Mapping myocardial activation distributions using neural networks: 2-D simulation results

T. R. Nelson, John M Boone

Research output: Contribution to journalArticle

Abstract

The goal of this study was to explore the capabilities of neural networks to map with accuracy the sequence and location of myocardial activation using QRS complexes simulating normal and altered activation. A two-dimensional (2- D) fractal-based computer model of myocardial activation was used to develop training data for initial network learning. Two types of activation scenarios were used to evaluate network learning: 1) 450 training sets based on three activation foci per set using randomly chosen times and activation sites, and 2) 199 training sets based on a sequential, hierarchical blocking of the fractal-based model conduction network. Network learning was evaluated with training and test cases using trained weights. Network-calculated activation maps compared with the target activation maps had a mean error of <5% in assigning the site and timing of activation. Pointwise mean correlation coefficients were >0.98 for all conduction network cases and >0.84 for the more demanding point foci cases. We conclude, based on these simulation results, that neural networks may be used to calculate activation maps using electrocardiogram lead data for a variety of activation patterns.

Original languageEnglish (US)
JournalAmerican Journal of Physiology - Heart and Circulatory Physiology
Volume267
Issue number5 36-5
StatePublished - 1994

Fingerprint

Fractals
Learning
Computer Simulation
Electrocardiography
Weights and Measures

Keywords

  • electrocardiogram analysis
  • electrocardiography
  • fractal activation

ASJC Scopus subject areas

  • Physiology

Cite this

@article{343409e150b04063ae0143f90ab48b8e,
title = "Mapping myocardial activation distributions using neural networks: 2-D simulation results",
abstract = "The goal of this study was to explore the capabilities of neural networks to map with accuracy the sequence and location of myocardial activation using QRS complexes simulating normal and altered activation. A two-dimensional (2- D) fractal-based computer model of myocardial activation was used to develop training data for initial network learning. Two types of activation scenarios were used to evaluate network learning: 1) 450 training sets based on three activation foci per set using randomly chosen times and activation sites, and 2) 199 training sets based on a sequential, hierarchical blocking of the fractal-based model conduction network. Network learning was evaluated with training and test cases using trained weights. Network-calculated activation maps compared with the target activation maps had a mean error of <5{\%} in assigning the site and timing of activation. Pointwise mean correlation coefficients were >0.98 for all conduction network cases and >0.84 for the more demanding point foci cases. We conclude, based on these simulation results, that neural networks may be used to calculate activation maps using electrocardiogram lead data for a variety of activation patterns.",
keywords = "electrocardiogram analysis, electrocardiography, fractal activation",
author = "Nelson, {T. R.} and Boone, {John M}",
year = "1994",
language = "English (US)",
volume = "267",
journal = "American Journal of Physiology - Renal Fluid and Electrolyte Physiology",
issn = "1931-857X",
publisher = "American Physiological Society",
number = "5 36-5",

}

TY - JOUR

T1 - Mapping myocardial activation distributions using neural networks

T2 - 2-D simulation results

AU - Nelson, T. R.

AU - Boone, John M

PY - 1994

Y1 - 1994

N2 - The goal of this study was to explore the capabilities of neural networks to map with accuracy the sequence and location of myocardial activation using QRS complexes simulating normal and altered activation. A two-dimensional (2- D) fractal-based computer model of myocardial activation was used to develop training data for initial network learning. Two types of activation scenarios were used to evaluate network learning: 1) 450 training sets based on three activation foci per set using randomly chosen times and activation sites, and 2) 199 training sets based on a sequential, hierarchical blocking of the fractal-based model conduction network. Network learning was evaluated with training and test cases using trained weights. Network-calculated activation maps compared with the target activation maps had a mean error of <5% in assigning the site and timing of activation. Pointwise mean correlation coefficients were >0.98 for all conduction network cases and >0.84 for the more demanding point foci cases. We conclude, based on these simulation results, that neural networks may be used to calculate activation maps using electrocardiogram lead data for a variety of activation patterns.

AB - The goal of this study was to explore the capabilities of neural networks to map with accuracy the sequence and location of myocardial activation using QRS complexes simulating normal and altered activation. A two-dimensional (2- D) fractal-based computer model of myocardial activation was used to develop training data for initial network learning. Two types of activation scenarios were used to evaluate network learning: 1) 450 training sets based on three activation foci per set using randomly chosen times and activation sites, and 2) 199 training sets based on a sequential, hierarchical blocking of the fractal-based model conduction network. Network learning was evaluated with training and test cases using trained weights. Network-calculated activation maps compared with the target activation maps had a mean error of <5% in assigning the site and timing of activation. Pointwise mean correlation coefficients were >0.98 for all conduction network cases and >0.84 for the more demanding point foci cases. We conclude, based on these simulation results, that neural networks may be used to calculate activation maps using electrocardiogram lead data for a variety of activation patterns.

KW - electrocardiogram analysis

KW - electrocardiography

KW - fractal activation

UR - http://www.scopus.com/inward/record.url?scp=0028072240&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0028072240&partnerID=8YFLogxK

M3 - Article

C2 - 7977838

AN - SCOPUS:0028072240

VL - 267

JO - American Journal of Physiology - Renal Fluid and Electrolyte Physiology

JF - American Journal of Physiology - Renal Fluid and Electrolyte Physiology

SN - 1931-857X

IS - 5 36-5

ER -