Gastric Cancer

, Volume 21, Issue 4, pp 653–660 | Cite as

Application of artificial intelligence using a convolutional neural network for detecting gastric cancer in endoscopic images

  • Toshiaki Hirasawa
  • Kazuharu Aoyama
  • Tetsuya Tanimoto
  • Soichiro Ishihara
  • Satoki Shichijo
  • Tsuyoshi Ozawa
  • Tatsuya Ohnishi
  • Mitsuhiro Fujishiro
  • Keigo Matsuo
  • Junko Fujisaki
  • Tomohiro Tada
Original Article



Image recognition using artificial intelligence with deep learning through convolutional neural networks (CNNs) has dramatically improved and been increasingly applied to medical fields for diagnostic imaging. We developed a CNN that can automatically detect gastric cancer in endoscopic images.


A CNN-based diagnostic system was constructed based on Single Shot MultiBox Detector architecture and trained using 13,584 endoscopic images of gastric cancer. To evaluate the diagnostic accuracy, an independent test set of 2296 stomach images collected from 69 consecutive patients with 77 gastric cancer lesions was applied to the constructed CNN.


The CNN required 47 s to analyze 2296 test images. The CNN correctly diagnosed 71 of 77 gastric cancer lesions with an overall sensitivity of 92.2%, and 161 non-cancerous lesions were detected as gastric cancer, resulting in a positive predictive value of 30.6%. Seventy of the 71 lesions (98.6%) with a diameter of 6 mm or more as well as all invasive cancers were correctly detected. All missed lesions were superficially depressed and differentiated-type intramucosal cancers that were difficult to distinguish from gastritis even for experienced endoscopists. Nearly half of the false-positive lesions were gastritis with changes in color tone or an irregular mucosal surface.


The constructed CNN system for detecting gastric cancer could process numerous stored endoscopic images in a very short time with a clinically relevant diagnostic ability. It may be well applicable to daily clinical practice to reduce the burden of endoscopists.


Stomach neoplasms Neural networks (computer) Artificial intelligence Endoscopy 



The authors thank Yuma Endo and other engineers at AI Medical Service, Inc. (Tokyo, Japan), for their cooperation in developing the CNN.

Author contributions

Study concept and design (TH, KA, TT, SI and TT), acquisition of data (TH, SS, TO, TO, KM and TT), analysis and interpretation of data (TH, KA, TT, SI and TT), drafting of the manuscript (TH, KA, TT, SI, SS, TO, MF, JF and TT)

Compliance with ethical standards

Conflict of interest

The authors declare that they have no conflict of interest.

Ethical standards

All procedures followed were in accordance with the ethical standards of the responsible committee on human experimentation (institutional and national) and with the Helsinki Declaration of 1964 and later versions. Informed consent or substitute for it was obtained from all patients for being included in the study.


