Characterizing the Robustness of a Physics-Informed Model for Anisotropic Conduction and Fiber Orientation Estimation in Atrial Tissue

Estimating heterogeneous conduction velocities (CVs) in the atria is essential for understanding arrhythmia mechanisms but remains challenging due to sparse and noisy clinical data. FiberNet, a physics-informed neural network-based method, offers a data-efficient approach to estimate direction-dependent CVs and fiber orientation from local activation time maps. We present a synthetic 2D benchmark setup, physiologically motivated by atrial tissue properties, specifically the preferential orientation of cardiomyocytes, as well as region-specific CVs and anisotropy ratios. By systematically varying data quality and fiber complexity, we analyzed FiberNet’s robustness and accuracy in estimating anisotropic properties across heterogeneous tissue, accounting for anatomical variability. Performance was evaluated using error thresholds of 30◦ for fiber angle (α) and 0.1 m/s and 0.2 m/s for CV. For uniform or sharply heterogeneous tissues, predictions were within these thresholds for 86 % (α), 67 % (CV, 0.1 m/s), and 79 % (CV, 0.2 m/s). Under Gaussian noise (σ = 1 m/s) percentages decreased to 61 %, 24 %, and 44 %, respectively. In regions with gradual fiber transitions, only 67 % of α predictions remained below 30◦. ... mehrThese results highlight conditions of reliable performance and opportunities for targeted improvement to advance clinical impact.