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 Concept Videos

You might also read

Related Articles

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

Sort by
Same author

SMaRT-Net: A novel framework of 7T brain MRI superresolution for Alzheimer's disease diagnosis and mild cognitive impairment prognostication.

NeuroImage·2026
Same author

Metaverse-based objective structured clinical examinations: an exploratory approach to advancing clinical competency assessment.

Korean journal of medical education·2026
Same author

Immersive Virtual Reality Training to Improve Novice Physicians' Emergency Response Skills: Randomized Controlled Trial.

JMIR medical education·2026
Same author

Immersive Virtual Reality Training to Improve Novice Physicians' Emergency Response Skills: A Randomized Controlled Trial.

JMIR medical education·2026
Same author

Association between visceral adipose tissue measured by deep neural network architecture and chronic kidney disease.

Scientific reports·2026
Same author

Body fat percentage is independently associated with lower pulmonary function in Korean never-smokers: A cross-sectional analysis of 33,748 adults.

PloS one·2026

Related Experiment Video

Updated: Jul 6, 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

2.8K

Density clustering-based automatic anatomical section recognition in colonoscopy video using deep learning.

Byeong Soo Kim1, Minwoo Cho2,3,4, Goh Eun Chung5

  • 1Interdisciplinary Program in Bioengineering, Graduate School, Seoul National University, Seoul, 08826, Korea.

Scientific Reports
|January 9, 2024
PubMed
Summary
This summary is machine-generated.

This study introduces a deep learning system to automatically identify colon sections during colonoscopy. The AI model accurately segments anatomical regions, aiding in disease diagnosis and automated reporting.

More Related Videos

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies
04:25

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Published on: December 15, 2023

2.4K
Deep Learning-Based Segmentation of Cryo-Electron Tomograms
10:25

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

8.8K

Related Experiment Videos

Last Updated: Jul 6, 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

2.8K
Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies
04:25

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Published on: December 15, 2023

2.4K
Deep Learning-Based Segmentation of Cryo-Electron Tomograms
10:25

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

8.8K

Area of Science:

  • Medical Imaging
  • Artificial Intelligence in Medicine
  • Gastroenterology

Background:

  • Accurate identification of anatomical sections in colonoscopy is vital for diagnosing colonic diseases and generating precise reports.
  • The colon's deformable nature presents challenges for reliable anatomical localization using current deep learning methods.

Purpose of the Study:

  • To develop and evaluate a novel system for automatic anatomical section recognition during colonoscopy using a combination of deep learning and density clustering.
  • To improve the accuracy and efficiency of colonoscopy reporting through AI-driven anatomical segmentation.

Main Methods:

  • A system was developed using 100 colonoscopy videos, integrating density clustering and deep learning (cascaded CNN models).
  • The system sequentially estimates the appendix orifice (AO), flexures, and "outside of the body" landmarks.
  • DBSCAN algorithm was applied for anatomical section identification, integrating clinical knowledge and context, with preprocessing for non-informative image removal.

Main Results:

  • The model categorizes the colon into three sections: right (cecum, ascending colon), middle (transverse colon), and left (descending colon, sigmoid colon, rectum).
  • Estimated appearance time errors for anatomical boundaries were: 6.31 s for AO, 9.79 s for hepatic flexure (HF), 27.69 s for splenic flexure (SF), and 3.26 s for "outside of the body".

Conclusions:

  • The proposed system demonstrates a viable approach for AI-based automatic anatomical section recognition in colonoscopy.
  • This method offers potential for time-saving efficacy and standardization in AI-based automatic colonoscopy reporting.