  1. 1.
    GLOBOCAN 2012. Available from: on 28 April 2017.
  2. 2.
    Sano T, Coit DG, Kim HH, Roviello F, Kassab P, Wittekind C, et al. Proposal of a new stage grouping of gastric cancer for TNM classification: international Gastric Cancer Association staging project. Gastric Cancer. 2017;20:217–25.CrossRefPubMedGoogle Scholar
  3. 3.
    Katai H, Ishikawa T, Akazawa K, Isobe Y, Miyashiro I, Oda I, et al. Five-year survival analysis of surgically resected gastric cancer cases in Japan: a retrospective analysis of more than 100,000 patients from the nationwide registry of the Japanese Gastric Cancer Association (2001–2007). Gastric Cancer. 2017. (Epub ahead of print).CrossRefPubMedGoogle Scholar
  4. 4.
    Itoh H, Oohata Y, Nakamura K, Nagata T, Mibu R, Nakayama F. Complete ten-year postgastrectomy follow-up of early gastric cancer. Am J Surg. 1989;158:14–6.CrossRefPubMedGoogle Scholar
  5. 5.
    Crew KD, Neugut AI. Epidemiology of gastric cancer. World J Gastroenterol. 2006;12:354–62.CrossRefPubMedPubMedCentralGoogle Scholar
  6. 6.
    Tsubono Y, Hisamichi S. Screening for gastric cancer in Japan. Gastric Cancer. 2000;3:9–18.CrossRefPubMedGoogle Scholar
  7. 7.
    Yeoh KG. How do we improve outcomes for gastric cancer? J Gastroenterol Hepatol. 2007;22:970–2.CrossRefPubMedGoogle Scholar
  8. 8.
    Jeon HK, Kim GH, Lee BE, Park DY, Song GA, Kim DH, et al. Long-term outcome of endoscopic submucosal dissection is comparable to that of surgery for early gastric cancer: a propensity-matched analysis. Gastric Cancer. 2017. (Epub ahead of print).CrossRefPubMedGoogle Scholar
  9. 9.
    Isomoto H, Shikuwa S, Yamaguchi N, Fukuda E, Ikeda K, Nishiyama H, et al. Endoscopic submucosal dissection for early gastric cancer: a large-scale feasibility study. Gut. 2009;58:331–6.CrossRefPubMedGoogle Scholar
  10. 10.
    Choi MK, Kim GH, Park DY, Song GA, Kim DU, Ryu DY, et al. Long-term outcomes of endoscopic submucosal dissection for early gastric cancer: a single-center experience. Surg Endosc. 2013;27:4250–8.CrossRefPubMedGoogle Scholar
  11. 11.
    Ahn JY, Jung HY. Long-term outcome of extended endoscopic submucosal dissection for early gastric cancer with differentiated histology. Clin Endosc. 2013;46:463–6.CrossRefPubMedPubMedCentralGoogle Scholar
  12. 12.
    Gotoda T, Iwasaki M, Kusano C, Seewald S, Oda I. Endoscopic resection of early gastric cancer treated by guideline and expanded National Cancer Centre criteria. Br J Surg. 2010;97:868–71.CrossRefPubMedGoogle Scholar
  13. 13.
    Menon S, Trudgill N. How commonly is upper gastrointestinal cancer missed at endoscopy?A meta-analysis. Endosc Int Open. 2014;2:E46–50.CrossRefPubMedPubMedCentralGoogle Scholar
  14. 14.
    Hosokawa O, Hattori M, Douden K, Hayashi H, Ohta K, Kaizaki Y. Difference in accuracy between gastroscopy and colonoscopy for detection of cancer. Hepatogastroenterology. 2007;54:442–4.PubMedGoogle Scholar
  15. 15.
    Hosokawa O, Tsuda S, Kidani E, Watanabe K, Tanigawa Y, Shirasaki S, et al. Diagnosis of gastric cancer up to three years after negative upper gastrointestinal endoscopy. Endoscopy. 1998;30:669–74.CrossRefPubMedGoogle Scholar
  16. 16.
    Amin A, Gilmour H, Graham L, Paterson-Brown S, Terrace J, Crofts TJ. Gastric adenocarcinoma missed at endoscopy. J R Coll Surg Edinb. 2002;47:681–4.PubMedGoogle Scholar
  17. 17.
    Yalamarthi S, Witherspoon P, McCole D, Auld CD. Missed diagnoses in patients with upper gastrointestinal cancers. Endoscopy. 2004;36:874–9.CrossRefPubMedGoogle Scholar
  18. 18.
    Voutilainen ME, Juhola MT. Evaluation of the diagnostic accuracy of gastroscopy to detect gastric tumours: clinicopathological features and prognosis of patients with gastric cancer missed on endoscopy. Eur J Gastroenterol Hepatol. 2005;17:1345–9.CrossRefPubMedGoogle Scholar
  19. 19.
    Zhang Q, Chen ZY, Chen CD, Liu T, Tang XW, Ren YT, et al. Training in early gastric cancer diagnosis improves the detection rate of early gastric cancer: an observational study in China. Medicine (Baltimore). 2015;94:e384.CrossRefGoogle Scholar
  20. 20.
    Yamazato T, Oyama T, Yoshida T, Baba Y, Yamanouchi K, Ishii Y, et al. Two years’ intensive training in endoscopic diagnosis facilitates detection of early gastric cancer. Intern Med. 2012;51:1461–5.CrossRefPubMedGoogle Scholar
  21. 21.
    Yoshida S, Yamaguchi H, Tajiri H, Saito D, Hijikata A, Yoshimori M, et al. Diagnosis of early gastric cancer seen as less malignant endoscopically. Jpn J Clin Oncol. 1984;14:225–41.PubMedGoogle Scholar
  22. 22.
    Esteva A, Kuprel B, Novoa RA, Ko J, Swetter SM, Blau HM, et al. Dermatologist-level classification of skin cancer with deep neural networks. Nature. 2017;542:115–8.CrossRefPubMedGoogle Scholar
  23. 23.
    Bibault JE, Giraud P, Burgun A. Big Data and machine learning in radiation oncology: state of the art and future prospects. Cancer Lett. 2016;382:110–7.CrossRefPubMedGoogle Scholar
  24. 24.
    Gulshan V, Peng L, Coram M, Stumpe MC, Wu D, Narayanaswamy A, et al. Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs. JAMA. 2016;316:2402–10.CrossRefPubMedGoogle Scholar
  25. 25.
    Misawa M, Kudo SE, Mori Y, Takeda K, Maeda Y, Kataoka S, et al. Accuracy of computer-aided diagnosis based on narrow-band imaging endocytoscopy for diagnosing colorectal lesions: comparison with experts. Int J Comput Assist Radiol Surg. 2017;12:757–66.CrossRefPubMedGoogle Scholar
  26. 26.
    Yoshida H, Shimazu T, Kiyuna T, Marugame A, Yamashita Y, Cosatto E, et al. Automated histological classification of whole-slide images of gastric biopsy specimens. Gastric Cancer. 2017. Scholar
  27. 27.
    Krizhevsky A, Sutskever I, Hinton GE. ImageNet classification with deep convolutional neural networks. In: Proceeding NIPS'12 Proceedings of the 25th International Conference on Neural Information Processing Systems, vol. 1. Lake Tahoe, Nevada; 2012. pp. 1097–105.
  28. 28.
    Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, et al.: Going deeper with convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2015:1–9.Google Scholar
  29. 29.
    Deng, J. Dong W, Socher R, Li L, Li K, Fei-Fei L. Imagenet: A large-scale hierarchical image database. In: EEE Conference on Computer Vision and Pattern Recognition. 2009:248–55.Google Scholar
  30. 30.
    Fujita S. Biology of early gastric carcinoma. Pathol Res Pract. 1978;163:297–309.CrossRefPubMedGoogle Scholar
  31. 31.
    Yoshimizu S, Yamamoto Y, Horiuchi Y, Omae M, Yoshio T, Ishiyama A, et al. Diagnostic performance of routine esophagogastroduodenoscopy using magnifying endoscope with narrow-band imaging for gastric cancer. Dig Endosc. 2017. (Epub ahead of print).CrossRefPubMedGoogle Scholar
  32. 32.
    Yao K, Doyama H, Gotoda T, Ishikawa H, Nagahama T, Yokoi C, et al. Diagnostic performance and limitations of magnifying narrow-band imaging in screening endoscopy of early gastric cancer: a prospective multicenter feasibility study. Gastric Cancer. 2014;17:669–79.CrossRefPubMedGoogle Scholar
  33. 33.
    Gotoda T, Uedo N, Yoshinaga S, Tanuma T, Morita Y, Doyama H, et al. Basic principles and practice of gastric cancer screening using high-definition white-light gastroscopy: eyes can only see what the brain knows. Dig Endosc. 2016;28(Suppl 1):2–15.CrossRefPubMedGoogle Scholar
  34. 34.
    Japanese Gastric Cancer Association. Japanese classification of gastric carcinoma. Gastric Cancer. 2011;14:101–12 (3rd English edition).CrossRefGoogle Scholar
  35. 35.
    Kimura K, Takemoto T. An endoscopic recognition of the atrophic border and its significance in chronic gastritis. Endoscopy. 1969;1:87–97.CrossRefGoogle Scholar

