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

Evaluating computer-aided detection algorithms.

Hong Jun Yoon1, Bin Zheng, Berkman Sahiner

  • 1Department of Radiology, University of Pittsburgh, Pittsburgh, Pennsylvania 15261, USA.

Medical Physics
|July 28, 2007
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

Physics-informed data augmentation to simulate low dose CT scans: Application to lung nodule detection.

Medical physics·2026
Same author

Synthetic data in radiological imaging: current state and future outlook.

BJR artificial intelligence·2026
Same author

Task-Based Sampling of Patient Data for Rigorous Machine Learning/AI Performance Assessment.

Journal of imaging informatics in medicine·2026
Same author

Statistical testing of agreement in overlap-based performance between an AI segmentation device and a multi-expert human panel without requiring a reference standard.

Journal of medical imaging (Bellingham, Wash.)·2025
Same author

A data-driven framework for identifying patient subgroups on which an AI/machine learning model may underperform.

NPJ digital medicine·2024
Same author

Bias Amplification to Facilitate the Systematic Evaluation of Bias Mitigation Methods.

IEEE journal of biomedical and health informatics·2024
Same journal

Decomposition-based harmonization for quantitative PET imaging across scanners and radiotracers.

Medical physics·2026
Same journal

Development and evaluation of an in vivo dose-based monitoring system for electron FLASH radiation therapy.

Medical physics·2026
Same journal

A novel optical respiratory gating system with a hybrid phase-amplitude algorithm for spot-scanning proton therapy.

Medical physics·2026
Same journal

Gamma Knife treatment planning using knowledge-based reinforcement learning.

Medical physics·2026
Same journal

Development and characterization of a novel, small animal external beam irradiator using a clinical high dose rate brachytherapy source.

Medical physics·2026
Same journal

Deep learning-based dose prediction for MR-guided prostate SIB: Supporting rapid feasibility assessment and adaptive editing margin selection.

Medical physics·2026
See all related articles

This study introduces a new Free-Response Receiver Operating Characteristic (FROC) curve fitting method using a visual search model for better computer-aided detection (CAD) algorithm evaluation. This approach improves CAD system optimization and robustness in medical imaging analysis.

Area of Science:

  • Medical Imaging
  • Radiology
  • Computer Science

Background:

  • Computer-aided detection (CAD) algorithms require robust evaluation methodologies for optimization.
  • Current Free-Response Receiver Operating Characteristic (FROC) curve analysis for CAD performance is often limited to specific operating points.
  • Accurate assessment of CAD performance is crucial for realizing its full potential in medical diagnosis.

Purpose of the Study:

  • To develop and implement a novel FROC curve fitting procedure based on a visual search model.
  • To establish a practical evaluation framework for CAD algorithms in diagnostic radiology.
  • To provide improved figures of merit for CAD performance assessment without arbitrary operating point selection.

Main Methods:

  • Implemented a maximum likelihood procedure for estimating parameters from free-response data.

Related Experiment Videos

  • Developed a FROC curve fitting procedure utilizing a recent visual search model.
  • Tested two methods, including a related initial detection and candidate analysis, on seven mammography CAD datasets.

    • Main Results:

    • Both implemented methods yielded good to excellent fits for the tested mammography CAD datasets.
    • The visual search model approach provides figures of merit without requiring arbitrary operating point specification.
    • The developed software is expected to benefit CAD developers across various medical imaging fields.

    Conclusions:

    • The visual search model offers a practical and effective approach for evaluating CAD performance using FROC curves.
    • This method can potentially be applied to radiologist-generated free-response data, enhancing its versatility.
    • This work represents a significant advancement in the evaluation of CAD systems in diagnostic radiology.