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 detection in screening CT for pulmonary nodules.

Ren Yuan1, Patrick M Vos, Peter L Cooperberg

  • 1Department of Radiology, Vancouver General Hospital, Vancouver, British Columbia, V5Z 1M9 Canada.

AJR. American Journal of Roentgenology
|April 25, 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

Fusion of Clinical and Deep Learning Features for Predicting Pembrolizumab Monotherapy Response in Advanced Non-Small Cell Lung Cancer.

Journal of clinical medicine·2026
Same author

Human eosinophils exert antitumorigenic effects on chordoma.

Chinese neurosurgical journal·2025
Same author

Machine Learning Model Integrating Computed Tomography Image-Derived Radiomics and Circulating miRNAs to Predict Residual Teratoma in Metastatic Nonseminoma Testicular Cancer.

JCO clinical cancer informatics·2025
Same author

Effects of Defocus Distance and Weld Spacing on Microstructure and Properties of Femtosecond Laser Welded Quartz Glass-TC4 Alloy Joints with Residual Stress Analysis.

Materials (Basel, Switzerland)·2025
Same author

Small and Stable Pancreatic Cysts Are Reassuring During Surveillance: Results From the PACYFIC Trial.

United European gastroenterology journal·2025
Same author

Landscape of 2D Deep Learning Segmentation Networks Applied to CT Scan from Lung Cancer Patients: A Systematic Review.

Journal of imaging informatics in medicine·2025
Same journal

Optimizing and Personalizing PSMA Radiopharmaceutical Selection.

AJR. American journal of roentgenology·2026
Same journal

The Importance of Distinguishing One- and Two-sided Hypothesis Tests.

AJR. American journal of roentgenology·2026
Same journal

Advances in Diabetes Medications and Patient Preparation for Oncologic FDG PET: <i>AJR</i> Expert Panel Narrative Review.

AJR. American journal of roentgenology·2026
Same journal

Incorporating BI-RADS v2025 Into Clinical Reporting.

AJR. American journal of roentgenology·2026
Same journal

Navigating Office Politics: Bullying, Gossip, and Workplace Incivility.

AJR. American journal of roentgenology·2026
Same journal

Author Disclosure of Use of Generative Artificial Intelligence Technologies in Submissions to <i>AJR</i>: Reflections From the <i>AJR</i> Editor in Chief.

AJR. American journal of roentgenology·2026
See all related articles

Computer-aided detection (CAD) systems improve pulmonary nodule detection on low-dose CT scans. Combining radiologist and CAD review is essential for comprehensive nodule identification and accurate patient follow-up.

Area of Science:

  • Radiology
  • Medical Imaging
  • Pulmonary Nodule Detection

Background:

  • Low-dose screening CT is crucial for early detection of pulmonary nodules.
  • Accurate identification of pulmonary nodules is essential for appropriate patient management and follow-up.

Purpose of the Study:

  • To evaluate the performance of a computer-aided detection (CAD) system for pulmonary nodule detection.
  • To compare the efficacy of a CAD system against a radiologist's interpretation of low-dose screening CT images.

Main Methods:

  • 150 low-dose screening CT examinations were independently reviewed by a radiologist and a CAD system.
  • Discrepancies were resolved through consensus review by additional radiologists to determine true nodule counts.
  • Detected nodules were classified by size, density, and location.

Related Experiment Videos

Main Results:

  • The radiologist detected 82% of true nodules, while the CAD system detected 73%.
  • The CAD system identified 110 true nodules missed by the radiologist, altering follow-up in six patients.
  • The CAD system generated a false-positive rate of 3.19 nodules per patient.

Conclusions:

  • CAD systems enhance pulmonary nodule detection rates on low-dose CT scans.
  • A combined review by radiologists and CAD is necessary for optimal identification of all pulmonary nodules.
  • CAD's ability to detect previously missed nodules can significantly impact patient imaging follow-up protocols.