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

Explainable AI to identify radiographic features of pulmonary edema.

Radiology advances·2025
Same author

Segmentation and quantification of atherosclerotic plaques in optical coherence tomography.

Computers in biology and medicine·2025
Same author

Advancing laser ablation assessment in hyperspectral imaging through machine learning.

Computers in biology and medicine·2024
Same author

ML-driven segmentation of microvascular features during histological examination of tissue-engineered vascular grafts.

Frontiers in bioengineering and biotechnology·2024
Same author

Perfect prosthetic heart valve: generative design with machine learning, modeling, and optimization.

Frontiers in bioengineering and biotechnology·2023
Same author

Use of semi-synthetic data for catheter segmentation improvement.

Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society·2023

Related Experiment Video

Updated: Jan 9, 2026

Improved Registration of 3D CT Angiography with X-ray Fluoroscopy for Image Fusion During Transcatheter Aortic Valve Implantation
06:59

Improved Registration of 3D CT Angiography with X-ray Fluoroscopy for Image Fusion During Transcatheter Aortic Valve Implantation

Published on: June 3, 2018

11.0K

Optimized aortic root segmentation during transcatheter aortic valve implantation.

Nikita V Laptev1, Olga M Gerget2, Julia K Belova3

  • 1Siberian State Medical University, Tomsk, Russia.

Frontiers in Cardiovascular Medicine
|December 1, 2025
PubMed
Summary

Convolutional neural networks (CNNs) improve transcatheter aortic valve implantation (TAVI) accuracy by automatically segmenting the aortic root on angiographic images, aiding precise valve placement.

Keywords:
TAVIangiographic imagesaortic rootautomatic segmentationconvolutional neural networks

More Related Videos

Standardized Technique of Aortic Valve Re-implantation for Valve-sparing Aortic Root Replacement
14:14

Standardized Technique of Aortic Valve Re-implantation for Valve-sparing Aortic Root Replacement

Published on: December 11, 2017

14.6K
Full-root Aortic Valve Replacement by Stentless Aortic Xenografts in Patients with Small Aortic Roots
12:17

Full-root Aortic Valve Replacement by Stentless Aortic Xenografts in Patients with Small Aortic Roots

Published on: May 21, 2017

11.8K

Related Experiment Videos

Last Updated: Jan 9, 2026

Improved Registration of 3D CT Angiography with X-ray Fluoroscopy for Image Fusion During Transcatheter Aortic Valve Implantation
06:59

Improved Registration of 3D CT Angiography with X-ray Fluoroscopy for Image Fusion During Transcatheter Aortic Valve Implantation

Published on: June 3, 2018

11.0K
Standardized Technique of Aortic Valve Re-implantation for Valve-sparing Aortic Root Replacement
14:14

Standardized Technique of Aortic Valve Re-implantation for Valve-sparing Aortic Root Replacement

Published on: December 11, 2017

14.6K
Full-root Aortic Valve Replacement by Stentless Aortic Xenografts in Patients with Small Aortic Roots
12:17

Full-root Aortic Valve Replacement by Stentless Aortic Xenografts in Patients with Small Aortic Roots

Published on: May 21, 2017

11.8K

Area of Science:

  • Medical Imaging
  • Artificial Intelligence in Healthcare
  • Cardiovascular Surgery

Background:

  • Transcatheter aortic valve implantation (TAVI) is crucial for severe aortic stenosis.
  • Accurate valve positioning is vital for TAVI success, especially with minimal contrast use in chronic kidney disease patients.
  • Fluoroscopic imaging poses challenges due to low contrast, noise, and artifacts, hindering precise anatomical visualization.

Purpose of the Study:

  • To compare various convolutional neural network (CNN) architectures for automatic aortic root segmentation on angiographic images.
  • To identify the optimal CNN model for enhancing TAVI valve positioning accuracy.
  • To explore the potential of CNN-based segmentation in reducing contrast agent use and surgical risks.

Main Methods:

  • Comparative analysis of CNN architectures including FPN, U-Net++, DeepLabV3+, LinkNet, MA-Net, and PSPNet.
  • Models were trained and tested with optimized hyperparameters on angiographic datasets.
  • Performance was evaluated using Dice coefficients and average symmetric surface distance.

Main Results:

  • DeepLabV3+ and U-Net++ demonstrated stable convergence during training (median Dice ~0.88).
  • MA-Net and PSPNet achieved superior patient-level performance, with Dice coefficients of 0.942 and 0.936, respectively.
  • MA-Net and PSPNet also yielded a low average symmetric surface distance of 4.1 mm.

Conclusions:

  • CNN-based automatic aortic root segmentation significantly improves valve positioning accuracy in TAVI.
  • MA-Net and PSPNet show strong potential for clinical application in cardiac surgery decision-support systems.
  • These methods can reduce contrast agent dependency, minimize surgical risks, and enhance TAVI outcomes.