PINN-ing the Balloon: A Physically Informed Neural Network Modelling the Nonlinear Haemodynamic Response Function in MRI
Rodrigo H. Avaria, David Ortiz-Puerta, Javier Palma-Espinosa, Astrid Cancino, Pablo Cox, Rodrigo Salas, Stéren Chabert
This paper introduces a physics-informed neural network to model the haemodynamic response function in MRI, achieving high accuracy in estimating neurovascular state variables and BOLD signals.
bioRxiv · Aug 25, 2026 · PreprintNeuroscience