Advertisement

Journal of Gastroenterology

, Volume 54, Issue 4, pp 321–329 | Cite as

Detection of gastritis by a deep convolutional neural network from double-contrast upper gastrointestinal barium X-ray radiography

  • Ren Togo
  • Nobutake Yamamichi
  • Katsuhiro MabeEmail author
  • Yu Takahashi
  • Chihiro Takeuchi
  • Mototsugu Kato
  • Naoya Sakamoto
  • Kenta Ishihara
  • Takahiro Ogawa
  • Miki Haseyama
Original Article—Alimentary Tract

Abstract

Background

Deep learning has become a new trend of image recognition tasks in the field of medicine. We developed an automated gastritis detection system using double-contrast upper gastrointestinal barium X-ray radiography.

Methods

A total of 6520 gastric X-ray images obtained from 815 subjects were analyzed. We designed a deep convolutional neural network (DCNN)-based gastritis detection scheme and evaluated the effectiveness of our method. The detection performance of our method was compared with that of ABC (D) stratification.

Results

Sensitivity, specificity, and harmonic mean of sensitivity and specificity of our method were 0.962, 0.983, and 0.972, respectively, and those of ABC (D) stratification were 0.925, 0.998, and 0.960, respectively. Although there were 18 false negative cases in ABC (D) stratification, 14 of those 18 cases were correctly classified into the positive group by our method.

Conclusions

Deep learning techniques may be effective for evaluation of gastritis/non-gastritis. Collaborative use of DCNN-based gastritis detection systems and ABC (D) stratification will provide more reliable gastric cancer risk information.

Keywords

Deep convolutional neural network Artificial intelligence Gastritis Double-contrast upper gastrointestinal barium X-ray radiography 

Abbreviations

DCNN

Deep convolutional neural network

Ha

Harmonic mean

H. pylori

Helicobacter pylori

PG

Pepsinogen

ROC curve

Receiver operating characteristic curve

ROI

Region of interest

Se

Sensitivity

Sp

Specificity

UGI-ES

Upper gastrointestinal endoscopy

UGI-XR

Double-contrast upper gastrointestinal barium X-ray radiography

Notes

Acknowledgements

The clinical data were acquired at The University of Tokyo Hospital in Japan. This study was partly supported by Global Station for Big Data and Cybersecurity, a project of Global Institution for Collaborative Research and Education at Hokkaido University JSPS KAKENHI Grant number JP17H01744.

