3 papers
eess.SP2022
Learning cardiac activation maps from 12-lead ECG with multi-fidelity Bayesian optimization on manifolds
Simone Pezzuto, Paris Perdikaris, Francisco Sahli Costabal
We propose a method for identifying an ectopic activation in the heart non-invasively. Ectopic activity in the heart can trigger deadly arrhythmias. The localization of the ectopic…
cs.LG2021
Learning atrial fiber orientations and conductivity tensors from intracardiac maps using physics-informed neural networks
Thomas Grandits, Simone Pezzuto, Francisco Sahli Costabal +4
Electroanatomical maps are a key tool in the diagnosis and treatment of atrial fibrillation. Current approaches focus on the activation times recorded. However, more information ca…
cs.LG2019
Multi-fidelity classification using Gaussian processes: accelerating the prediction of large-scale computational models
Francisco Sahli Costabal, Paris Perdikaris, Ellen Kuhl +1
Machine learning techniques typically rely on large datasets to create accurate classifiers. However, there are situations when data is scarce and expensive to acquire. This is the…