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 Experiment Video

Updated: Dec 27, 2025

Four-Dimensional Computed Tomography-Guided Valve Sizing for Transcatheter Pulmonary Valve Replacement
09:57

Four-Dimensional Computed Tomography-Guided Valve Sizing for Transcatheter Pulmonary Valve Replacement

Published on: January 20, 2022

3.0K

Recursive multiresolution convolutional neural networks for 3D aortic valve annulus planimetry.

Pascal Theriault-Lauzier1,2, Hind Alsosaimi3, Negareh Mousavi3

  • 1Division of Cardiology, University of Ottawa Heart Institute, Ottawa, ON, Canada. ptheriault@ottawaheart.ca.

International Journal of Computer Assisted Radiology and Surgery
|March 5, 2020
PubMed
Summary

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

Impact of a Cloud-Based Care Coordination Platform on False Cardiac Catheterization Laboratory Activations and Unnecessary Team Mobilization: Retrospective Cohort Study.

JMIR cardio·2026
Same author

Predictors of Procedural and Clinical Outcomes Following Transcatheter Tricuspid Edge-to-Edge Repair: An Expert Overview.

JACC. Cardiovascular interventions·2026
Same author

Impact of a Cloud-Based Care Coordination Platform on False Activations of the Cardiac Catheterization Laboratory and Unnecessary Team Mobilization: A Retrospective Cohort Study.

JMIR cardio·2026
Same author

Atorvastatin and left ventricular strain during anthracycline-based chemotherapy.

International journal of cardiology·2026
Same author

Natural History of Tricuspid Regurgitation Following Transcatheter Edge-to-Edge Repair: Insights From Clinical Trials and Multi-center Registries.

The Canadian journal of cardiology·2026
Same author

Predictors of Nonresponse to Transcatheter Edge-to-edge Repair in Atrial Functional Mitral Regurgitation.

The Canadian journal of cardiology·2026
This summary is machine-generated.

A novel convolutional neural network (CNN) accurately determines the aortic valve annular plane for transcatheter aortic valve replacement (TAVR) sizing. This AI approach achieves expert-level accuracy, improving TAVR planning for patients with aortic valve stenosis.

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Cardiovascular Surgery

Background:

  • Transcatheter aortic valve replacement (TAVR) is standard for severe symptomatic aortic valve stenosis.
  • Accurate TAVR device sizing relies on precise aortic valve annular plane determination from CT imaging.
  • Current methods for annular plane identification can be time-consuming and complex.

Purpose of the Study:

  • To present a fully tridimensional recursive multiresolution convolutional neural network (CNN).
  • To automatically infer the location and orientation of the aortic valve annular plane.
  • To enhance the accuracy and efficiency of TAVR planning.

Main Methods:

  • Development and training of a 3D CNN using TensorFlow on 1007 ECG-gated CT volumes from 94 patients.
Keywords:
HeartMachine learningNeural networkSegmentationX-ray imaging and computed tomography

More Related Videos

Quantifying Intermembrane Distances with Serial Image Dilations
07:45

Quantifying Intermembrane Distances with Serial Image Dilations

Published on: September 28, 2018

6.7K
Three-Dimensional Printing of a Complex Aortic Anomaly
03:40

Three-Dimensional Printing of a Complex Aortic Anomaly

Published on: November 1, 2018

7.0K

Related Experiment Videos

Last Updated: Dec 27, 2025

Four-Dimensional Computed Tomography-Guided Valve Sizing for Transcatheter Pulmonary Valve Replacement
09:57

Four-Dimensional Computed Tomography-Guided Valve Sizing for Transcatheter Pulmonary Valve Replacement

Published on: January 20, 2022

3.0K
Quantifying Intermembrane Distances with Serial Image Dilations
07:45

Quantifying Intermembrane Distances with Serial Image Dilations

Published on: September 28, 2018

6.7K
Three-Dimensional Printing of a Complex Aortic Anomaly
03:40

Three-Dimensional Printing of a Complex Aortic Anomaly

Published on: November 1, 2018

7.0K
  • Manual labeling of the aortic valve annular plane in the training dataset.
  • K-fold cross-validation (K=9) to evaluate algorithm performance.

    • Main Results:

    • Achieved clinically insignificant out-of-plane localization error (0.9 ± 0.8 mm) on the evaluation dataset.
    • Demonstrated expert-level angular orientation accuracy (6.4 ± 4.0°), with 84.6% of volumes < 10° error.
    • Reported low relative measurement errors for annular area (4.73 ± 5.32%) and perimeter (2.46 ± 2.94%).

    Conclusions:

    • The proposed CNN is the first to apply deep learning to aortic valve planimetry.
    • The algorithm achieves automated localization accuracy comparable to existing methods and expert-level orientation accuracy.
    • The method's generalizability to other anatomical structures warrants further investigation.