Physics-guided deep learning inference of intramural slow-conduction depth from simulated epicardial optical mapping

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. K.M. was supported by the Research Council of Lithuania (LMTLT) through a postdoctoral fellowship (No. NB is supported by the Medical Research Council (MR/Z504968/1).

S.E.W. is supported by the British Heart Foundation (FS/20/26/34952). MCW is supported by the British Heart Foundation (FS/ICRF/20/26002). The ECCI GPU is funded by SINAPSE.

Institute of Cardiology, Lithuanian University of Health Sciences, Sukilėlių pr. 15, LT-50103, Kaunas, Lithuania Kęstutis Maciūnas, Regina Mačianskienė & Jonas Jurevičius Biomedical Engineering Institute, Kaunas University of Technology, K. Baršausko st. 59, LT-51423, Kaunas, Lithuania Department of Electronics Engineering, Kaunas University of Technology, Studentų 50, LT-51368, Kaunas, Lithuania Centre for Cardiovascular Science, University of Edinburgh, Queen’s Medical Research Institute, 47 Little France Crescent, EH16 4TJ, Edinburgh, United Kingdom Kęstutis Maciūnas, Steven E. Williams, Alan Ranieri Guimaraes, Magda Klis, Vinush Vigneswaran, Ali Gharaviri & Arno von Kietzell Guy’s and St Thomas’ Hospital, King’s College London, Westminster Bridge Road, SE1 7EH, London, United Kingdom MCW has given talks for Canon Medical Systems, Siemens Healthineers, GE Healthcare, and Novartis and performed consultancy for FEOPS, Novartis, Bayer, Elucid and Canon Medical Systems.

Experimental recordings were obtained from previously performed animal experiments conducted in accordance with Directive 2010/63/EU and approved by the State Food and Veterinary Service of the Republic of Lithuania (permission No. No additional animal experiments were performed for this study. Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.