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

Computer-aided tumor detection in endoscopic video using color wavelet features.

Stavros A Karkanis1, Dimitris K Iakovidis, Dimitris E Maroulis

  • 1Realtime Systems and Image Analysis Group, Department of Informatics and Telecommunications, University of Athens, Greece. sk@teilam.gr

IEEE Transactions on Information Technology in Biomedicine : a Publication of the IEEE Engineering in Medicine and Biology Society
|October 2, 2003
PubMed
Summary

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

Synthetic data generation: challenges and perspectives for gastrointestinal medicine.

Nature reviews. Gastroenterology & hepatology·2026
Same author

Clinical evaluation of medical image synthesis: a case study in wireless capsule endoscopy.

Scientific reports·2025
Same author

E pluribus unum interpretable convolutional neural networks.

Scientific reports·2023
Same author

Interpretable EEG-Based Emotion Recognition Using Fuzzy Cognitive Maps.

Studies in health technology and informatics·2023
Same author

Artificial Intelligence in Cardiology-A Narrative Review of Current Status.

Journal of clinical medicine·2022
Same author

Constructive Fuzzy Cognitive Map for Depression Severity Estimation.

Studies in health technology and informatics·2022

This study introduces a new method for detecting colon tumors using color wavelet covariance features extracted from colonoscopic videos. The approach achieves high accuracy, with 97% specificity and 90% sensitivity in identifying adenomatous polyps.

Area of Science:

  • Medical Imaging
  • Computer Vision
  • Gastroenterology

Background:

  • Colonoscopic video analysis is crucial for early detection of colorectal abnormalities.
  • Automated detection systems can improve diagnostic accuracy and efficiency.

Purpose of the Study:

  • To develop and validate a novel automated approach for detecting tumors in colonoscopic videos.
  • To enhance the accuracy of identifying adenomatous polyps using advanced feature extraction techniques.

Main Methods:

  • A new color feature extraction scheme based on wavelet decomposition was developed.
  • Color Wavelet Covariance (CWC) features were computed from second-order textural measures.
  • A selection algorithm identified an optimal subset of CWC features.
  • Linear Discriminant Analysis (LDA) was employed for image region characterization.

Related Experiment Videos

Main Results:

  • The methodology was applied to real-world colonoscopic video datasets.
  • The system demonstrated high performance in detecting abnormal colonic regions.
  • Achieved a specificity of 97% and a sensitivity of 90% for adenomatous polyp detection.

Conclusions:

  • The proposed color feature extraction scheme effectively detects tumors in colonoscopic videos.
  • The combination of CWC features and LDA provides a robust method for polyp identification.
  • This approach shows significant potential for improving colon cancer screening.