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

Reliability analysis framework for computer-assisted medical decision systems.

Piotr A Habas1, Jacek M Zurada, Adel S Elmaghraby

  • 1Computational Intelligence Laboratory, Department of Electrical and Computer Engineering, University of Louisville, Louisville, Kentucky 40292, USA. habas@ci.louisville.edu

Medical Physics
|March 29, 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

Optimizing place-based data infrastructure siting: balancing energy, environment, and communities.

ACS ES&T water·2026
Same author

Deep Learning for Image Watermarking: A Comprehensive Review and Analysis of Techniques, Challenges, and Applications.

Sensors (Basel, Switzerland)·2026
Same author

Bidirectional Multiscale Efficient Dilated Convolutional Recurrent Neural Network Improved by Swarm Intelligence Optimization.

IEEE transactions on neural networks and learning systems·2025
Same author

Development of message passing-based graph convolutional networks for classifying cancer pathology reports.

BMC medical informatics and decision making·2024
Same author

Deep learning uncertainty quantification for clinical text classification.

Journal of biomedical informatics·2023
Same author

Patient-Specific Modeling and Model Predictive Control Approach to Personalized Optimal Anemia Management.

Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference·2023
Same journal

Correction to "On the shape of the radiation survival curve in tumor spheroids: The role of oxygen heterogeneity".

Medical physics·2026
Same journal

Multi-view constrained semi-supervised vertebra detection for 3D ultrasound spine volume.

Medical physics·2026
Same journal

Accuracy of quantitative <sup>177</sup>Lu SPECT/CT imaging: A systematic review.

Medical physics·2026
Same journal

Physics-constrained dual-domain network for CBCT reconstruction from orthogonal X-rays in gynecologic radiotherapy.

Medical physics·2026
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
See all related articles

This study introduces a novel method for computer-assisted decision (CAD) systems to assess their own decision reliability. The technique improves diagnostic accuracy by identifying reliable CAD outputs, crucial for clinical applications.

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Computer-Aided Diagnosis

Background:

  • Computer-assisted decision (CAD) systems require reliable decision-making capabilities.
  • Assessing the reliability of individual CAD system decisions is crucial for clinical trust and utility.

Purpose of the Study:

  • To develop and validate a technique for assessing the case-specific reliability of CAD system decisions.
  • To enhance the accuracy and trustworthiness of CAD systems by providing a measure of decision confidence.

Main Methods:

  • A novel reliability assessment technique was developed, analyzing the feature space neighborhood of query cases.
  • Dynamically selected known cases relevant to the query were used to estimate local accuracy, serving as a reliability measure.
  • Three decision models (BPNN, GRNN, SVM) were trained on mammographic data with 1337 ROIs to detect masses using eight morphological features.

Related Experiment Videos

Main Results:

  • The proposed reliability measure strongly predicted case-specific accuracy across all tested decision models.
  • Receiver Operating Characteristic (ROC) analysis showed significantly better performance for high-reliability CAD predictions compared to low-reliability ones.
  • The technique demonstrated consistency across different classifier structures and required no additional training.

Conclusions:

  • The case-specific reliability analysis technique enhances CAD system trustworthiness by providing a reliable measure of decision accuracy.
  • This method can alert clinicians to potentially unreliable CAD outputs, improving diagnostic workflows.
  • The technique is easily deployable in clinical settings due to its classifier-agnostic nature and minimal training requirements.