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 Video

Updated: Dec 2, 2025

Decoding Natural Behavior from Neuroethological Embedding
08:00

Decoding Natural Behavior from Neuroethological Embedding

Published on: October 3, 2025

380

WCE polyp detection with triplet based embeddings.

Pablo Laiz1, Jordi Vitrià1, Hagen Wenzek2

  • 1Department of Mathematics and Computer Science, Universitat de Barcelona, Barcelona, Spain.

Computerized Medical Imaging and Graphics : the Official Journal of the Computerized Medical Imaging Society
|November 1, 2020
PubMed
Summary
This summary is machine-generated.

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

Learning instance-specific counterfactual models for continuous treatments using hypernetworks.

Frontiers in artificial intelligence·2026
Same author

PPI-Refractory GERD in Systemic Sclerosis Is Driven by Distinct Esophageal and Gastric Motility Abnormalities.

medRxiv : the preprint server for health sciences·2026
Same author

Systemic sclerosis and small bowel involvement: A systematic review of diagnostic approaches and current evidence.

Seminars in arthritis and rheumatism·2026
Same author

Collagen and microvascular alterations contribute to neuromuscular degeneration and disease progression in chronic intestinal pseudo-obstruction.

Journal of internal medicine·2026
Same author

Proton pump inhibitor use and treatment satisfaction in Spanish patients with systemic sclerosis: Insights from a nationwide survey.

Gastroenterologia y hepatologia·2026
Same author

Biofeedback Guided by Thoracoabdominal Wall Motion for the Treatment of Rumination: A Randomized Placebo-Controlled Trial.

Gastroenterology·2026
Same journal

RGCNN-nnUNet: Recurrent group equivariant nnU-Net for robust brain tissue segmentation on stroke NCCT.

Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society·2026
Same journal

Self-supervised isotropic reconstruction for abnormality detection in anisotropic MRI.

Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society·2026
Same journal

WDBDM: Wavelet-based dual-branch diffusion model for low-dose CT and PET denoising.

Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society·2026
Same journal

ScribSAM: A robust scribble-supervised framework for spatiotemporal segmentation of breast lesions in ultrasound videos.

Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society·2026
Same journal

Anatomically and biochemically guided deep image prior for sodium MRI denoising.

Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society·2026
Same journal

Segment Anything Model for medical image segmentation: A review.

Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society·2026
See all related articles

This study introduces an AI system for detecting polyps in wireless capsule endoscopy videos, improving accuracy with a novel deep learning approach. The system also provides visual explanations to build physician trust and aid debugging.

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Gastroenterology

Background:

  • Wireless capsule endoscopy (WCE) aids in diagnosing gastrointestinal conditions but manual video analysis is time-consuming and error-prone.
  • Automatic image analysis for WCE is crucial for efficient diagnosis but remains a research challenge.
  • Computer-aided polyp detection in WCE images faces hurdles like diverse polyp appearances, imbalanced datasets, and limited data.

Purpose of the Study:

  • To develop an advanced computer-aided decision system for polyp detection in capsule endoscopy images.
  • To enhance feature extraction and model robustness, particularly with limited data, using metric learning.
  • To provide visual explanations for AI decisions to foster physician trust and system transparency.

Main Methods:

Keywords:
Capsule endoscopyDeep learningDeep metric learningPolyp detectionTriplet loss

More Related Videos

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

2.1K
Colorectal Cancer Cell Surface Protein Profiling Using an Antibody Microarray and Fluorescence Multiplexing
15:17

Colorectal Cancer Cell Surface Protein Profiling Using an Antibody Microarray and Fluorescence Multiplexing

Published on: September 25, 2011

14.2K

Related Experiment Videos

Last Updated: Dec 2, 2025

Decoding Natural Behavior from Neuroethological Embedding
08:00

Decoding Natural Behavior from Neuroethological Embedding

Published on: October 3, 2025

380
A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

2.1K
Colorectal Cancer Cell Surface Protein Profiling Using an Antibody Microarray and Fluorescence Multiplexing
15:17

Colorectal Cancer Cell Surface Protein Profiling Using an Antibody Microarray and Fluorescence Multiplexing

Published on: September 25, 2011

14.2K
  • A deep convolutional neural network combined with metric learning was developed for polyp detection.
  • The Triplet Loss function was employed to improve feature representation by learning discriminative embeddings from image data.
  • A method for generating visual explanations of the polyp detection outcomes was implemented.

Main Results:

  • The developed system demonstrated a significant increase in Area Under the Curve (AUC) values compared to existing state-of-the-art methods.
  • The use of Triplet Loss proved effective in improving feature extraction, especially in data-scarce scenarios.
  • The visual explanation method provides insights into the system's decision-making process.

Conclusions:

  • The proposed AI system offers a promising solution for accurate and efficient polyp detection in wireless capsule endoscopy.
  • The integration of metric learning and visual explainability enhances the system's potential for clinical adoption.
  • This approach addresses key challenges in WCE image analysis, paving the way for improved diagnostic tools.