Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
Comment
. 2021 Jun;70(6):1196-1198.
doi: 10.1136/gutjnl-2020-322453. Epub 2020 Aug 18.

Challenging detection of hard-to-find gastric cancers with artificial intelligence-assisted endoscopy

Daisuke Murakami  1   2 , Masayuki Yamato  2 , Yuji Amano  3 , Tomohiro Tada  4   5
Affiliations
Comment

Challenging detection of hard-to-find gastric cancers with artificial intelligence-assisted endoscopy

Daisuke Murakami et al. Gut. 2021 Jun.
No abstract available

Keywords: endoscopy; gastric cancer; gastric neoplasia.

PubMed Disclaimer

Conflict of interest statement

Competing interests: TT is a shareholder of AI Medical Service and YA received the lecture fee from Takeda Pharmaceutical.

Figures

Figure 1
Figure 1
A minute gastric cancer (GC, 3 mm in major diameter) identified in follow-up oesophagogastroduodenoscopy (OGD) from a patient after eradication of Helicobacter pylori (HP) infection. (A) A minute GC in white light images (WLI) (arrow) that neither the expert nor our artificial intelligence (AI) system could detect is barely discoverable in retrospective inspection. (B) Our AI method detected a minute lesion in a non-magnified view of narrow band imaging (NBI)(blue rectangular frame), confirming what the expert identified during an actual OGD procedure: GCs were recognised as light-brownish areas in surrounding green epithelium by NBI non-enlargement observation facilitated GC detection after eradication. (C) A slight lesion depression was enhanced by indigo carmine (IC) spraying, and our AI was also able to detect it (blue rectangular frame).
See this image and copyright information in PMC

Comment on

References

    1. van der Sommen F, de Groof J, Struyvenberg M, et al. . Machine learning in Gi endoscopy: practical guidance in how to interpret a novel field. Gut 2020;69:2035–45. 10.1136/gutjnl-2019-320466 - DOI - PMC - PubMed
    1. Ebigbo A, Mendel R, Probst A, et al. . Computer-Aided diagnosis using deep learning in the evaluation of early oesophageal adenocarcinoma. Gut 2019;68:1143–5. 10.1136/gutjnl-2018-317573 - DOI - PMC - PubMed
    1. Wang P, Berzin TM, Glissen Brown JR, et al. . Real-Time automatic detection system increases colonoscopic polyp and adenoma detection rates: a prospective randomised controlled study. Gut 2019;68:1813–9. 10.1136/gutjnl-2018-317500 - DOI - PMC - PubMed
    1. Menon S, Trudgill N. How commonly is upper gastrointestinal cancer missed at endoscopy? A meta-analysis. Endosc Int Open 2014;2:E46–50. 10.1055/s-0034-1365524 - DOI - PMC - PubMed
    1. Lee HL, Eun CS, Lee OY, et al. . When do we miss synchronous gastric neoplasms with endoscopy? Gastrointest Endosc 2010;71:1159–65. 10.1016/j.gie.2010.01.011 - DOI - PubMed