Skip to main content

Adoption value of deep learning and serological indicators in the screening of atrophic gastritis based on artificial intelligence


This work aimed to improve the early clinical diagnosis rate of atrophic gastritis (AG) and reduce the risk of disease deterioration or cancerization. Three hundred and eight patients with gastric disease were taken as the research object, who were divided into two groups: AG (n = 159) and non-AG (n = 149), according to the diagnosis results. The gastric antrum images of patients were collected, and the DenseNet model for gastric antrum image lesion screening was improved. Then, the differences in serum pepsinogen (PG I and PG II) of patients were detected, and the efficiency of different methods to screen AG was compared. The results revealed that the levels of PG I and PG II in AG patients were substantially reduced, and the sensitivity (70.44%), specificity (66.44%), and accuracy (68.51%) of AG diagnosis by indicator PG I were higher than that of PG II and joint diagnosis. The diagnosis accuracy rate of AG based on the improved DenseNet model was 98.63%. The accuracy of model recognition combined with serological indicators for disease diagnosis was as high as 99.25%, with a sensitivity of 96.17% and a specificity of 94.33%. In summary, the combination of deep learning-based image recognition methods and serological specific indicators could improve the clinical diagnosis rate of AG, which could provide a reference for the subsequent clinical adoption of artificial intelligence recognition technology.

This is a preview of subscription content, access via your institution.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12


  1. 1.

    Yao F, Shi CL, Liu CC et al (2017) Economic burden of stomach cancer in China during 1996–2015: a systematic review. Zhonghua Yu Fang Yi Xue Za Zhi 51(8):756–762

    Google Scholar 

  2. 2.

    Venneman K, Huybrechts I, Gunter MJ et al (2018) The epidemiology of Helicobacter pylori infection in Europe and the impact of lifestyle on its natural evolution toward stomach cancer after infection: a systematic review. Helicobacter 23(3):e12483

    Article  Google Scholar 

  3. 3.

    Li Y, Xia R, Zhang B, Li C (2018) Chronic atrophic gastritis: a review. J Environ Pathol Toxicol Oncol 37(3):241–259

    Article  Google Scholar 

  4. 4.

    Rodriguez-Castro KI, Franceschi M, Miraglia C et al (2018) Autoimmune diseases in autoimmune atrophic gastritis. Acta Biomed 89(8):100–103

    Google Scholar 

  5. 5.

    Tahara S, Tahara T, Horiguchi N et al (2019) DNA methylation accumulation in gastric mucosa adjacent to cancer after Helicobacter pylori eradication. Int J Cancer 144(1):80–88

    Article  Google Scholar 

  6. 6.

    Xuan Y, Hur H, Byun CS et al (2013) Efficacy of intraoperative gastroscopy for tumor localization in totally laparoscopic distal gastrectomy for cancer in the middle third of the stomach. Surg Endosc 27(11):4364–4370

    Article  Google Scholar 

  7. 7.

    Thillaikkarasi R, Saravanan S (2019) An enhancement of deep learning algorithm for brain tumor segmentation using kernel based CNN with M-SVM. J Med Syst 43(4):84

    Article  Google Scholar 

  8. 8.

    Hussain S, Anwar SM, Majid M (2017) Brain tumor segmentation using cascaded deep convolutional neural network. Annu Int Conf IEEE Eng Med Biol Soc 2017:1998–2001

    Google Scholar 

  9. 9.

    Yamaguchi Y, Nagata Y, Hiratsuka R et al (2016) Gastric cancer screening by combined assay for serum anti-Helicobacter pylori IgG antibody and serum pepsinogen levels-the ABC method. Digestion 93(1):13–18

    Article  Google Scholar 

  10. 10.

    Leja M, Park JY, Murillo R et al (2017) Multicentric randomised study of Helicobacter pylori eradication and pepsinogen testing for prevention of gastric cancer mortality: the GISTAR study. BMJ Open 7(8):e016999

    Article  Google Scholar 

  11. 11.

