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 interplay between dynamic regulation of ion-channel gating and trafficking in cardiac arrhythmogenesis.

The Journal of physiology·2026
Same author

Dipeptidyl aminopeptidase-like protein 6 regulates the <i>I</i><sub>Na</sub>-<i>I</i><sub>to</sub> balance influencing cardiac electrophysiology and arrhythmogenesis.

Science translational medicine·2026
Same author

Novel RYR2-A4510T Variant Presenting Both as Autosomal Dominant and Autosomal Recessive Catecholaminergic Polymorphic Ventricular Tachycardia.

Circulation. Genomic and precision medicine·2026
Same author

Implantable Cardioverter-Defibrillator Therapy and Implantable Cardioverter-Defibrillator Complications in Idiopathic Ventricular Fibrillation Patients.

JACC. Clinical electrophysiology·2026
Same author

Temporal variability of the electromechanical window in long-QT syndrome and drug-induced QT prolongation: Value for enhanced arrhythmia-risk assessment.

Heart rhythm·2026
Same author

Computer-aided characterization of the arrhythmogenic substrate after myocardial infarction.

Europace : European pacing, arrhythmias, and cardiac electrophysiology : journal of the working groups on cardiac pacing, arrhythmias, and cardiac cellular electrophysiology of the European Society of Cardiology·2026
Same journal

Real-time EEG-based epileptic seizure prediction using artificial intelligence: A systematic review.

Artificial intelligence in medicine·2026
Same journal

R-peak detection and ECG data compression scheme based on empirical mode decomposition and wavelet transform.

Artificial intelligence in medicine·2026
Same journal

CastNet: A three-channel EEG-based deep learning model for cross-subject depression detection.

Artificial intelligence in medicine·2026
Same journal

State-of-the-art TinyML approaches for colorectal cancer detection: Current advances, challenges, and future directions.

Artificial intelligence in medicine·2026
Same journal

JRadiEvo: A Japanese radiology report generation model enhanced by evolutionary optimization of model merging.

Artificial intelligence in medicine·2026
Same journal

Causally-informed deep learning towards explainable and generalizable outcome prediction in critical care.

Artificial intelligence in medicine·2026
See all related articles

Related Experiment Video

Updated: May 22, 2025

Patient-specific Modeling of the Heart: Estimation of Ventricular Fiber Orientations
12:09

Patient-specific Modeling of the Heart: Estimation of Ventricular Fiber Orientations

Published on: January 8, 2013

13.6K

Deep learning based estimation of heart surface potentials.

Tiantian Wang1, Joël M H Karel1, Niels Osnabrugge1

  • 1Department of Advanced Computing Sciences, Maastricht University, The Netherlands.

Artificial Intelligence in Medicine
|March 12, 2025
PubMed
Summary
This summary is machine-generated.

This study introduces a deep learning framework for noninvasive electrocardiographic imaging (ECGI) that estimates heart surface potentials from body surface potentials alone. The AI model achieves performance comparable to traditional methods, without requiring complex imaging, enabling wider clinical use.

Keywords:
Deep learningElectrocardiographic imagingInverse problem

More Related Videos

Author Spotlight: Advancing the Study of Brain-Heart Interplay with a Comprehensive EEGLAB Plugin for Multimodal Signal Analysis
08:22

Author Spotlight: Advancing the Study of Brain-Heart Interplay with a Comprehensive EEGLAB Plugin for Multimodal Signal Analysis

Published on: April 26, 2024

1.6K
Anesthesia-free Heartbeat Measurements in Freely Moving Zebrafish
03:57

Anesthesia-free Heartbeat Measurements in Freely Moving Zebrafish

Published on: April 18, 2025

245

Related Experiment Videos

Last Updated: May 22, 2025

Patient-specific Modeling of the Heart: Estimation of Ventricular Fiber Orientations
12:09

Patient-specific Modeling of the Heart: Estimation of Ventricular Fiber Orientations

Published on: January 8, 2013

13.6K
Author Spotlight: Advancing the Study of Brain-Heart Interplay with a Comprehensive EEGLAB Plugin for Multimodal Signal Analysis
08:22

Author Spotlight: Advancing the Study of Brain-Heart Interplay with a Comprehensive EEGLAB Plugin for Multimodal Signal Analysis

Published on: April 26, 2024

1.6K
Anesthesia-free Heartbeat Measurements in Freely Moving Zebrafish
03:57

Anesthesia-free Heartbeat Measurements in Freely Moving Zebrafish

Published on: April 18, 2025

245

Area of Science:

  • Computational electrophysiology
  • Medical imaging
  • Artificial intelligence in healthcare

Background:

  • Electrocardiographic imaging (ECGI) traditionally estimates heart potentials from body surface potentials using complex geometric data, limiting clinical application.
  • Current ECGI methods require detailed torso and heart geometry from imaging (e.g., CT/MRI), complicating workflow and increasing costs.

Purpose of the Study:

  • To develop a deep learning framework for estimating heart surface potentials (HSPMs) directly from body surface potentials (BSPMs), eliminating the need for anatomical imaging.
  • To enable wider and more cost-effective clinical application of ECGI.

Main Methods:

  • A deep learning framework utilizing a Pix2Pix network adapted for 2.5D data (2D BSPMs and HSPMs with temporal information).
  • Transformation of 3D torso and heart geometries into standardized 2D representations to handle diverse patient anatomies.
  • A novel loss function incorporating cosine similarity and input-specific weighting for improved accuracy.

Main Results:

  • The model achieved high accuracy in estimating HSPMs, with a mean absolute error (MAE) of 0.012 ± 0.011 and a structural similarity index measure (SSIM) of 0.984 ± 0.026.
  • Electrograms (EGMs) derived from the model showed strong correlation (Pearson correlation coefficient PCC = 0.643 ± 0.352) and low MAE (0.004 ± 0.004).
  • Estimated activation and recovery times demonstrated clinical relevance, with mean absolute differences of 6.05 ± 5.19 ms and 18.77 ± 17.30 ms, respectively.

Conclusions:

  • The deep learning framework accurately estimates heart surface potentials and related clinical metrics from body surface potentials alone, comparable to standard ECGI.
  • The model's ability to integrate spatial and temporal information without anatomical imaging facilitates broader clinical adoption.
  • Potential applications include cost-effective patient screening and post-operative follow-up in cardiology.