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 detection for CT colonography: external validation.

S Halligan1, S A Taylor, J Dehmeshki

  • 1Department of Specialist Radiology, University College Hospital, London, UK. s.halligan@ucl.ac.uk

Clinical Radiology
|August 15, 2006
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

An Analysis of Biomechanical and Physiological Changes During Abdominal Wall Reconstruction.

Journal of abdominal wall surgery : JAWS·2026
Same author

Expert consensus recommendations on the daily clinical use of pembrolizumab for early triple-negative breast cancer.

Hong Kong medical journal = Xianggang yi xue za zhi·2025
Same author

Medicolegal implications of the Royal College of Radiologists standards for the interpretation and reporting of imaging investigations: a retrospective review of claims in abdominal radiology.

Clinical radiology·2025
Same author

Surgical training for simple and complex hernia repair in the UK: results of a nationwide training survey.

Annals of the Royal College of Surgeons of England·2025
Same author

Citation and adherence to TRIPOD guidelines by published radiological prognostic models: systematic review.

The British journal of radiology·2025
Same author

Does training less-than-full-time predict performance at the FRCR exams?: a UKMED cohort study.

Clinical radiology·2024

This study externally validated a computer-assisted detection (CAD) system for computed tomography (CT) colonography, achieving 96% per-patient sensitivity. The CAD system showed improved detection of small polyps with lower sphericity settings, but this decreased specificity.

Area of Science:

  • Medical Imaging
  • Artificial Intelligence in Healthcare
  • Gastroenterology

Background:

  • Computed tomography (CT) colonography is a key tool for colorectal cancer screening.
  • Computer-assisted detection (CAD) systems aim to improve the accuracy of CT colonography interpretation.
  • External validation is crucial to assess the generalizability of CAD systems.

Purpose of the Study:

  • To externally validate a CAD system for CT colonography using an independent dataset.
  • To evaluate the CAD system's performance across different sphericity filter settings.
  • To determine the system's sensitivity and specificity for polyp detection.

Main Methods:

  • Two readers analyzed 25 CT colonography datasets with known polyps.
  • A CAD system, developed independently, was applied to the datasets.

Related Experiment Videos

  • Performance was assessed by comparing CAD findings to known polyp locations, calculating true-positive, false-negative, and false-positive rates.

    • Main Results:

    • The CAD system achieved 96% per-patient sensitivity in detecting polyps (median size 6mm).
    • Sensitivity increased from 77% to 86% for polyps when lowering the sphericity setting from 0.75 to 0.50, particularly for smaller polyps (≤5mm).
    • Lowering the sphericity setting significantly increased false-positive prompts, requiring more detailed review.

    Conclusions:

    • External validation confirmed the CAD system's high per-patient sensitivity (96%) for polyp detection in CT colonography.
    • Adjusting the sphericity filter impacts the trade-off between sensitivity for small polyps and specificity.
    • The findings support the potential utility of CAD systems in colorectal cancer screening via CT colonography.