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

Magnetic Resonance Imaging01:24

Magnetic Resonance Imaging

5.0K
Magnetic resonance imaging (MRI) is a noninvasive medical imaging technique based on a phenomenon of nuclear physics discovered in the 1930s, in which matter exposed to magnetic fields and radio waves was found to emit radio signals. In 1970, a physician and researcher named Raymond Damadian noticed that malignant (cancerous) tissue gave off different signals than normal body tissue. He applied for a patent for the first MRI scanning device in clinical use by the early 1980s. The early MRI...
5.0K

You might also read

Related Articles

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

Sort by
Same author

Indium Tin Oxide (ITO) Substrates Enable Coating-Free SEM Imaging and Simplified Preparation of Purified Fibrinogen Clots.

bioRxiv : the preprint server for biology·2026
Same author

Nonlinear relationships of fibrin network structure as a function of fibrinogen and thrombin concentrations for purified fibrinogen and plasma clots.

Acta biomaterialia·2026
Same author

Azolla reshapes rhizosphere microbiomes and nutrient cycling in paddy fields.

Environmental microbiome·2026
Same author

Cryo-EM structures of prevalent gut phage PD491P1 uncover extensive disulfide stabilization and distinct structural adaptations.

Structure (London, England : 1993)·2026
Same author

Standardization of scanning electron microscopy analysis of fibrin fiber diameter measurement: communication from the ISTH SSC subcommittee on FXIII and fibrinogen.

Journal of thrombosis and haemostasis : JTH·2025
Same author

Capsid structure of phage SPO1 reveals novel minor capsid proteins and insights into capsid stabilization.

Structure (London, England : 1993)·2025

Related Experiment Video

Updated: Jun 10, 2025

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

376

A Multi-task Neural Network for Image Recognition in Magnetically Controlled Capsule Endoscopy.

Ting Xu1, Yuan-Yi Li2, Fang Huang3

  • 1Department of Gastroenterology, The Second Affiliated Hospital of Chongqing Medical University, No. 74 Linjiang Road, Chongqing, China.

Digestive Diseases and Sciences
|October 15, 2024
PubMed
Summary
This summary is machine-generated.

This study introduces a multi-task recognition model (Mul-Recog-Model) for capsule endoscopy, improving diagnostic efficiency by simultaneously identifying gastric anatomical sites and lesions with high accuracy.

Keywords:
Artificial intelligenceGastric anatomical sitesGastric lesionsMulti-task neural network

More Related Videos

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

2.7K
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

478

Related Experiment Videos

Last Updated: Jun 10, 2025

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

376
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

2.7K
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

478

Area of Science:

  • Medical imaging analysis
  • Artificial intelligence in healthcare
  • Gastroenterology

Background:

  • Physicians spend significant time reviewing capsule endoscopy images.
  • Current deep learning models perform single recognition tasks, not replicating physician diagnostics.
  • Need for advanced AI to assist in analyzing complex gastrointestinal data.

Purpose of the Study:

  • To develop a multi-task deep learning model for simultaneous recognition of gastric anatomical sites and lesions.
  • To improve the efficiency and accuracy of capsule endoscopy analysis.
  • To create a tool that better mimics the diagnostic process of physicians.

Main Methods:

  • Developed the Mul-Recog-Model, a novel multi-task recognition system.
  • Trained and tested the model using capsule endoscopy images from 886 patients.
  • Compared the multi-task model against current single-task recognition models on the same test dataset.

Main Results:

  • Mul-Recog-Model achieved high sensitivity (>98.8%) and specificity (>98.5%) for both anatomical sites and lesions.
  • Demonstrated excellent positive predictive value, negative predictive value, and accuracy (>95%).
  • Outperformed single-task models in efficiency, with faster image recognition (15.5 ms) and fewer parameters (49.1 M).

Conclusions:

  • The Mul-Recog-Model shows high performance in accuracy and efficiency for gastric capsule endoscopy analysis.
  • The model's ability to perform multiple recognition tasks simultaneously enhances diagnostic capabilities.
  • This AI tool can significantly improve physician reporting efficiency and meet complex diagnostic needs.