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

Imaging Studies for Cardiovascular System V: CT01:28

Imaging Studies for Cardiovascular System V: CT

673
Cardiac computed tomography (CT) scanning is an advanced cardiac imaging technique that utilizes CT technology, with or without intravenous (IV) contrast, to produce accurate cross-sectional virtual slices of specific areas of the heart, coronary circulation, and major blood vessels such as the aorta, pulmonary veins, and arteries. The computer processes these slices to generate three-dimensional images. Multidetector CT (MDCT) is a rapid form of CT scanning that captures multiple slices...
673

You might also read

Related Articles

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

Sort by
Same author

Characterization of CT Imaging-Derived Pulmonary Vascular Abnormalities Associated With Pulmonary Hypertension in Chronic Lung Disease.

Chest·2026
Same author

Measures of vascular volume in the lung: an emerging quantitative tool for clinical and physiological studies in pulmonary vascular disease.

American journal of respiratory cell and molecular biology·2026
Same author

The clinical relevance of chest computed tomography imaging in pulmonary hypertension associated with lung diseases.

Current opinion in pulmonary medicine·2026
Same author

Increased Venous Volumes in Response to Catheter-Based Intervention for Acute PE: Lessons From the OPTALYSE PE Trial (OPTALYSE-3D).

Circulation. Cardiovascular imaging·2026
Same author

Optimizing the Accuracy of Natural Language Processing Tools for Pulmonary Embolism Detection Through Integration with Claims Data: The PE-EHR+ Study.

Thrombosis and haemostasis·2026
Same author

Pulmonary vascular features on chest computed tomography differentially associate with adverse outcomes in smokers in COPDGene.

Annals of the American Thoracic Society·2025

Related Experiment Video

Updated: May 5, 2026

Author Spotlight: A 3D Digital Model for the Diagnosis and Treatment of Pulmonary Nodules
10:26

Author Spotlight: A 3D Digital Model for the Diagnosis and Treatment of Pulmonary Nodules

Published on: May 19, 2023

1.8K

DEEP-LEARNING STRATEGY FOR PULMONARY ARTERY-VEIN CLASSIFICATION OF NON-CONTRAST CT IMAGES.

P Nardelli1, D Jimenez-Carretero2, D Bermejo-Peláez2

  • 1Applied Chest Imaging Laboratory, Brigham and Women's Hospital, Boston, MA, USA.

Proceedings. IEEE International Symposium on Biomedical Imaging
|July 29, 2024
PubMed
Summary

This study introduces a new method for classifying pulmonary arteries and veins in CT scans using scale-space particle segmentation and a CNN-GC approach. The novel technique achieved 87% accuracy, outperforming traditional Random Forests.

Keywords:
Artery-vein segmentationFrangi filterconvolutional neural networkslung

More Related Videos

Author Spotlight: Advancing 3D Modeling for Enhanced Diagnosis and Treatment of Pulmonary Nodules in Early-Stage Lung Cancer
07:53

Author Spotlight: Advancing 3D Modeling for Enhanced Diagnosis and Treatment of Pulmonary Nodules in Early-Stage Lung Cancer

Published on: October 13, 2023

1.4K
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

470

Related Experiment Videos

Last Updated: May 5, 2026

Author Spotlight: A 3D Digital Model for the Diagnosis and Treatment of Pulmonary Nodules
10:26

Author Spotlight: A 3D Digital Model for the Diagnosis and Treatment of Pulmonary Nodules

Published on: May 19, 2023

1.8K
Author Spotlight: Advancing 3D Modeling for Enhanced Diagnosis and Treatment of Pulmonary Nodules in Early-Stage Lung Cancer
07:53

Author Spotlight: Advancing 3D Modeling for Enhanced Diagnosis and Treatment of Pulmonary Nodules in Early-Stage Lung Cancer

Published on: October 13, 2023

1.4K
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

470

Area of Science:

  • Medical imaging
  • Pulmonary vascular disease research
  • Artificial intelligence in radiology

Background:

  • Pulmonary vascular diseases impact both arteries and veins through diverse mechanisms.
  • Accurate artery-vein classification in computed tomography (CT) images is crucial for understanding and managing these conditions.
  • Current classification methods may lack the precision needed for complex pulmonary vasculature.

Purpose of the Study:

  • To develop and evaluate a novel automated method for segmenting and classifying pulmonary artery-vein structures in CT images.
  • To improve the accuracy of vessel classification by integrating scale-space particle segmentation with a convolutional neural network (CNN) and graph-cut (GC) algorithm.
  • To assess the algorithm's performance against manual classification and a Random Forests (RF) classifier.

Main Methods:

  • A novel approach combining scale-space particle segmentation for vessel isolation.
  • Classification of segmented particles using a hybrid CNN and graph-cut (GC) model.
  • Integration of airway proximity information via a bronchus-enhanced image to aid network learning.
  • Validation on the superior and inferior lobes of the right lung from twenty clinical CT cases.

Main Results:

  • The proposed algorithm achieved an overall accuracy of 87% in artery-vein classification when compared to manual reference standards.
  • This accuracy significantly surpasses the 73% accuracy obtained by a conventional Random Forests (RF) classifier.
  • The method demonstrated effective segmentation and classification of pulmonary vessels.

Conclusions:

  • The novel CNN-GC approach combined with scale-space segmentation offers a highly accurate and automated solution for pulmonary artery-vein classification in CT images.
  • This methodology shows significant potential for improving the diagnosis and management of pulmonary vascular diseases.
  • The algorithm's superior performance compared to RF highlights the effectiveness of deep learning and hybrid approaches in medical image analysis.