The solution to the inverse problem of electrocardiography enables a novel imaging technology to noninvasively assess the heart function. Statistical methods have been used to tackle the ill-posedness of the inverse problem. In this study, a Gaussian process model is incorporated into the classical Bayesian solution framework to combine spatial information and reflect realistic activation patterns on the heart tissue. I demonstrate that the solution using the proposed method outperforms the most commonly used empirical method in robustness and fidelity.
Please read this report for details.