Compliance with ethical standards

Conflict of interest

The authors declare that they have no conflict of interest

References

  1. 1.
    Ferlay J, Soerjomataram I, Dikshit R, et al. Cancer incidence and mortality worldwide: sources, methods and major patterns in GLOBOCAN 2012: Globocan 2012. Int J Cancer. 2015;136:E359–86.CrossRefGoogle Scholar
  2. 2.
    Jung K-W, Won Y-J, Kong H-J, et al. Cancer statistics in Korea: incidence, mortality, survival, and prevalence in 2012. Cancer Res Treat. 2015;47:127–41.CrossRefGoogle Scholar
  3. 3.
    The EUROGAST Study Group. An international association between Helicobacter pylori infection and gastric cancer. Lancet Elsevier. 1993;341:1359–63.CrossRefGoogle Scholar
  4. 4.
    Shimoyama T, Aoki M, Sasaki Y, et al. ABC screening for gastric cancer is not applicable in a Japanese population with high prevalence of atrophic gastritis. Gastric Cancer. 2012;15:331–4.CrossRefGoogle Scholar
  5. 5.
    Zhu R, Chen K, Zheng Y-Y, et al. Meta-analysis of the efficacy of probiotics in Helicobacter pylori eradication therapy. World J Gastroenterol. Baishideng Publishing Group Inc. 2014;20:18013–21.CrossRefGoogle Scholar
  6. 6.
    Kudo T, Kakizaki S, Sohara N, et al. Analysis of ABC (D) stratification for screening patients with gastric cancer. World J Gastroenterol. Baishideng Publishing Group Inc. 2011;17:4793–8.CrossRefGoogle Scholar
  7. 7.
    Miura K, Okada H, Kouno Y, et al. Actual status of involvement of Helicobacter pylori infection that developed gastric cancer from group A of ABC (D) stratification—study of early gastric cancer cases that underwent endoscopic submucosal dissection. Digestion Karger Publishers. 2016;94:17–23.CrossRefGoogle Scholar
  8. 8.
    Oshima A, Hirata N, Ubukata T, et al. Evaluation of a mass screening program for stomach cancer with a case–control study design. Int J Cancer. Wiley Subscription Services, Inc., A Wiley Company. 1986;38:829–33.Google Scholar
  9. 9.
    Krizhevsky A, Sutskever I, Hinton GE. ImageNet classification with deep convolutional neural networks. In: Proceedings of the 25th international conference on neural information processing systems. Lake Tahoe, Nevada: Curran Associates Inc.; 2012. pp. 1097–105.Google Scholar
  10. 10.
    Suzuki K. Overview of deep learning in medical imaging. Radiol Phys Technol. 2017;10:257–73.CrossRefGoogle Scholar
  11. 11.
    LeCun Yann, Bengio Yoshua, Hinton Geoffrey. Deep learning. Nature. 2015;521:436–44.CrossRefGoogle Scholar
  12. 12.
    Yamamichi N, Hirano C, Takahashi Y, et al. Comparative analysis of upper gastrointestinal endoscopy, double-contrast upper gastrointestinal barium X-ray radiography, and the titer of serum anti-Helicobacter pylori IgG focusing on the diagnosis of atrophic gastritis. Gastric Cancer. Springer Japan. 2016;19:670–5.CrossRefGoogle Scholar
  13. 13.
    Itoh T, Saito M, Marugami N, et al. Correlation between the ABC classification and radiological findings for assessing gastric cancer risk. Jpn J Radiol. Springer Japan. 2015;33:636–44.CrossRefGoogle Scholar
  14. 14.
    Dheer S, Levine MS, Redfern RO, et al. Radiographically diagnosed antral gastritis: findings in patients with and without Helicobacter pylori infection. Br J Radiol. British Institute of Radiology. 2002;75:805–11.CrossRefGoogle Scholar
  15. 15.
    Kimura K, Takemoto T. An endoscopic recognition of the atrophic border and its significance in chronic gastritis. Endoscopy. © Georg Thieme Verlag, Stuttgart. 1969;1:87–97.Google Scholar
  16. 16.
    Kimura K. Chronological transition of the fundic-pyloric border determined by stepwise biopsy of the lesser and greater curvatures of the stomach. Gastroenterology. 1972;63:584–92.Google Scholar
  17. 17.
    Cortes C. Support-vector networks. Mach Learn Springer. 1995;20:273–97.Google Scholar
  18. 18.
    Otsu N. A threshold selection method from gray-level. IEEE Trans Syst Man Cybern. 1979;9:62–6.CrossRefGoogle Scholar
  19. 19.
    Venegas-Barrera CS, Manjarrez J. Visual categorization with bags of keypoints. In: Workshop on statistical learning in computer vision, ECCV. 2004.Google Scholar
  20. 20.
    Jia Y, Shelhamer E, Caffe DJ. Caffe: convolutional architecture for fast feature embedding. In: Proceedings of the 22nd ACM international conference on multimedia. Orlando, Florida, USA: ACM; 2014. pp. 675–8.Google Scholar
  21. 21.
    Litjens G, Kooi T, Bejnordi BE, et al. A survey on deep learning in medical image analysis. Med Image Anal. 2017;42:60–88.CrossRefGoogle Scholar
  22. 22.
    Sugano K. Screening of gastric cancer in Asia. Best Pract Res Clin Gastroenterol. Baillière Tindall. 2015;29:895–905.CrossRefGoogle Scholar
  23. 23.
    Lakhani P, Sundaram B. Deep learning at chest radiography: automated classification of pulmonary tuberculosis by using convolutional neural networks. Radiology. Radiological Society of North America. 2017;284:574–82.Google Scholar
  24. 24.
    Kim KH, Choi SH, Park S-H. Improving arterial spin labeling by using deep learning. Radiology. Radiological Society of North America. 2018;287:658–66.Google Scholar
  25. 25.
    Larson DB, Chen MC, Lungren MP, et al. Performance of a deep-learning neural network model in assessing skeletal maturity on pediatric hand radiographs. Radiology. Radiological Society of North America. 2018;287:313–22.Google Scholar
  26. 26.
    Ishihara K, Ogawa T, Haseyama M. Classification of gastric cancer risk from X-ray images based on efficient image features related to serum Hp antibody level and serum PG levels. ITE Trans Media Technol Appl. 2016;4:337–48.CrossRefGoogle Scholar
  27. 27.
    Ishihara K, Ogawa T, Haseyama M. Helicobacter pylori infection detection from gastric X-ray images based on feature fusion and decision fusion. Comput Biol Med. Elsevier Ltd. 2017;84:69–78.CrossRefGoogle Scholar
  28. 28.
    Togo R, Ishihara K, Mabe K, et al. Preliminary study of automatic gastric cancer risk classification from photofluorography. World J Gastrointest Oncol Febr World J Gastrointest Oncol. 2018;15:62–70.CrossRefGoogle Scholar

Copyright information

© Japanese Society of Gastroenterology 2018

Authors and Affiliations

  • Ren Togo
    • 1
  • Nobutake Yamamichi
    • 2
  • Katsuhiro Mabe
    • 3
    Email author
  • Yu Takahashi
    • 2
  • Chihiro Takeuchi
    • 2
  • Mototsugu Kato
    • 3
  • Naoya Sakamoto
    • 4
  • Kenta Ishihara
    • 1
  • Takahiro Ogawa
    • 1
  • Miki Haseyama
    • 1
  1. 1.Graduate School of Information Science and TechnologyHokkaido UniversitySapporoJapan
  2. 2.Department of Gastroenterology, Graduate School of MedicineThe University of TokyoTokyoJapan
  3. 3.Department of GastroenterologyNational Hospital Organization Hakodate HospitalHakodate CityJapan
  4. 4.Department of GastroenterologyHokkaido University Graduate School of MedicineSapporoJapan

Personalised recommendations