Periodic Reporting for period 1 - PhyNeTouch (Multiphysics modelling and neural networks synergy to enhance the outcome of robotic catheter ablation for the treatment of atrial fibrillation)
Berichtszeitraum: 2022-01-01 bis 2023-12-31
This Marie Sklodowska Curie Action (MSCA) is titled “Multiphysics modelling and neural networks synergy to enhance the outcome of robotic catheter ablation for the treatment of atrial fibrillation”. This project aims to propose novel computational methods to assist the improved delivery of cardiac radiofrequency ablation for the treatment of atrial fibrilation. This is an important topic for society because atrial fibrillation is the most common cardiac arrhythmia and a major risk factor for ischemic stroke with serious health and socioeconomic implications for EU. Despite the superior outcome of catheter ablation, its success rate remains limited, and the complication risk significant.
To address this challenge, the objectives of this project are:
(1) to predict bioheat distribution in tissue with high accuracy, and
(2) to achieve real-time feedback through Neural Networks.
To address this challenge, the objectives of this project are:
(1) to predict bioheat distribution in tissue with high accuracy, and
(2) to achieve real-time feedback through Neural Networks.
Results of the project were the following:
(1) a meshless computational model was developed for lesion formation simulation during cardiac radiofrequency ablation
(2) simulations were evaluated with experimental data
(3) multisite ablation protocols were introduced in the simulation process
(4) physics informed neural networks were employed for lesion formation simulation
These results have been disseminated in three national and international conferences:
(1) BioMedEng’22, London 2022, United Kingdom
(2) The Hamlyn Symposium on Medical Robotics, London, United Kingdom
(3) IEEE Engineering in Medicine and Biology Society, Sydney, Australia
(1) a meshless computational model was developed for lesion formation simulation during cardiac radiofrequency ablation
(2) simulations were evaluated with experimental data
(3) multisite ablation protocols were introduced in the simulation process
(4) physics informed neural networks were employed for lesion formation simulation
These results have been disseminated in three national and international conferences:
(1) BioMedEng’22, London 2022, United Kingdom
(2) The Hamlyn Symposium on Medical Robotics, London, United Kingdom
(3) IEEE Engineering in Medicine and Biology Society, Sydney, Australia
This project has progressed the state of the art by providing novel computational models employing emerging technologies such as meshless methods and physics informed neural networks. Such models have the potential to be integrated in clinical systems to assist the catheter ablation treatment of atrial fibrillation in the future. This would allow the delivery of improved healthcare with less implications having a positive socio-economic impact in the Eurozone and beyond.