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 Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Improving visibility of small anatomical details on low and ultra-low dose computed tomography with artificial intelligence-based image reconstructions.

Radiation protection dosimetry·2026
Same author

Pulmonary Nodule Prevalence at CT in Middle-Aged Participants from the Swedish CArdioPulmonary bioImage Study (SCAPIS).

Radiology·2026
Same author

The acute pulmonary embolism CT protocol should not be optimized for acute aortic syndrome.

European heart journal. Cardiovascular Imaging·2026
Same author

Carotid plaque characteristics and their association with cardiovascular risk factors and coronary atherosclerosis in a middle-aged population.

Journal of cardiovascular magnetic resonance : official journal of the Society for Cardiovascular Magnetic Resonance·2026
Same author

Soft-tissue and half-value windows outperform bone window in ureteral stone size measurements in non-enhanced computed tomography.

Acta radiologica (Stockholm, Sweden : 1987)·2025
Same author

Head-to-Head Comparison between MRI and CT in the Evaluation of Volume and Quality of Epicardial Adipose Tissue.

Radiology. Cardiothoracic imaging·2025

Related Experiment Video

Updated: Dec 12, 2025

Multi-modal Pulmonary Imaging: Using Complementary Information from CT and Hyperpolarized 129Xe MRI to Evaluate Lung Structure-Function
02:09

Multi-modal Pulmonary Imaging: Using Complementary Information from CT and Hyperpolarized 129Xe MRI to Evaluate Lung Structure-Function

Published on: April 12, 2024

913

Multi-Reader-Multi-Split Annotation of Emphysema in Computed Tomography.

Mats Lidén1, Ola Hjelmgren2,3, Jenny Vikgren4

  • 1Department of Radiology, Faculty of Medicine and Health, Örebro University, Örebro, Sweden. matsliden@yahoo.com.

Journal of Digital Imaging
|August 12, 2020
PubMed
Summary

Training machine learning models for emphysema detection requires labeled computed tomography (CT) images. A multi-reader-multi-split method efficiently acquired these labels from radiologists, showing reasonable validity and inter-observer reliability for emphysema assessment.

Keywords:
Chronic Obstructive Pulmonary DiseaseComputed TomographyImage AnnotationMachine LearningObserver VariationPulmonary EmphysemaX-Ray

More Related Videos

Lung CT Segmentation to Identify Consolidations and Ground Glass Areas for Quantitative Assesment of SARS-CoV Pneumonia
08:05

Lung CT Segmentation to Identify Consolidations and Ground Glass Areas for Quantitative Assesment of SARS-CoV Pneumonia

Published on: December 19, 2020

14.6K
Automated Measurement of Pulmonary Emphysema and Small Airway Remodeling in Cigarette Smoke-exposed Mice
10:37

Automated Measurement of Pulmonary Emphysema and Small Airway Remodeling in Cigarette Smoke-exposed Mice

Published on: January 16, 2015

13.5K

Related Experiment Videos

Last Updated: Dec 12, 2025

Multi-modal Pulmonary Imaging: Using Complementary Information from CT and Hyperpolarized 129Xe MRI to Evaluate Lung Structure-Function
02:09

Multi-modal Pulmonary Imaging: Using Complementary Information from CT and Hyperpolarized 129Xe MRI to Evaluate Lung Structure-Function

Published on: April 12, 2024

913
Lung CT Segmentation to Identify Consolidations and Ground Glass Areas for Quantitative Assesment of SARS-CoV Pneumonia
08:05

Lung CT Segmentation to Identify Consolidations and Ground Glass Areas for Quantitative Assesment of SARS-CoV Pneumonia

Published on: December 19, 2020

14.6K
Automated Measurement of Pulmonary Emphysema and Small Airway Remodeling in Cigarette Smoke-exposed Mice
10:37

Automated Measurement of Pulmonary Emphysema and Small Airway Remodeling in Cigarette Smoke-exposed Mice

Published on: January 16, 2015

13.5K

Area of Science:

  • Radiology and Medical Imaging
  • Artificial Intelligence in Medicine
  • Pulmonary Medicine

Background:

  • Emphysema, characterized by pulmonary alveolar destruction, is visualized on computed tomography (CT) scans.
  • Training machine learning (ML) models for emphysema detection necessitates accurately labeled CT image data.
  • Acquiring these labels relies on trained radiologists, a resource often limited.

Purpose of the Study:

  • To evaluate the reading time, inter-observer reliability, and validity of the multi-reader-multi-split (MRMS) method for generating CT image labels for emphysema.
  • To assess the feasibility of using MRMS for large-scale emphysema quantification in CT imaging.

Main Methods:

  • Lung CT images from 102 subjects were split into 1-cm chunks, each containing 17 axial slices.
  • Twenty-six readers (radiologists and residents) were randomly assigned chunks to score emphysema type and severity.
  • A median reading time of 15 seconds per chunk was recorded, and labels were compared against existing regional annotations.

Main Results:

  • Inter-observer reliability (Krippendorff's alpha) was 0.40 for emphysema type and 0.53 for severity.
  • Reliability varied between apical and basal lung regions, being higher in the apical sections.
  • The emphysema scores generated via MRMS demonstrated general consistency with pre-existing regional annotations.

Conclusions:

  • The MRMS method offers a practical approach for generating reasonably valid emphysema image labels from CT scans.
  • This method can help overcome the limitations of expert reader availability for ML model training.
  • The study provides an estimation of inter-observer reliability for emphysema assessment using the MRMS technique.