infection showed good overall performance in internal and external validation datasets,
particularly in categorizing patients into the never- versus ever-infected groups.
Abbreviations:
AI (artificial intelligence), CNN (convolutional neural network), CI (confidence interval), SNUH-GC (Seoul National University Hospital Gangnam Center)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
References
- 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
- Carcinogenesis of Helicobacter pylori.Gastroenterology. 2007; 133: 659-672
- Diagnostic tests for Helicobacter pylori: a prospective evaluation of their accuracy, without selecting a single test as the gold standard.Am J Gastroenterol. 1996; 91: 2125-2129
- Helicobacter pylori eradication as a strategy for gastric cancer prevention. Lyon, France: International Agency for Research on Cancer (IARC Working Group Reports, No. 8).(Available at:)
- Family history of gastric cancer and Helicobacter pylori treatment.N Engl J Med. 2020; 382: 427-436
- Helicobacter pylori therapy for the prevention of metachronous gastric cancer.N Engl J Med. 2018; 378: 1085-1095
- Helicobacter pylori eradication therapy to prevent gastric cancer in healthy asymptomatic infected individuals: systematic review and meta-analysis of randomised controlled trials.BMJ. 2014; 348: g3174
- Non-invasive diagnostic tests for Helicobacter pylori infection.Cochrane Database Syst Rev. 2018; 3: CD012080
- Accuracy of urea breath test in Helicobacter pylori infection: meta-analysis.World J Gastroenterol. 2015; 21: 1305-1314
- Evaluation of CLO test and polymerase chain reaction for biopsy-dependent diagnosis of Helicobacter pylori infection.Zhonghua Min Guo Wei Sheng Wu Ji Mian Yi Xue Za Zhi. 1997; 30: 219-227
- 13C-urea breath test during hospitalization for the diagnosis of Helicobacter pylori infection in peptic ulcer bleeding.Helicobacter. 2007; 12: 231-237
- The endoscopic predictors of Helicobacter pylori status: a meta-analysis of diagnostic performance.Ther Adv Gastrointest Endosc. 2020;
- Screening of gastric cancer in Asia.Best Pract Res Clin Gastroenterol. 2015; 29: 895-905
- Accuracy of endoscopic diagnosis of Helicobacter pylori infection according to level of endoscopic experience and the effect of training.BMC Gastroenterol. 2013; 13: 128
- 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; 22e21983
- Systematic review and meta-analysis: artificial intelligence for the diagnosis of gastric precancerous lesions and Helicobacter pylori infection.Dig Liver Dis. 2022;
- Application of convolutional neural networks for evaluating Helicobacter pylori infection status on the basis of endoscopic images.Scand J Gastroenterol. 2019; 54: 158-163
- Potential of automatic diagnosis system with linked color imaging for diagnosis of Helicobacter pylori infection.Dig Endosc. 2020; 32: 373-381
- Endoscopic three-categorical diagnosis of Helicobacter pylori infection using linked color imaging and deep learning: a single-center prospective study (with video).Gastric Cancer. 2020; 23: 1033-1040
- Survey on deep learning with class imbalance.J Big Data. 2019; 6: 27
- Balancing class for performance of classification with a clinical dataset.Lecture Notes Engineer Comput Sci. 2014; 1: 237-242
Szegedy C, Vanhoucke V, Ioffe S, et al. Rethinking the inception architecture for computer vision. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2016. p. 2818-26.
- Current status and future perspective of artificial intelligence applications in endoscopic diagnosis and management of gastric cancer.Dig Endosc. 2021; 33: 263-272
- SciPy 1.0: fundamental algorithms for scientific computing in Python.Nat Methods. 2020; 17: 261-272
- Application of convolutional neural networks in the diagnosis of Helicobacter pylori infection based on endoscopic images.EBioMed. 2017; 25: 106-111
- Convolutional neural networks in the computer-aided diagnosis of Helicobacter pylori infection and non-causal comparison to physician endoscopists: a systematic review with meta-analysis.Ann Gastroenterol. 2021; 34: 20-25
- Validity of endoscopic features for the diagnosis of Helicobacter pylori infection status based on the Kyoto classification of gastritis.Dig Endosc. 2020; 32: 74-83
- Helicobacter pylori eradication: Exploring its impacts on the gastric mucosa.World J Gastroenterol. 2021; 27: 5152-5170
- Diagnostic accuracy of H. pylori status by conventional endoscopy: time-trend change after eradication and impact of endoscopic image quality.Front Med. 2021; 8830730
- Reinfection rate and endoscopic changes after successful eradication of Helicobacter pylori.World J Gastroenterol. 2010; 16: 251-255
- The false hope of current approaches to explainable artificial intelligence in health care.Lancet Digit Health. 2021; 3: e745-e750
- Global prevalence of Helicobacter pylori infection: systematic review and meta-analysis.Gastroenterology. 2017; 153: 420-429
- Endoscopic and histological findings among Israeli populations infected with Helicobacter pylori: Does ethnicity matter?.Isr Med Assoc J. 2019; 21: 339-344
- Impact of Helicobacter pylori CagA diversity on gastric mucosal damage: an immunohistochemical study of East-Asian-type CagA.J Gastroenterol Hepatol. 2011; 26: 688-693
- Ten-year prospective follow-up study on the relationship between Helicobacter pylori infection and progression of atrophic gastritis, particularly assessed by endoscopic findings.Aliment Pharmacol Ther. 2002; 16: 198-203
Article info
Publication history
Published online: January 11, 2023
Accepted:
January 9,
2023
Received:
November 7,
2022
Publication stage
In Press Journal Pre-ProofFootnotes
DISCLOSURE: The following authors disclosed financial relationships: H. Hong, W.-S. Ryu, D. Kim: Full-time employer JLK Inc. All other authors disclosed no financial relationships. Research support for this study (M-S. Kwak) was provided by the Seoul National University Hospital Gangnam Center Research Fund (grant no. 2020-01).
Identification
Copyright
© 2023 by the American Society for Gastrointestinal Endoscopy
