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

The integrity of the Circle of Willis predicted hemodynamic changes after bypass surgery in Moyamoya disease: a prospective cohort study by 4D flow MRI.

AJNR. American journal of neuroradiology·2026
Same author

Territorial heterogeneity of atherosclerosis and vascular calcification.

Nature cardiovascular research·2026
Same author

Diagnostic accuracy of third-generation dual-source dual-energy CT virtual non-contrast vs true non-contrast imaging in adrenal gland masses: a comparative study following the ACR guidelines.

La Radiologia medica·2026
Same author

Independent prognostic value of left ventricular stroke volume index in patients with takotsubo syndrome: insights from the EVOLUTION registry.

Heart (British Cardiac Society)·2026
Same author

Radiology appointment management in German hospitals: a survey of referring physicians.

Insights into imaging·2026
Same author

Gravitational 3D Magnetic Resonance Elastography for Differentiating Focal Nodular Hyperplasia and Hepatic Adenoma.

Diagnostics (Basel, Switzerland)·2026

Related Experiment Video

Updated: Mar 15, 2026

Ultrasound Based Assessment of Coronary Artery Flow and Coronary Flow Reserve Using the Pressure Overload Model in Mice
06:39

Ultrasound Based Assessment of Coronary Artery Flow and Coronary Flow Reserve Using the Pressure Overload Model in Mice

Published on: April 13, 2015

15.8K

Assessment of Fractional Flow Reserve from Coronary CT Angiography Using a Deep Learning-Based Algorithm: A

Ludovica R M Lanzafame1, Claudia Gulli1, Maria Teresa Cannizzaro2

  • 1Diagnostic and Interventional Radiology Unit, BIOMORF Department, University Hospital "Policlinico G. Martino", Via Consolare Valeria 1, 98100 Messina, Italy.

Diagnostics (Basel, Switzerland)
|March 14, 2026
PubMed
Summary

A deep learning algorithm accurately computes non-invasive fractional flow reserve (FFR-CT) from coronary computed tomography angiography (CCTA). This AI tool also reliably assigns cardiovascular risk categories, aiding in ischemia assessment and patient stratification.

Keywords:
Artificial Intelligencecoronary artery diseasecoronary computed tomography angiographycoronary stenosisdeep learningfractional flow reserveinvasive coronary angiography

More Related Videos

Author Spotlight: Improved Localization and Monitoring of Coronary Flow Reserve Using Modified PLAX View in Mice
05:07

Author Spotlight: Improved Localization and Monitoring of Coronary Flow Reserve Using Modified PLAX View in Mice

Published on: August 25, 2023

2.1K
Evaluation of Coronary Flow Reserve After Myocardial Ischemia Reperfusion in Rats
06:32

Evaluation of Coronary Flow Reserve After Myocardial Ischemia Reperfusion in Rats

Published on: June 28, 2019

8.6K

Related Experiment Videos

Last Updated: Mar 15, 2026

Ultrasound Based Assessment of Coronary Artery Flow and Coronary Flow Reserve Using the Pressure Overload Model in Mice
06:39

Ultrasound Based Assessment of Coronary Artery Flow and Coronary Flow Reserve Using the Pressure Overload Model in Mice

Published on: April 13, 2015

15.8K
Author Spotlight: Improved Localization and Monitoring of Coronary Flow Reserve Using Modified PLAX View in Mice
05:07

Author Spotlight: Improved Localization and Monitoring of Coronary Flow Reserve Using Modified PLAX View in Mice

Published on: August 25, 2023

2.1K
Evaluation of Coronary Flow Reserve After Myocardial Ischemia Reperfusion in Rats
06:32

Evaluation of Coronary Flow Reserve After Myocardial Ischemia Reperfusion in Rats

Published on: June 28, 2019

8.6K

Area of Science:

  • Cardiology
  • Radiology
  • Artificial Intelligence in Medicine

Background:

  • Coronary artery disease (CAD) diagnosis often relies on invasive procedures.
  • Non-invasive methods for assessing coronary stenosis severity are crucial for improving patient care.
  • Deep learning (DL) offers potential for advanced image analysis in cardiovascular imaging.

Purpose of the Study:

  • To evaluate the diagnostic accuracy of a DL-based algorithm for non-invasive fractional flow reserve (FFR-CT) calculation.
  • To assess the DL model's capability in automatically assigning Coronary Artery Disease-Reporting and Data System (CAD-RADS) risk categories.
  • To compare DL-derived FFR-CT and CAD-RADS classifications against invasive coronary angiography (ICA) and expert radiologist assessments.

Main Methods:

  • Retrospective analysis of coronary computed tomography angiography (CCTA) data from 60 patients with suspected CAD.
  • Application of a DL algorithm to estimate FFR-CT values and assign CAD-RADS categories from CCTA.
  • Evaluation of diagnostic performance using ICA as the reference standard, including ROC curve analysis and agreement statistics (Cohen's kappa).

Main Results:

  • FFR-CT derived from DL showed high diagnostic accuracy (AUC=0.935, sensitivity=93.2%, specificity=93.7%) for identifying significant coronary stenoses on a per-patient basis.
  • The DL model demonstrated excellent agreement with the reference standard (k=0.836) and consistent per-vessel performance.
  • Automated CAD-RADS classifications by the DL algorithm showed good agreement with expert radiologist assessments (k=0.765).

Conclusions:

  • The DL-based FFR-CT computation is a highly accurate, non-invasive method for assessing myocardial ischemia.
  • The algorithm's ability to automatically assign CAD-RADS categories enhances its utility for cardiovascular risk stratification.
  • This DL approach shows promise for improving the non-invasive diagnosis and management of coronary artery disease.