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

Artificial intelligence for detecting acute heart failure on chest CT: prospective clinical proof-of-concept validation.

European radiology experimental·2026
Same author

Small Pulmonary Artery and Vein Volumes Independently Predict Oxygen Desaturation in Smokers.

Chronic obstructive pulmonary diseases (Miami, Fla.)·2026
Same author

Impact of 2 years of treatment with elexacaftor/tezacaftor/ivacaftor on longitudinal changes in structural lung disease in people with cystic fibrosis: results from the RECOVER trial.

Annals of the American Thoracic Society·2026
Same author

Assessing the feasibility of neonatal chest MRI for bronchopulmonary dysplasia using a standard 1.5-Tesla scanner.

European radiology·2026
Same author

The CFTR potentiator icenticaftor for treatment of bronchiectasis: an international phase 2, double-blind, randomized placebo-controlled trial.

American journal of respiratory and critical care medicine·2026
Same author

A fast fully automated approach for evaluating calcified lesions in intravascular ultrasound.

European heart journal. Digital health·2026

Related Experiment Video

Updated: Oct 11, 2025

Deep Learning-Based Segmentation of Cryo-Electron Tomograms
10:25

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

9.6K

Creating a training set for artificial intelligence from initial segmentations of airways.

Ivan Dudurych1, Antonio Garcia-Uceda2,3, Zaigham Saghir4,5

  • 1Department of Radiology, University of Groningen, University Medical Centre Groningen, Groningen, Netherlands. i.dudurych@umcg.nl.

European Radiology Experimental
|November 29, 2021
PubMed
Summary

Manual correction of AI-generated airway segmentations significantly improves accuracy for pulmonary disease research. This time-efficient method enhances artificial intelligence (AI) tool performance on specific datasets.

Keywords:
Artificial intelligenceImage processing (computer-assisted)Respiratory systemThoraxTomography (x-ray computed)

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

14.4K
Three-Dimensional Phase Resolved Functional Lung Magnetic Resonance Imaging
10:44

Three-Dimensional Phase Resolved Functional Lung Magnetic Resonance Imaging

Published on: June 21, 2024

688

Related Experiment Videos

Last Updated: Oct 11, 2025

Deep Learning-Based Segmentation of Cryo-Electron Tomograms
10:25

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

9.6K
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

14.4K
Three-Dimensional Phase Resolved Functional Lung Magnetic Resonance Imaging
10:44

Three-Dimensional Phase Resolved Functional Lung Magnetic Resonance Imaging

Published on: June 21, 2024

688

Area of Science:

  • Medical Imaging
  • Artificial Intelligence in Medicine
  • Pulmonary Research

Background:

  • Accurate airway segmentation is crucial for pulmonary disease research but is time-consuming.
  • Existing artificial intelligence (AI) tools require refinement for optimal performance on diverse datasets.

Purpose of the Study:

  • To improve airway segmentation accuracy using manual corrections and AI retraining.
  • To evaluate the impact of manual corrections on airway measurements and AI performance.

Main Methods:

  • Airway segmentation was performed using a 3D-Unet AI tool on low-dose chest CT scans.
  • Manual corrections were applied to initial segmentations using 3D Slicer software.
  • The corrected segmentations were used to retrain the 3D-Unet AI tool.

Main Results:

  • Manual correction significantly increased airway branching, length, and reduced luminal diameter (p < 0.001).
  • Retrained AI models showed improved segmentation, particularly in later airway generations (6th onwards).
  • Correction time averaged 2-4 hours per scan.

Conclusions:

  • Manual correction is a valuable method for enhancing AI-based airway segmentation.
  • This approach improves AI tool performance for specific research or clinical datasets.
  • The refined segmentations provide more accurate airway measurements for pulmonary research.