Skip to main content
OSTI.GOVU.S. Department of Energy Office of Scientific and Technical Information
U.S. Department of Energy
Office of Scientific and Technical Information
 

Intracardiac Electrical Imaging using the 12-lead ECG: A Machine Learning Approach using Synthetic Data

Journal Article · · Computing in Cardiology (CinC) (Online)
 [1];  [1];  [2];  [1]
  1. Lawrence Livermore National Laboratory (LLNL), Livermore, CA (United States)
  2. Harvard Medical School, Boston, MA (United States)
+ Show Author Affiliations
Current state-of-the-art techniques for non-invasive imaging of cardiac electrical phenomena require voltage recordings from dozens of different torso locations and anatomical models built from expensive medical diagnostic imaging procedures. Here this study aimed to assess if recent machine learning advances could alternatively reconstruct electroanatomical maps at clinically relevant resolutions using only the standard 12-lead electrocardiogram (ECG) as input. To that end, a computational study was conducted to generate a dataset of over 16000 detailed cardiac simulations, which was then used to train neural network (NN) architectures designed to exploit both spatial and temporal correlations in the ECG signal. Analysis over a validation set showed average errors in activation map reconstruction below 1.7 msec over 75 intracardiac locations. Furthermore, phenotypical patterns of activation and the morphology of the activation potential were correctly reconstructed. The approach offers opportunities to stratify patients non-invasively, both retrospectively and prospectively, using metrics otherwise only available through invasive clinical procedures.
Research Organization:
Lawrence Livermore National Laboratory (LLNL), Livermore, CA (United States)
Sponsoring Organization:
USDOE Laboratory Directed Research and Development (LDRD) Program; USDOE National Nuclear Security Administration (NNSA)
Grant/Contract Number:
AC52-07NA27344
OSTI ID:
1968134
Report Number(s):
LLNL-JRNL-799842; 1002047
Journal Information:
Computing in Cardiology (CinC) (Online), Journal Name: Computing in Cardiology (CinC) (Online) Journal Issue: N/A Vol. 498; ISSN 2325-887X
Publisher:
IEEECopyright Statement
Country of Publication:
United States
Language:
English

References (3)

Dataset of Simulated Intracardiac Transmembrane Voltage Recordings and ECG Signals. In Lawrence Livermore National Laboratory (LLNL) Open Data Initiative dataset January 2022
Dataset of Simulated Intracardiac Transmembrane Voltage Recordings and ECG Signals dataset January 2022
Lawrence Livermore National Laboratory (LLNL) Open Data Initiative dataset January 2020

Figures / Tables (8)

Figure 1(p. 5)figure Figure 1
Figure 2(p. 6)figure Figure 2
Table 1(p. 8)table Table 1
Table 2(p. 8)table Table 2
Table 3(p. 9)table Table 3
Figure 3(p. 10)figure Figure 3
Figure 4(p. 11)figure Figure 4
Figure 5(p. 12)figure Figure 5

Similar Records

Dataset of Simulated Intracardiac Transmembrane Voltage Recordings and ECG Signals
Dataset · Thu May 19 00:00:00 EDT 2022 · OSTI ID:1870838
Efficient Computational Modeling of Human Ventricular Activation and Its Electrocardiographic Representation: A Sensitivity Study
Journal Article · Thu Mar 15 20:00:00 EDT 2018 · Cardiovascular Engineering and Technology · OSTI ID:1463971
Cardiac C-arm computed tomography using a 3D + time ROI reconstruction method with spatial and temporal regularization
Journal Article · Fri Feb 14 23:00:00 EST 2014 · Medical Physics · OSTI ID:22251179

Related Subjects

59 BASIC BIOLOGICAL SCIENCES
electrocardiography
imaging
machine learning
machine learning algorithms
measurement
torso
voltage