Deep Adaptive Electrocardiographic Imaging with Generative Forward Model for Error Reduction

Maryam Toloubidokhti, Prashnna K. Gyawali, Omar A. Gharbia, Xiajun Jiang, Jaume Coll-Font, Jake A. Bergquist, Brian Zenger, Wilson W. Good, Dana H. Brooks, Rob S. MacLeod, Linwei Wang

Abstract: Accuracy of estimating the heart’s electrical activity with Electrocardiographic Imaging (ECGI) is challenging due to using an error-prone physics-based model (forward model). While getting better results than the traditional numerical methods following the underlying physics, modern deep learning approaches ignore the physics behind the electrical propagation in the body and do not allow the use of patient-specific geometry. We introduce a deep-learning-based ECGI framework capable of understanding the underlying physics, aware of geometry, and adjustable to patient-specific data. Using a variational autoencoder (VAE), we uncover the forward model’s parameter space, and when solving the inverse problem, these parameters will be optimized to reduce the errors in the forward model. In both simulation and real data experiments, we demonstrated the ability of the presented framework to provide accurate reconstruction of the heart’s electrical potentials and localization of the earliest activation sites.