Mathias Peirlinck

This study translates lab-based arterial stress-stretch data into clinically relevant pressure-diameter predictions using a fiber-reinforced model and systematic validation.

Constitutive artificial neural networks trained on biaxial tests of 8 ovine main pulmonary artery samples consistently discover a two-term model: exponential first-invariant plus quadratic fifth-invariant terms.

This paper automates material model selection in finite element simulations using constitutive neural networks, improving robustness and accessibility of biomedical simulations.

The paper develops a computational pipeline to create digital twins of cardiac electrophysiology for pediatric congenital heart disease patients using BLNMs to match clinical ECGs.

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