Physics-based Deep Learning for Model Error Correction

Maxime Sermesant

Physics-based and data-driven approaches both progressed tremendously during the last decade. There is now increasing research activity at the interface between these two scientific areas. In particular, deep learning can be used to efficiently predict the solution to a given PDE. However, in most of these approaches, the learned model can at best achieve similar accuracy as the physics-based model used to train it. Therefore, the benefit can be reduced to a better computational efficiency, with the risk of a loss of realism for conditions far from the training data. I will present an approach to learn cardiac electrophysiology models and recent results on a new framework to learn model error from data. This has the potential to produce a final dynamical model combining simulation and learning that is closer to the reality than the original biophysical model.

Maxime Sermesant is a permanent researcher at Inria, the French research institute in digital sciences. He also obtained a chair of AI & Biophysics at the 3IA Côte d’Azur AI Institute, and created the Multimodal Data Science team at IHU Liryc in 2019. His research work combines biophysical and statistical modeling with clinical data. This is by nature a very collaborative and multi-disciplinary work at the intersection of academic, clinical and industrial environments. His research interests include biomedical image processing, organ modelling and machine learning. The integration of these areas open up possibilities in clinical data analysis for diagnosis, and in pathology simulation for therapy planning. His main focus has been the application of patient-specific models of the heart to cardiac pathologies. He received his Diploma in General Engineering from Ecole Centrale Paris, France in 1999, his MSc from Ecole Normale Superieure de Cachan, France in 1999, and his PhD in Control, Signal and Image Processing from the University of Nice – Sophia Antipolis, France in 2003. From June 2003 to December 2005, he was a Research Fellow with the Cardiac MR Research Group, Guy’s Hospital, King’s College London, UK and since 2005, he is a Research Scientist at Inria.