Denisa Martonová

This study compares constitutive neural network predictions of fiber dispersion in the right ventricle with experimental data, showing that multi-axial loading improves parameter identifiability.

This paper develops a framework to discover constitutive models of passive myocardial mechanics directly from in vivo cardiac imaging data, improving accuracy over existing models.

This study evaluates the robustness of automated model discovery in human myocardial tissue by incorporating generalized structure tensors to account for fiber dispersion.

This paper automates cardiac tissue model discovery by training a neural network to identify the best model and parameters for human cardiac tissue.