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

CoLD: a versatile detection system for colorectal lesions in endoscopy video-frames.

D E Maroulis1, D K Iakovidis, S A Karkanis

  • 1Department of Informatics and Telecommunications, University of Athens, Panepistimiopolis, Ilisia, 15784, Athens, Greece. rtsimage@di.uoa.gr

Computer Methods and Programs in Biomedicine
|January 1, 2003
PubMed
Summary

This study introduces CoLD (colorectal lesions detector), an AI system for detecting colorectal cancer and polyps from colonoscopy images. Achieving over 95% accuracy, it aids gastroenterologists in diagnosis.

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

Telemonitoring predicts in advance heart failure admissions.

International journal of cardiology·2016
Same author

Ratsnake: a versatile image annotation tool with application to computer-aided diagnosis.

TheScientificWorldJournal·2014
Same author

Image analysis framework for infection monitoring.

IEEE transactions on bio-medical engineering·2012
Same author

Reduction of capsule endoscopy reading times by unsupervised image mining.

Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society·2009
Same author

Microarray-MD: a system for exploratory analysis of microarray gene expression data.

Computer methods and programs in biomedicine·2006
Same author

Efficient information theoretic strategies for classifier combination, feature extraction and performance evaluation in improving false positives and false negatives for spam e-mail filtering.

Neural networks : the official journal of the International Neural Network Society·2005

Area of Science:

  • Medical imaging analysis
  • Artificial intelligence in diagnostics
  • Gastroenterology

Background:

  • Colorectal cancer and polyps pose significant health risks.
  • Early detection through colonoscopy is crucial for effective treatment.
  • Accurate identification of lesions during colonoscopy remains a challenge.

Purpose of the Study:

  • To present CoLD (colorectal lesions detector), an automated system for detecting colorectal lesions.
  • To enhance the diagnostic capabilities for colorectal cancer and pre-cancerous polyps.
  • To provide a user-friendly tool for gastroenterologists during colonoscopy procedures.

Main Methods:

  • Utilizing wavelet transformation to extract second-order statistical features from endoscopic images.
  • Employing an artificial neural network for the classification of tissue regions (normal vs. abnormal).

Related Experiment Videos

  • Integrating feature extraction and classification into a graphical user interface (GUI).

    • Main Results:

    • CoLD demonstrated a detection accuracy exceeding 95% in tests on colonoscopy videos.
    • The system effectively discriminates between normal and abnormal tissue regions.
    • Developed in collaboration with gastroenterology specialists for clinical relevance.

    Conclusions:

    • CoLD serves as an effective supplementary diagnostic tool for colorectal lesions.
    • The system enhances the accuracy and efficiency of colorectal cancer and polyp detection.
    • Its user-friendly interface facilitates adoption by both novice and expert users.