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

Endoscopic Procedures III: Video Capsule Endoscopy01:28

Endoscopic Procedures III: Video Capsule Endoscopy

64
Capsule endoscopy, or wireless or video capsule endoscopy, is a diagnostic procedure for examining the entire gastrointestinal tract. Patients swallow a capsule about the size of a vitamin tablet. The capsule is equipped with a transmitter, a battery, an LED light source, and a color video camera to capture images throughout the gastrointestinal tract. This procedure is particularly useful for diagnosing conditions such as Crohn's disease, ulcerative colitis, tumors, polyps, ulcers,...
64
Imaging Studies III: Gastrointestinal Motility Studies and Virtual Colonoscopy01:26

Imaging Studies III: Gastrointestinal Motility Studies and Virtual Colonoscopy

35
This lesson explores three gastrointestinal imaging techniques: radionuclide testing, colonic transit studies, and virtual colonoscopy.
Radionuclide Testing
Radionuclide testing is a sophisticated medical technique for assessing gastrointestinal motility. It focuses on gastric emptying and colonic transit time. Radioactive markers track the movement of food through the digestive system, providing insights into gastrointestinal disorders.
In gastric emptying studies, a meal's liquid and...
35
Endoscopic Procedures II: Colonoscopy01:25

Endoscopic Procedures II: Colonoscopy

40
The colon, or large intestine, is the final segment of the digestive system. Its primary functions include absorbing water and vitamins produced by gut bacteria and transforming waste from liquid to solid to form stool. In adults, the large intestine is approximately 5 feet long and consists of four main sections:
40

You might also read

Related Articles

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

Sort by
Same author

Construction of an artificial intelligence system for the Los Angeles classification-based assessment of reflux esophagitis (with video).

Digital health·2026
Same author

Clinical Characteristics and Cancer-Specific Survival of Adolescents and Young Adults With Pancreatic Neuroendocrine Tumors: A SEER-Based Study.

Cancer control : journal of the Moffitt Cancer Center·2026
Same author

Development and validation of machine learning models for predicting cancer-specific survival in colorectal signet ring cell carcinoma.

BMC gastroenterology·2026
Same author

Machine learning prediction of overall survival in patients with primary gastrointestinal melanoma.

Translational cancer research·2025
Same author

Real-time deep-learning NICE classification and withdrawal-speed monitoring for colorectal endoscopy.

Digital health·2025
Same author

Comparing long-term survival prognosis with surgery-based systemic treatment of gastrointestinal stromal tumors: A population-based study.

Journal of cancer research and therapeutics·2025

Related Experiment Video

Updated: May 21, 2025

Flexible Colonoscopy in Mice to Evaluate the Severity of Colitis and Colorectal Tumors Using a Validated Endoscopic Scoring System
15:49

Flexible Colonoscopy in Mice to Evaluate the Severity of Colitis and Colorectal Tumors Using a Validated Endoscopic Scoring System

Published on: October 16, 2013

31.7K

Development and Validation of a Multi-Task Artificial Intelligence-Assisted System for Small Bowel Capsule Endoscopy.

Jian Chen1,2, Hongwei Wang1,2, Zihao Zhang3

  • 1Department of Gastroenterology, Changshu Hospital Affiliated to Soochow University, Suzhou, Jiangsu, 215500, People's Republic of China.

International Journal of General Medicine
|May 19, 2025
PubMed
Summary

This study developed an AI system using Transformer networks for small bowel capsule endoscopy (SBCE). The AI system accurately identifies lesions, improving diagnostic speed and efficiency for endoscopists.

Keywords:
artificial intelligencesmall bowel capsule endoscopysmall bowel lesionstransfer learningtransformer

More Related Videos

Technical Detail for Robot Assisted Pancreaticoduodenectomy
14:45

Technical Detail for Robot Assisted Pancreaticoduodenectomy

Published on: September 28, 2019

14.3K
Clinical Application of Single-Surgeon, Three-Port, Laparoscopic Resection for Colorectal Cancer with Natural Orifice Specimen Extraction
08:26

Clinical Application of Single-Surgeon, Three-Port, Laparoscopic Resection for Colorectal Cancer with Natural Orifice Specimen Extraction

Published on: March 24, 2023

297

Related Experiment Videos

Last Updated: May 21, 2025

Flexible Colonoscopy in Mice to Evaluate the Severity of Colitis and Colorectal Tumors Using a Validated Endoscopic Scoring System
15:49

Flexible Colonoscopy in Mice to Evaluate the Severity of Colitis and Colorectal Tumors Using a Validated Endoscopic Scoring System

Published on: October 16, 2013

31.7K
Technical Detail for Robot Assisted Pancreaticoduodenectomy
14:45

Technical Detail for Robot Assisted Pancreaticoduodenectomy

Published on: September 28, 2019

14.3K
Clinical Application of Single-Surgeon, Three-Port, Laparoscopic Resection for Colorectal Cancer with Natural Orifice Specimen Extraction
08:26

Clinical Application of Single-Surgeon, Three-Port, Laparoscopic Resection for Colorectal Cancer with Natural Orifice Specimen Extraction

Published on: March 24, 2023

297

Area of Science:

  • Artificial Intelligence
  • Medical Imaging
  • Gastroenterology

Background:

  • Small bowel capsule endoscopy (SBCE) is crucial for diagnosing gastrointestinal conditions.
  • Interpreting SBCE images is time-consuming and prone to diagnostic errors.
  • Existing AI tools lack comprehensive functionalities for efficient SBCE analysis.

Purpose of the Study:

  • To develop a multi-task AI-assisted system for SBCE using Transformer neural networks.
  • To integrate lesion recognition, cumulative time statistics, and progress bar marking.
  • To enhance diagnostic accuracy and efficiency while minimizing missed diagnoses in SBCE.

Main Methods:

  • Collected and annotated a dataset of 34,799 SBCE images across 12 categories from three device brands.
  • Utilized transfer learning and fine-tuning on five pre-trained Transformer models.
  • Developed a multi-task SBCE-assisted reading system named "FocalCE-Master" using the optimal FocalNet model (ONNX format) and OpenCV/MMCV tools.

Main Results:

  • The FocalNet model achieved a weighted average sensitivity of 85.69%, specificity of 98.58%, and accuracy of 85.69%.
  • Diagnostic accuracy of FocalNet was superior to junior physicians and comparable to senior physicians.
  • The "FocalCE-Master" system processed images at 592.40 frames per second, significantly faster than human endoscopists, and streamlined lesion localization.

Conclusions:

  • The Transformer-based multi-task AI system demonstrates rapid and accurate classification of small bowel lesions.
  • The system has the potential to significantly improve diagnostic efficiency and image review speed in SBCE.
  • Further validation in prospective clinical trials is necessary to confirm the clinical applicability of the AI system.