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
. 2024 Dec 22;9(12):783.
doi: 10.3390/biomimetics9120783.

Edge Artificial Intelligence Device in Real-Time Endoscopy for Classification of Gastric Neoplasms: Development and Validation Study

Eun Jeong Gong  1   2   3 , Chang Seok Bang  1   2   3   4 , Jae Jun Lee  3   4   5
Affiliations

Edge Artificial Intelligence Device in Real-Time Endoscopy for Classification of Gastric Neoplasms: Development and Validation Study

Eun Jeong Gong et al. Biomimetics (Basel). .

Abstract

Objective: We previously developed artificial intelligence (AI) diagnosis algorithms for predicting the six classes of stomach lesions. However, this required significant computational resources. The incorporation of AI into medical devices has evolved from centralized models to decentralized edge computing devices. In this study, a deep learning endoscopic image classification model was created to automatically categorize all phases of gastric carcinogenesis using an edge computing device.

Design: A total of 15,910 endoscopic images were collected retrospectively and randomly assigned to train, validation, and internal-test datasets in an 8:1:1 ratio. The major outcomes were as follows: 1. lesion classification accuracy in six categories: normal/atrophy/intestinal metaplasia/dysplasia/early/advanced gastric cancer; and 2. the prospective evaluation of classification accuracy in real-world procedures.

Results: The internal-test lesion-classification accuracy was 93.8% (95% confidence interval: 93.4-94.2%); precision was 88.6%, recall was 88.3%, and F1 score was 88.4%. For the prospective performance test, the established model attained an accuracy of 93.3% (91.5-95.1%). The established model's lesion classification inference speed was 2-3 ms on GPU and 5-6 ms on CPU. The expert endoscopists reported no delays in lesion classification or any interference from the deep learning model throughout their exams.

Conclusions: We established a deep learning endoscopic image classification model to automatically classify all stages of gastric carcinogenesis using an edge computing device.

Keywords: deep learning; edge computing; endoscopy; gastric neoplasms.

PubMed Disclaimer

Conflict of interest statement

The authors disclose no conflicts of interest.

Figures

Figure 1
Figure 1
Scheme of the algorithm.
Figure 2
Figure 2
Confusion matrix for the internal test.
Figure 3
Figure 3
Confusion matrix for the prospective validation test.
Figure 4
Figure 4
Representative images of attention map analysis.
See this image and copyright information in PMC

Similar articles

See all similar articles

References

    1. Kim I.-H., Kang S.J., Choi M., Kim B.-H., Eom B.W., Kim B.J., Min B.-H., Choi C.I., Shin C.M., Tae C.H., et al. Korean Practice Guidelines for Gastric Cancer 2022: An Evidence-based, Multidisciplinary Approach. J. Gastric Cancer. 2023;23:3–106. doi: 10.5230/jgc.2023.23.e11. Corrected in J. Gastric Cancer 2023, 23, 365. - DOI - PMC - PubMed
    1. Kim J.H., Oh S.I., Han S.Y., Keum J.S., Kim K.N., Chun J.Y., Youn Y.H., Park H. An Optimal Artificial Intelligence System for Re-al-Time Endoscopic Prediction of Invasion Depth in Early Gastric Cancer. Cancers. 2022;14:6000. doi: 10.3390/cancers14236000. - DOI - PMC - PubMed
    1. Nam S.J., Moon G., Park J.H., Kim Y., Lim Y.J., Choi H.S. Deep Learning-Based Real-Time Organ Localization and Transit Time Estimation in Wireless Capsule Endoscopy. Biomedicines. 2024;12:1704. - PMC - PubMed
    1. Gong E.J., Bang C.S., Lee J.J., Jeong H.M., Baik G.H., Jeong J.H., Dick S., Lee G.H. Clinical Decision Support System for All Stages of Gastric Carcinogenesis in Real-Time En-doscopy: Model Establishment and Validation Study. J. Med. Internet Res. 2023;25:e50448. doi: 10.2196/50448. - DOI - PMC - PubMed
    1. Lee J.W., Woo D., Kim K.O., Kim S.K., Lee H.S., Kang B., Lee Y.J., Kim J., Jang B.I., Kim E.Y., et al. Deep Learning Model Using Stool Pictures for Predicting Endoscopic Mucosal Inflammation in Patients With Ulcerative Colitis. Am. J. Gastroenterol. 2024 doi: 10.14309/ajg.0000000000002978. online ahead of print . - DOI - PMC - PubMed

LinkOut - more resources