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-assisted diagnosis system in digestive endoscopy.

Jean-Michel Cauvin1, Clara Le Guillou, Basel Solaiman

  • 1Département d'Information Médicale, Centre Hospitalier Universitaire, Brest 29609, France. jean-michel.cauvin@chu-brest.fr

IEEE Transactions on Information Technology in Biomedicine : a Publication of the IEEE Engineering in Medicine and Biology Society
|March 6, 2004
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

Rare disease care pathways profile in France: leveraging hospital big data to characterize natural history in osteogenesis imperfecta.

JBMR plus·2026
Same author

Long-Term Effects of Rheumatoid Arthritis Treatments on Bone Mineral Density: 8-Year-Follow-Up Data from Real-World Practice.

Journal of clinical medicine·2026
Same author

Marked regression of calcinosis with canakinumab in hyperphosphatemic familial tumoral calcinosis.

JBMR plus·2026
Same author

Impact of regulatory events on JAK inhibitor prescribing in rheumatoid arthritis: Insights from the French MAJIK Registry.

Joint bone spine·2025
Same author

Opportunistic screening for osteoporosis and vertebral fracture using CT attenuation from 18F-fluorocholine PET/CT in patients with prostate cancer.

RMD open·2025
Same author

Cartilage turnover, but not novel synovial collagen marker, is associated with joint damage progression in osteoarthritis patients.

Rheumatology (Oxford, England)·2025

This study introduces an intelligent atlas of endoscopic lesions for computer-assisted diagnosis. The system accurately classifies findings, aiding in medical decision-making for digestive endoscopy.

Area of Science:

  • Medical Informatics
  • Computer-Aided Diagnosis
  • Gastroenterology

Background:

  • Computer-assisted diagnosis requires robust reference data for medical decision-making.
  • Digestive endoscopy diagnostic reasoning involves a scene-object approach, linking findings to diagnoses.
  • Existing endoscopic terminologies and expert experience inform the development of diagnostic systems.

Purpose of the Study:

  • To present an intelligent atlas of indexed endoscopic lesions for computer-assisted diagnosis.
  • To develop a system that analyzes and reproduces cognitive processes in medical decision-making.
  • To create a reference database for training and validating diagnostic algorithms in endoscopy.

Main Methods:

  • Analysis of endoscopist experience and professional terminologies to define diagnostic reasoning.

Related Experiment Videos

  • Listing classes of endoscopic findings and diagnoses with their primitive characteristics and relationships.
  • Implementing a retrieval method based on a similarity metric comparing cases to class prototypes.

    • Main Results:

    • A simulation test demonstrated good classification of endoscopic findings, with correct classification as the unique response in 68% of cases.
    • Anatomic location, shape, color, and relief were identified as crucial descriptors for the classification algorithm.
    • The current database contains approximately 150 endoscopic images, accessible via the Internet.

    Conclusions:

    • The developed intelligent atlas serves as a valuable reference for computer-assisted diagnosis in digestive endoscopy.
    • The system shows promise in accurately classifying endoscopic findings, supporting medical decision-making.
    • Future integration into a learning tool for junior endoscopists is planned to enhance training.