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

Premature ventricular complexes.

Clinical medicine (London, England)·2026
Same author

Computational modelling for personalized transcatheter aortic valve replacement planning: a systematic review of complications and decision support.

Frontiers in digital health·2026
Same author

Posterior Electrical Axis Deviation Is Associated With Future Development of Left Bundle Branch Block: A UK Biobank Study.

JACC. Advances·2026
Same author

Assessment of the Relevant Field of View of Unipolar Electrodes Using In Vivo Imaging.

JACC. Clinical electrophysiology·2026
Same author

Long Noncoding RNA Associations Define an Interferon-Myeloid Immune Axis in Kawasaki Disease.

medRxiv : the preprint server for health sciences·2026
Same author

Validation of a 2-Gene Blood Test for Kawasaki Disease in Febrile Children.

JAMA network open·2026

Related Experiment Video

Updated: Nov 25, 2025

Estimating Bilateral Atrial Function by Cardiovascular Magnetic Resonance Feature Tracking in Patients with Paroxysmal Atrial Fibrillation
08:10

Estimating Bilateral Atrial Function by Cardiovascular Magnetic Resonance Feature Tracking in Patients with Paroxysmal Atrial Fibrillation

Published on: July 20, 2022

1.9K

Fully Automatic Atrial Fibrosis Assessment Using a Multilabel Convolutional Neural Network.

Orod Razeghi1, Iain Sim1, Caroline H Roney1

  • 1Biomedical Engineering and Imaging Sciences, King's College London, United Kingdom (O.R., I.S., C.H.R., R.K., H.C., J.W., L.O., R.M., M.O., S.E.W., S.N.).

Circulation. Cardiovascular Imaging
|December 15, 2020
PubMed
Summary
This summary is machine-generated.

This study introduces an automated pipeline for estimating atrial fibrosis from cardiac magnetic resonance scans, improving consistency in atrial fibrillation research. The open-source tool offers reproducible and operator-independent fibrosis burden measurements.

Keywords:
atrial fibrillationdeep learningfibrosismagnetic resonance imaging

More Related Videos

High-Resolution Endocardial and Epicardial Optical Mapping in a Sheep Model of Stretch-Induced Atrial Fibrillation
09:17

High-Resolution Endocardial and Epicardial Optical Mapping in a Sheep Model of Stretch-Induced Atrial Fibrillation

Published on: July 29, 2011

15.1K
Electrophysiological Assessment of Murine Atria with High-Resolution Optical Mapping
08:19

Electrophysiological Assessment of Murine Atria with High-Resolution Optical Mapping

Published on: February 22, 2018

10.2K

Related Experiment Videos

Last Updated: Nov 25, 2025

Estimating Bilateral Atrial Function by Cardiovascular Magnetic Resonance Feature Tracking in Patients with Paroxysmal Atrial Fibrillation
08:10

Estimating Bilateral Atrial Function by Cardiovascular Magnetic Resonance Feature Tracking in Patients with Paroxysmal Atrial Fibrillation

Published on: July 20, 2022

1.9K
High-Resolution Endocardial and Epicardial Optical Mapping in a Sheep Model of Stretch-Induced Atrial Fibrillation
09:17

High-Resolution Endocardial and Epicardial Optical Mapping in a Sheep Model of Stretch-Induced Atrial Fibrillation

Published on: July 29, 2011

15.1K
Electrophysiological Assessment of Murine Atria with High-Resolution Optical Mapping
08:19

Electrophysiological Assessment of Murine Atria with High-Resolution Optical Mapping

Published on: February 22, 2018

10.2K

Area of Science:

  • Cardiology
  • Medical Imaging
  • Computational Biology

Background:

  • Pathological atrial fibrosis is a key driver of sustained atrial fibrillation.
  • Late gadolinium enhancement (LGE) cardiac magnetic resonance (CMR) imaging is the current standard for noninvasively assessing atrial fibrosis.
  • Nonstandardized LGE processing leads to variability and limits clinical adoption.

Purpose of the Study:

  • To develop and validate a reproducible, operator-independent, fully automatic open-source pipeline for estimating atrial fibrosis from LGE-CMR scans.
  • To overcome limitations of manual LGE analysis, including operator and algorithm dependency.
  • To enhance the reliability and accessibility of atrial fibrosis quantification.

Main Methods:

  • A multilabel convolutional neural network was designed for automatic delineation of atrial structures.
  • The pipeline integrates segmentation and fibrosis quantification, removing operator-dependent steps.
  • Results were compared against manual fibrosis burden calculations using established intensity ratio thresholds (0.97, 1.61) and a signal +3.3 SD threshold.

Main Results:

  • The automatic atrial segmentation achieved a high Dice score of 91%, surpassing interobserver agreement (85%).
  • Excellent intraclass correlation coefficients (0.94-0.99) were observed between the automatic pipeline and manual analyses, outperforming interobserver correlations.
  • The automated analysis is rapid, requiring only 3 minutes per case on a standard workstation, and the software is publicly available.

Conclusions:

  • The developed pipeline offers a fully automatic and reproducible method for estimating atrial fibrosis burden from LGE-CMR.
  • This approach significantly reduces measurement variability, enhancing the reliability of fibrosis assessment.
  • The open-source nature promotes wider adoption and validation in atrial fibrillation research.