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 VII: Vascular Imaging01:19

Imaging Studies VII: Vascular Imaging

DefinitionRenal angiography, also known as renal arteriography, is an imaging technique used to obtain a comprehensive view of blood flow and the vascular structure of blood vessels in the kidneys and surrounding areas.PurposeRenal angiography detects blood vessel abnormalities in the kidneys, such as aneurysms, stenosis, thrombosis, vascular tumors, and renal artery stenosis. It evaluates kidney function and guides interventional treatments like angioplasty or stent placement.Pre-Procedure...

You might also read

Related Articles

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

Sort by
Same author

Clinical utility of coronary CT angiography to guide PCI: a survey among P4 investigators.

The international journal of cardiovascular imaging·2025
Same author

Validation of contemporary methods to assess vessel specific myocardial mass.

Cardiovascular revascularization medicine : including molecular interventions·2025
Same author

Impact of Bifurcation Lesions on Outcomes After FFR-Guided PCI or CABG.

Circulation. Cardiovascular interventions·2024
Same author

Gender-Based Specificities of Fractional Flow Reserve Measurement.

Catheterization and cardiovascular interventions : official journal of the Society for Cardiac Angiography & Interventions·2024
Same author

Impact of Robotic Percutaneous Coronary Intervention (R-PCI) With and Without CCTA-Guidance on Clinical Outcomes and Hospital Economics: A Single Center Registry.

Catheterization and cardiovascular interventions : official journal of the Society for Cardiac Angiography & Interventions·2024
Same author

Sex Differences in Patients Undergoing FFR-Guided PCI or CABG in the FAME 3 Trial.

JACC. Cardiovascular interventions·2024

Related Experiment Video

Updated: Jun 27, 2026

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

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

8.6K

AngioPy Segmentation: An open-source, user-guided deep learning tool for coronary artery segmentation.

Thabo Mahendiran1, Dorina Thanou2, Ortal Senouf2

  • 1Department of Cardiology, Lausanne University Hospital, Lausanne, Switzerland; Mathematical Data Science, EPFL, Lausanne, Switzerland.

International Journal of Cardiology
|September 28, 2024
PubMed
Summary
This summary is machine-generated.

AngioPy, a deep learning tool, accurately segments coronary arteries without manual correction, improving quantitative coronary angiography (QCA) efficiency. This open-source model enhances 3D reconstructions and hemodynamic index accuracy.

Keywords:
Artificial intelligenceChronic coronary syndromesDeep learningOpen sourceQuantitative coronary angiographyStenosis assessment

More Related Videos

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

2.7K
Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies
04:25

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Published on: December 15, 2023

2.3K

Related Experiment Videos

Last Updated: Jun 27, 2026

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

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

8.6K
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

2.7K
Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies
04:25

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Published on: December 15, 2023

2.3K

Area of Science:

  • Cardiovascular imaging
  • Medical AI
  • Computational cardiology

Background:

  • Quantitative coronary angiography (QCA) traditionally relies on edge detection algorithms requiring manual correction, impacting 3D reconstructions and hemodynamic analysis accuracy.
  • Manual correction in QCA is time-consuming and can introduce variability.
  • Developing automated segmentation methods is crucial for improving QCA workflow and diagnostic precision.

Purpose of the Study:

  • To develop and validate AngioPy, a deep learning model for automated coronary artery segmentation.
  • To assess AngioPy's performance in terms of accuracy and efficiency compared to established QCA systems.
  • To evaluate the potential of AngioPy to minimize manual correction in QCA procedures.

Main Methods:

  • Deep learning models were trained on 2455 images from the FAME 2 study, incorporating user-defined ground-truth points.
  • External validation was performed on an independent dataset of 580 images.
  • Vessel dimensions, including minimal luminal diameter, were compared between AngioPy (uncorrected) and Medis QFR® using 203 images.

Main Results:

  • The top AngioPy model achieved a high F1 score of 0.927, with 99.2% of masks exceeding 0.8.
  • External validation confirmed robust performance with an F1 score of 0.924.
  • AngioPy demonstrated excellent agreement with QCA for vessel dimensions (r=0.96) and minimal luminal diameter (r=0.93), with minimal mean differences.

Conclusions:

  • AngioPy provides rapid and accurate coronary segmentation without manual correction, outperforming traditional methods.
  • The open-source AngioPy tool has the potential to significantly enhance the accuracy and efficiency of QCA.
  • This deep learning approach can improve downstream analyses like 3D reconstructions and hemodynamic calculations.