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

Automatic detection of abnormalities in chest radiographs using local texture analysis.

Bram van Ginneken1, Shigehiko Katsuragawa, Bart M ter Haar Romeny

  • 1Image Sciences Institute, University Medical Center Utrecht, The Netherlands. bram@isi.uu.nl

IEEE Transactions on Medical Imaging
|April 4, 2002
PubMed
Summary

This study introduces an automated method for detecting diffuse textural abnormalities in chest X-rays, crucial for mass screening programs like tuberculosis (TB) detection. The system achieves high accuracy in identifying abnormalities, aiding in early disease detection.

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

Community-based tuberculosis screening with computer-aided detection technology alone and in combination with point-of-care C-reactive protein testing: a paired screen-positive trial.

The Lancet. Infectious diseases·2026
Same author

Assessment of modifications to a blind-sweep ultrasound protocol for improved lower-uterus imaging by novice operators.

Scientific reports·2026
Same author

Large Language Model Automated Extraction of Clinical Signs and Symptoms From Emergency Department Reports for Machine Learning Prediction Models: Development and Validation Study.

JMIR medical informatics·2026
Same author

Leveraging open-source large language models for clinical information extraction in resource-constrained settings.

JAMIA open·2025
Same author

Artificial intelligence-based identification of thin-cap fibroatheromas and clinical outcomes: the PECTUS-AI study.

European heart journal·2025
Same author

Segmenting Whole-Body MRI and CT for Multiorgan Anatomic Structure Delineation.

Radiology. Artificial intelligence·2025

Area of Science:

  • Medical Imaging
  • Computer-Aided Diagnosis
  • Radiology

Background:

  • Mass chest screening programs, particularly for tuberculosis (TB), require efficient methods for detecting subtle, diffuse textural abnormalities.
  • Existing methods may struggle with the nuanced nature of these abnormalities, necessitating advanced automated solutions.

Purpose of the Study:

  • To develop and evaluate a fully automatic method for detecting diffuse textural abnormalities in frontal chest radiographs.
  • To aggregate regional abnormality findings into an overall abnormality score for each image.

Main Methods:

  • Automatic lung field segmentation using active shape models.
  • Extraction of texture and difference features from multiscale filter bank responses in segmented regions.
  • Classification of regions using k-nearest neighbors with leave-one-out validation.

Related Experiment Videos

  • Weighted combination of regional classification results to generate an overall image abnormality score.

    • Main Results:

    • On a TB screening database (147 abnormal, 241 normal), the method achieved 0.86 sensitivity and 0.50 specificity (ROC AUC 0.820).
    • On a second database (100 normal, 100 interstitial disease abnormal), sensitivity was 0.97 and specificity 0.90 (ROC AUC 0.986).

    Conclusions:

    • The presented fully automatic method effectively detects diffuse textural abnormalities in chest radiographs.
    • The system demonstrates strong performance across different databases, showing promise for computer-aided diagnosis in mass screening scenarios.