    Begum A, Baten MA, Begum Z et al (2017) Role of serum pepsinogen I and II ratio in screening of gastric carcinoma. Mymensingh Med J 26(3):628–634

    Google Scholar 

  12. 12.

    Yoon K, Kim N (2018) Reversibility of atrophic gastritis and intestinal metaplasia by eradication of Helicobacter pylori. Korean J Gastroenterol 72(3):104–115

    Article  Google Scholar 

  13. 13.

    Jin EH, Chung SJ, Lim JH (2018) 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 33(15):e117

    Article  Google Scholar 

  14. 14.

    Chapelle N, Petryszyn P, Blin J, Leroy M, Tamara Matysiak〣udnik (2020) A panel of stomach: specific biomarkers (gastropanel) for the diagnosis of atrophic gastritis: a prospective, multicenter study in a low gastric cancer incidence area. Helicobacter 25(5):2020

    Article  Google Scholar 

  15. 15.

    Zagari RM, Rabitti S, Greenwood DC et al (2017) Systematic review with meta-analysis: diagnostic performance of the combination of pepsinogen, gastrin-17 and anti-Helicobacter pylori antibodies serum assays for the diagnosis of atrophic gastritis. Aliment Pharmacol Ther 46(7):657–667

    Article  Google Scholar 

  16. 16.

    Tong Y, Wu Y, Song Z et al (2017) The potential value of serum pepsinogen for the diagnosis of atrophic gastritis among the health check-up populations in China: a diagnostic clinical research. BMC Gastroenterol 17(1):88

    Article  Google Scholar 

  17. 17.

    Cavalcoli F, Zilli A, Conte D, Massironi S (2017) Micronutrient deficiencies in patients with chronic atrophic autoimmune gastritis: A review. World J Gastroenterol 23(4):563–572

    Article  Google Scholar 

  18. 18.

    PérezRomero S, Alberca de Las Parras F, SánchezDelRío A et al (2019) Quality indicators in gastroscopy. Gastroscopy procedure. Rev Esp Enferm Dig 111(9):699–709

    Google Scholar 

  19. 19.

    Nishihara K, Oono Y, Kuwata T et al (2019) Depressed gastric-type adenoma in nonatrophic gastric mucosa without Helicobacter pylori infection. Endoscopy 51(6):E138–E140

    Article  Google Scholar 

  20. 20.

    Grewal PS, Oloumi F, Rubin U, Tennant MTS (2018) Deep learning in ophthalmology: a review. Can J Ophthalmol 53(4):309–313

    Article  Google Scholar 

  21. 21.

    Litjens G, Ciompi F, Wolterink JM et al (2019) State-of-the-art deep learning in cardiovascular image analysis. JACC Cardiovasc Imaging 12(8 Pt 1):1549–1565

    Article  Google Scholar 

  22. 22.

    Kumar M, Alshehri M, Alghamdi R, Sharma P, Deep V (2020) A de-ann inspired skin cancer detection approach using fuzzy c-means clustering. Mobile Netw Appl 25:1319–1329

    Article  Google Scholar 

  23. 23.

    Wang S, Yang DM, Rong R, Zhan X, Xiao G (2019) Pathology image analysis using segmentation deep learning algorithms. Am J Pathol 189(9):1686–1698

    Article  Google Scholar 

  24. 24.

    Sahiner B, Pezeshk A, Hadjiiski LM et al (2019) Deep learning in medical imaging and radiation therapy. Med Phys 46(1):e1–e36

    Article  Google Scholar 

  25. 25.

    Xiao Y, Wu J, Lin Z, Zhao X (2018) A deep learning-based multi-model ensemble method for cancer prediction. Comput Methods Programs Biomed 153:1–9

    Article  Google Scholar 

  26. 26.

