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

Location of GI lesions with bleeding potential in patients with iron deficiency anemia: a multicenter prospective study.

Gastrointestinal endoscopy·2026
Same author

Comprehensive microbiome profiling reveals mucosal microbiome heterogeneity in patients with left- and right-sided colorectal neoplasia.

Cancer biology & medicine·2026
Same author

Risk of Complicated Upper Gastrointestinal Bleeding With Direct Oral Anticoagulants: An Asian Population-Based Analysis.

Clinical gastroenterology and hepatology : the official clinical practice journal of the American Gastroenterological Association·2026
Same author

Rapid customization of base editors via machine learning-powered combinatorial mutagenesis.

Molecular cell·2026
Same author

ASO Author Reflections: Preoperative Biliary Drainage-A Controversial Intervention with a Complicated Past.

Annals of surgical oncology·2026
Same author

Outcomes of diagnostic and therapeutic EUS procedures in live course <i>versus</i> routine service between 2015 and 2021: A propensity score analysis.

Endoscopic ultrasound·2026

Related Experiment Video

Updated: Dec 21, 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

3.2K

AI-doscopist: a real-time deep-learning-based algorithm for localising polyps in colonoscopy videos with edge

Carmen C Y Poon1, Yuqi Jiang1, Ruikai Zhang1

  • 11Division of Biomedical Engineering Research, Department of Surgery, The Chinese University of Hong Kong, Hong Kong SAR, People's Republic of China.

NPJ Digital Medicine
|May 22, 2020
PubMed
Summary
This summary is machine-generated.

An AI-doscopist model accurately localized 96.9% of colorectal polyps during colonoscopy. This artificial intelligence tool shows potential to assist endoscopists, improving polyp detection rates and patient outcomes.

Keywords:
CancerTranslational research

More Related Videos

Long-term Video Tracking of Cohoused Aquatic Animals: A Case Study of the Daily Locomotor Activity of the Norway Lobster Nephrops norvegicus
05:57

Long-term Video Tracking of Cohoused Aquatic Animals: A Case Study of the Daily Locomotor Activity of the Norway Lobster Nephrops norvegicus

Published on: April 8, 2019

7.2K
Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images
08:20

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Published on: October 27, 2023

2.3K

Related Experiment Videos

Last Updated: Dec 21, 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

3.2K
Long-term Video Tracking of Cohoused Aquatic Animals: A Case Study of the Daily Locomotor Activity of the Norway Lobster Nephrops norvegicus
05:57

Long-term Video Tracking of Cohoused Aquatic Animals: A Case Study of the Daily Locomotor Activity of the Norway Lobster Nephrops norvegicus

Published on: April 8, 2019

7.2K
Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images
08:20

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Published on: October 27, 2023

2.3K

Area of Science:

  • Medical Imaging
  • Artificial Intelligence in Medicine
  • Gastroenterology

Background:

  • Colorectal cancer (CRC) screening relies heavily on colonoscopy for early detection of polyps.
  • Accurate polyp localization is crucial for effective removal and preventing interval cancers.
  • Human error and visual limitations can lead to missed polyps during colonoscopy.

Purpose of the Study:

  • To develop and evaluate a deep-learning model, termed AI-doscopist, for localizing colonic neoplasia during colonoscopy.
  • To assess the agreement between human endoscopists and the AI-doscopist in identifying and localizing colorectal polyps.
  • To determine the potential of AI-doscopist as an assistive tool for improving polyp detection rates in real-time colonoscopy.

Main Methods:

  • A deep-learning model (AI-doscopist) was pre-trained on 1.2 million non-medical images and fine-tuned on 291,090 colonoscopy and non-medical images.
  • Colonoscopy images from six databases were classified into 13 categories with polyp locations marked by bounding boxes.
  • The AI-doscopist's performance was evaluated image-by-image on 144 full colonoscopies, with 128 suspicious lesions biopsied for confirmation.

Main Results:

  • The AI-doscopist achieved a specificity of 93.3% in image-by-image evaluation.
  • The model demonstrated a polyp-based sensitivity of 96.9%, localizing 124 out of 128 polyps.
  • In a separate cohort, AI-highlighted regions helped an endoscopist identify four previously missed polyps in three patients.

Conclusions:

  • The AI-doscopist shows high accuracy in localizing colorectal polyps, achieving 96.9% sensitivity.
  • Real-time application of AI-doscopist could potentially assist endoscopists, improving polyp detection by an estimated 1 additional patient per 20-33 colonoscopies.
  • AI-assisted colonoscopy holds promise for enhancing the efficacy of colorectal cancer screening programs.