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 Videos

FMC-Net: Fine-grained multi-lesion classification in wireless capsule endoscopy via attention-guided feature

Shanhui Fan1, Shangguang Wei2, Zhiwen Wang2

  • 1School of Automation (School of Artificial Intelligence), Hangzhou Dianzi University, Hangzhou 310018, Zhejiang, China; Key Laboratory of Micro-nano Sensing and IoT of Wenzhou, Wenzhou Institute of Hangzhou Dianzi University, Wenzhou 325038, Zhejiang, China.

Computerized Medical Imaging and Graphics : the Official Journal of the Computerized Medical Imaging Society
|May 22, 2026
PubMed
Summary

Related Concept Videos

Endoscopic Procedures III: Video Capsule Endoscopy01:28

Endoscopic Procedures III: Video Capsule Endoscopy

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, unexplained...

You might also read

Related Articles

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

Sort by
Same author

Prognostic Genes Linked to Asparagine Metabolism in Hepatocellular Carcinoma: Identification, Validation, and Regulatory Mechanisms Based on Transcriptome and Single-Cell RNA Sequencing.

International journal of molecular sciences·2026
Same author

Electroacupuncture Attenuates Neuroinflammation and Postoperative Cognitive Dysfunction in Aged Rats by Suppressing the cGAS-STING Pathway.

Experimental neurobiology·2026
Same author

Morphologically Switchable Twin Photonic Hooks.

Materials (Basel, Switzerland)·2024
Same author

Design of Surface Plasmon Resonance-Based D-Type Double Open-Loop Channels PCF for Temperature Sensing.

Sensors (Basel, Switzerland)·2023
Same author

Ultra-Wideband High-Efficiency Solar Absorber and Thermal Emitter Based on Semiconductor InAs Microstructures.

Micromachines·2023
Same author

PbSe Quantum Dot Doped Mode-Locked Fiber Laser.

Materials (Basel, Switzerland)·2022
This summary is machine-generated.

A new network, FMC-Net, improves gastrointestinal disease diagnosis by accurately detecting multiple lesions in wireless capsule endoscopy images. This AI-powered tool enhances lesion classification for better patient outcomes.

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Gastroenterology

Background:

  • Accurate detection of gastrointestinal lesions in wireless capsule endoscopy (WCE) is vital for disease diagnosis.
  • Challenges include high similarity between lesion types, variability within lesion types, and multiple lesions in single images.

Purpose of the Study:

  • To develop a fine-grained multi-lesion classification network (FMC-Net) for enhanced lesion discrimination in WCE images.
  • To support both single-label and multi-label classification tasks.

Main Methods:

  • Proposed FMC-Net utilizes an attention-guided feature selection module with independent local and global feature branches.
  • A global-local attention module integrates features to improve fine-grained lesion recognition.
  • A flexible classifier supports both single-label and multi-label learning.
Keywords:
Attention-guided feature selection moduleFine-grained recognitionMulti-labelMulti-lesion classificationWireless capsule endoscopy

Related Experiment Videos

Main Results:

  • FMC-Net demonstrated superior performance over state-of-the-art methods in classifying WCE images (normal, bleeding, ulcer, erosion, polyp).
  • Achieved >2.68% accuracy improvement in single-label classification on test datasets and >5.15% on complete WCE cases.
  • Attained 81.78% average accuracy in multi-label classification, exceeding existing methods by at least 6.29%.

Conclusions:

  • FMC-Net offers competitive and robust detection performance in complex WCE scenarios.
  • The method shows potential for clinical application in automated gastrointestinal lesion detection.
  • Contributes to more accurate and efficient diagnostic workflows for gastrointestinal diseases.