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 Video

Updated: Apr 17, 2026

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances
07:35

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Published on: October 11, 2018

8.1K

Assessing diagnostic complexity: An image feature-based strategy to reduce annotation costs.

Jose R Zamacona1, Ronald Niehaus1, Alexander Rasin1

  • 1School of Computing, DePaul University, Chicago, USA.

Computers in Biology and Medicine
|February 26, 2015
PubMed
Summary

This study introduces a method to classify diagnostic complexity in CT scans, helping radiologists manage workload. By identifying easy versus hard cases, costs can be reduced with minimal impact on accuracy.

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

Heterogeneity of Treatment Effect of Aspirin and Clinically Significant Bleeding in Older Adults.

medRxiv : the preprint server for health sciences·2026
Same author

Correlation Aware Relevance-Based Semantic Index for Clinical Big Data Repository.

Journal of imaging informatics in medicine·2024
Same author

Biomedical heterogeneous data categorization and schema mapping toward data integration.

Frontiers in big data·2023
Same author

Learning Latent Spiculated Features for Lung Nodule Characterization.

Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference·2020
Same author

Ontology-Based Radiology Teaching File Summarization, Coverage, and Integration.

Journal of digital imaging·2020
Same author

Automatic extraction of informal topics from online suicidal ideation.

BMC bioinformatics·2018

Area of Science:

  • Medical Imaging
  • Radiology
  • Artificial Intelligence in Medicine

Background:

  • Computer-aided diagnosis (CAD) systems aid radiologists by analyzing medical images.
  • Efficient management of radiologist time and diagnostic complexity is crucial for cost reduction and workload optimization.
  • Current CAD systems require further development to effectively manage radiologist time and diagnostic complexity.

Purpose of the Study:

  • To develop strategies for managing clinical radiologists' limited time using predictive model diagnosis.
  • To introduce a metric for discriminating diagnostic complexity in CT scans (easy vs. hard).
  • To demonstrate how classifying diagnostic complexity can optimize radiologist case allocation.

Main Methods:

  • A metric was developed to categorize diagnostic complexity of CT scans.
Keywords:
Computer-aided diagnosisImage classificationResource allocation

Related Experiment Videos

Last Updated: Apr 17, 2026

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances
07:35

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Published on: October 11, 2018

8.1K
  • Diagnostic complexity was learned using a classification approach with low-level image features.
  • A lung nodule image dataset was used to evaluate the proposed method.

    • Main Results:

    • A simple division of cases into hard and easy to diagnose significantly lowered interpretation costs.
    • This approach resulted in limited loss in prediction accuracy.
    • A significant subset (66%) of lung nodule image data could be classified using only 18% of the original low-level image features.

    Conclusions:

    • Classifying diagnostic complexity is an effective strategy for managing radiologist workload and reducing costs.
    • Low-level image features can accurately predict diagnostic complexity for a substantial portion of medical image data.
    • This method offers a practical approach to optimize resource allocation in radiological diagnosis.