    Al-Khafaji SL, Jun Z, Zia A, Liew AW (2018) Spectral-spatial scale invariant feature transform for hyperspectral images. IEEE Trans Image Process 27(2):837–850

    MathSciNet  MATH  Article  Google Scholar 

  27. 27.

    Zhou Q, Zhou Z, Chen C et al (2019) Grading of hepatocellular carcinoma using 3D SE-DenseNet in dynamic enhanced MR images. Comput Biol Med 107:47–57

    Article  Google Scholar 

  28. 28.

    Su W, Zhou B, Qin G et al (2018) Low PG I/II ratio as a marker of atrophic gastritis: association with nutritional and metabolic status in healthy people. Medicine (Baltimore) 97(20):e10820

    Article  Google Scholar 

  29. 29.

    Mansour-Ghanaei F, Joukar F, Baghaee M, Sepehrimanesh M, Hojati A (2019) Only serum pepsinogen I and pepsinogen I/II ratio are specific and sensitive biomarkers for screening of gastric cancer. Biomol Concepts 10(1):82–90

    Article  Google Scholar 

  30. 30.

    Mezmale L, Isajevs S, Bogdanova I et al (2019) Prevalence of atrophic gastritis in Kazakhstan and the accuracy of pepsinogen tests to detect gastric mucosal atrophy. Asian Pac J Cancer Prev 20(12):3825–3829

    Article  Google Scholar 

  31. 31.

    Massarrat S, Haj-Sheykholeslami A (2016) Increased serum pepsinogen II level as a marker of pangastritis and corpus-predominant gastritis in gastric cancer prevention. Arch Iran Med 19(2):137–140

    Google Scholar 

  32. 32.

    Zagari RM, Rabitti S, Greenwood DC, Eusebi LH, Vestito A, Bazzoli F (2017) Systematic review with meta-analysis: diagnostic performance of the combination of pepsinogen, gastrin-17 and anti-Helicobacter pylori antibodies serum assays for the diagnosis of atrophic gastritis. Aliment Pharmacol Ther 46(7):657–667

    Article  Google Scholar 

  33. 33.

    Shao X, Zhang H, Wang Y et al (2020) Deep convolutional neural networks combine Raman spectral signature of serum for prostate cancer bone metastases screening. Nanomedicine 29:102245

    Article  Google Scholar 

  34. 34.

    Guan Q, Wang Y, Ping B et al (2019) Deep convolutional neural network VGG-16 model for differential diagnosing of papillary thyroid carcinomas in cytological images: a pilot study. J Cancer 10(20):4876–4882

    Article  Google Scholar 

  35. 35.

    Dawud AM, Yurtkan K, Oztoprak H (2019) Application of deep learning in neuroradiology: brain haemorrhage classification using transfer learning. Comput Intell Neurosci 2019:4629859

    Article  Google Scholar 

  36. 36.

    Ding Y, Sohn JH, Kawczynski MG et al (2019) A deep learning model to predict a diagnosis of Alzheimer disease by using 18F-FDG PET of the brain. Radiology 290(2):456–464

    Article  Google Scholar 

  37. 37.

    Brito C, Machado A, Sousa A (2019) Electrocardiogram beat-classification based on a ResNet network. Stud Health Technol Inform 264:55–59

    Google Scholar 

  38. 38.

    Cai J, Xing F, Batra A et al (2019) Texture analysis for muscular dystrophy classification in MRI with improved class activation mapping. Pattern Recognit 86:368–375

    Article  Google Scholar 

Download references

Author information



Corresponding author

Correspondence to Xinhua Tian.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Zhang, J., Yu, J., Fu, S. et al. Adoption value of deep learning and serological indicators in the screening of atrophic gastritis based on artificial intelligence. J Supercomput 77, 8674–8693 (2021).

Download citation


  • Atrophic gastritis
  • Deep learning
  • Sinuses ventriculi images
  • Pepsinogen
  • Diagnostic efficiency