Physics-guided deep learning inference of intramural slow-conduction depth from simulated epicardial optical mapping
Abstract
Epicardial optical mapping integrates fluorescence over depth, making intramural slow conduction difficult to localize from surface signals alone. We present a simulation-based proof-of-concept study coupling monodomain electrophysiology and Monte Carlo photon transport to generate epicardial optical action potentials (OAPs) from slow-conduction layers in a 5 mm ventricular wall. In an initial 71-case depth sweep with fixed layer properties, 5-fold cross-validation of a one-dimensional residual network gave r=0.963 , R2=0.916 , and RMSE =0.298 mm, with reduced performance beyond approximately 3 mm. We then varied start depth (0.5–3.5 mm), thickness (0.15–0.50 mm), and conductivity multiplier (0.15–0.4) in a 279-case factorial study. Training the same architecture on this expanded dataset and using grouped-depth cross-validation, in which every substrate variant at each test depth was withheld, retained predictive depth information across all tested combinations ( r=0.852 , R2=0.717 , RMSE =0.476 mm), although accuracy varied with layer thickness and conductivity. Previously acquired rabbit optical and depth-stepped microelectrode recordings showed behaviour consistent with the simulated signals but were not used to train or quantitatively validate the estimator. These results demonstrate that simulated OAP morphology contains recoverable information about slow-layer depth across the tested variations in layer thickness and conductivity.
Related
- Sleep quality as a potential target in the behavioral network of children and adolescents with multimorbidity: a machine learning and computer‑simulated network intervention study
- Giant Aneurysm Involving the Sinus of Valsalva and the Right Coronary Artery with a Massive Intramural Thrombus
- Successful Conservative Management of a Traumatic Intramural Duodenal Hematoma Using a Double Elementary Diet Tube
- Salvage gastrectomy for perforated gastric intramural metastasis after definitive chemoradiotherapy for distal esophageal squamous cell carcinoma: a case report.
- Systematic Review and Meta-Analysis of Patients with Esophageal Cancer and Intramural Metastasis
BibTeX
@article{maciunas2026physicsguided,
title = {{Physics-guided deep learning inference of intramural slow-conduction depth from simulated epicardial optical mapping}},
author = {Kęstutis Maciūnas and Vaidotas Marozas and Steven E. Williams and Michelle C. Williams and Alan Ranieri Guimaraes and Neil Bodagh and Magda Klis and Vinush Vigneswaran and Ali Gharaviri and Arno von Kietzell and Regina Mačianskienė and Jonas Jurevičius},
journal = {Scientific Reports},
year = {2026},
month = oct,
doi = {10.1038/s41598-026-75905-2},
url = {https://www.nature.com/articles/s41598-026-75905-2},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Physics-guided deep learning inference of intramural slow-conduction depth from simulated epicardial optical mapping
AU - Kęstutis Maciūnas
AU - Vaidotas Marozas
AU - Steven E. Williams
AU - Michelle C. Williams
AU - Alan Ranieri Guimaraes
AU - Neil Bodagh
AU - Magda Klis
AU - Vinush Vigneswaran
AU - Ali Gharaviri
AU - Arno von Kietzell
AU - Regina Mačianskienė
AU - Jonas Jurevičius
PY - 2026
DA - 2026/10/17
JO - Scientific Reports
DO - 10.1038/s41598-026-75905-2
UR - https://www.nature.com/articles/s41598-026-75905-2
AB - Epicardial optical mapping integrates fluorescence over depth, making intramural slow conduction difficult to localize from surface signals alone. We present a simulation-based proof-of-concept study coupling monodomain electrophysiology and Monte Carlo photon transport to generate epicardial optical action potentials (OAPs) from slow-conduction layers in a 5 mm ventricular wall. In an initial 71-case depth sweep with fixed layer properties, 5-fold cross-validation of a one-dimensional residual network gave r=0.963 , R^2=0.916 , and RMSE =0.298 mm, with reduced performance beyond approximately 3 mm. We then varied start depth (0.5–3.5 mm), thickness (0.15–0.50 mm), and conductivity multiplier (0.15–0.4) in a 279-case factorial study. Training the same architecture on this expanded dataset and using grouped-depth cross-validation, in which every substrate variant at each test depth was withheld, retained predictive depth information across all tested combinations ( r=0.852 , R^2=0.717 , RMSE =0.476 mm), although accuracy varied with layer thickness and conductivity. Previously acquired rabbit optical and depth-stepped microelectrode recordings showed behaviour consistent with the simulated signals but were not used to train or quantitatively validate the estimator. These results demonstrate that simulated OAP morphology contains recoverable information about slow-layer depth across the tested variations in layer thickness and conductivity.
SN - 2045-2322
ER -