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 recognition of regional lung disease patterns.

R Uppaluri1, E A Hoffman, M Sonka

  • 1Department of Electrical and Computer Engineering and Radiology, Divison of Pulmonary, Department of Internal Medicine, The University of Iowa, Iowa City, Iowa, USA.

American Journal of Respiratory and Critical Care Medicine
|August 3, 1999
PubMed
Summary

A new Adaptive Multiple Feature Method (AMFM) objectively evaluates lung tissue patterns from CT scans. This automated approach shows reproducibility and performance comparable to experienced human observers for pulmonary parenchyma assessment.

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

Aquifer-Mediated Speciation in Cave-Adapted Fishes.

Integrative organismal biology (Oxford, England)·2026
Same author

Progression patterns and clinical outcomes in patients with cutaneous squamous-cell carcinoma following anti-PD-1 therapy failure.

ESMO open·2026
Same author

Risk Stratification and Coronary Optical Coherence Tomography Findings in Asymptomatic Patients With Type 1 Diabetes Mellitus.

Physiological research·2025
Same author

High-purity alkaline lignin extraction from Saccharum ravannae and optimization of lignin recovery through response surface methodology.

International journal of biological macromolecules·2023
Same author

Substance use patterns in 9-10 year olds: Baseline findings from the adolescent brain cognitive development (ABCD) study.

Drug and alcohol dependence·2021
Same author

Do Pulmonary Cavity Shapes Influence Lung Function?

Journal of biomechanical engineering·2019

Area of Science:

  • Radiology and Medical Imaging
  • Computational Pathology
  • Pulmonary Medicine

Background:

  • Accurate regional evaluation of pulmonary parenchyma in computed tomography (CT) scans is crucial for diagnosing lung diseases.
  • Existing methods for tissue pattern classification can be subjective and lack reproducibility.

Purpose of the Study:

  • To develop and validate an objective, reproducible, and automated method for regional pulmonary parenchyma evaluation using CT scans.
  • To compare the performance of the automated method against experienced human observers.

Main Methods:

  • The Adaptive Multiple Feature Method (AMFM) was developed, assessing up to 22 texture features to classify six tissue patterns (honeycombing, ground glass, bronchovascular, nodular, emphysemalike, normal).
  • Lung slices were analyzed regionally using 31x31 pixel regions of interest.

Related Experiment Videos

  • Computer output was validated against experienced observers in three blinded and unblinded settings.

    • Main Results:

    • The AMFM demonstrated 100% reproducibility for regional tissue characterization.
    • Computer versus observer agreement ranged from 44.4% to 51.7%, comparable to interobserver agreement (48.8% to 53.9%).
    • The kappa statistic for agreement between the computer and majority observer consensus was 0.62.

    Conclusions:

    • The Adaptive Multiple Feature Method (AMFM) provides an objective, reproducible, and automated tool for regional pulmonary parenchyma assessment from CT scans.
    • The AMFM performs comparably to experienced human observers, even when provided with patient diagnosis.
    • This automated method holds potential for improving the accuracy and consistency of lung tissue pattern classification.