Copyright information

© The International Gastric Cancer Association and The Japanese Gastric Cancer Association 2018

Authors and Affiliations

  • Toshiaki Hirasawa
    • 1
    • 2
  • Kazuharu Aoyama
    • 3
  • Tetsuya Tanimoto
    • 4
    • 5
  • Soichiro Ishihara
    • 2
    • 6
  • Satoki Shichijo
    • 7
  • Tsuyoshi Ozawa
    • 2
    • 6
  • Tatsuya Ohnishi
    • 8
  • Mitsuhiro Fujishiro
    • 9
  • Keigo Matsuo
    • 10
  • Junko Fujisaki
    • 1
  • Tomohiro Tada
    • 2
    • 3
    • 11
  1. 1.Department of GastroenterologyCancer Institute Hospital Ariake, Japanese Foundation for Cancer ResearchTokyoJapan
  2. 2.Tada Tomohiro Institute of Gastroenterology and ProctologySaitamaJapan
  3. 3.AI Medical Service Inc.TokyoJapan
  4. 4.Medical Governance Research InstituteTokyoJapan
  5. 5.Navitas ClinicTokyoJapan
  6. 6.Surgery Department, Sanno HospitalInternational University of Health and WelfareTokyoJapan
  7. 7.Department of Gastrointestinal OncologyOsaka International Cancer InstituteOsakaJapan
  8. 8.Lalaport Yokohama ClinicKanagawaJapan
  9. 9.Department of Gastroenterology, Graduate School of MedicineThe University of TokyoTokyoJapan
  10. 10.Department of ColoproctologyTokatsu-Tsujinaka HospitalChibaJapan
  11. 11.Department of Surgical Oncology, Graduate School of MedicineThe University of TokyoTokyoJapan

Personalised recommendations