Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Video

Updated: Oct 18, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

3.0K

Deep learning-based endoscopic anatomy classification: an accelerated approach for data preparation and model

Yuan-Yen Chang1, Pai-Chi Li1, Ruey-Feng Chang1,2,3

  • 1Graduate Institute of Biomedical Electronics and Bioinformatics, National Taiwan University, Taipei, Taiwan.

Surgical Endoscopy
|September 29, 2021
PubMed
Summary

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Tetrahydrocurcumin Attenuates NaIO<sub>3</sub>-Induced Retinal Oxidative Injury via Suppression of NOX2-Derived ROS-Mediated Apoptosis.

Antioxidants (Basel, Switzerland)·2026
Same author

LiquidGAN for Handwriting-Based Detection and Severity Classification of Extrapyramidal Symptoms.

Sensors (Basel, Switzerland)·2026
Same author

Mechanobiology of the tumor microenvironment: a review of therapeutic interactions and in vitro elasticity measurement techniques.

Journal of biomedical science·2026
Same author

Esophageal Schwannoma: Successful Resection with Endoscopic Submucosal Dissection.

Digestive diseases and sciences·2026
Same author

Dual-Phase Computed Tomography-Based Deep Learning Architecture for Three-Year Survival Prediction in Hepatocellular Carcinoma.

Journal of imaging informatics in medicine·2026
Same author

Ethanol Ablation for Intrahepatic Bile Duct Dilatation in an Elderly Patient: A Case Report.

Journal of medical ultrasound·2026
This summary is machine-generated.

Artificial intelligence enhances endoscopy quality control. A deep learning model accurately classifies endoscopic images, improving performance audits with an accelerated data preparation approach.

Area of Science:

  • Medical technology
  • Artificial intelligence in healthcare
  • Gastroenterology

Background:

  • Photodocumentation quality in endoscopy is hard to measure.
  • Artificial intelligence (AI) offers a solution for performance auditing.
  • AI requires substantial data for model development.

Purpose of the Study:

  • Develop a deep learning-based endoscopic anatomy classification system.
  • Utilize convolutional neural networks (CNNs) for image analysis.
  • Implement an accelerated data preparation approach for model training.

Main Methods:

  • Retrospectively collected 8,041 esophagogastroduodenoscopy (EGD) images.
  • Expert labeling of nine anatomical locations in the upper gastrointestinal tract.
Keywords:
Artificial intelligenceDeep learningEndoscopy anatomy

More Related Videos

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application
05:56

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

2.7K

Related Experiment Videos

Last Updated: Oct 18, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

3.0K
Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application
05:56

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

2.7K
  • Developed and enhanced a CNN model using a multi-stage training approach with additional datasets.

    • Main Results:

    • The base model achieved 96.29% accuracy.
    • The enhanced model reached 96.64% accuracy.
    • The enhanced model showed improved accuracy on internal (93.05-92.74%) and external (92.56%) test datasets.

    Conclusions:

    • A deep learning model was developed for endoscopy quality control.
    • The model utilizes an accelerated data preparation method.
    • High accuracy was achieved and validated on internal and external datasets.