A novel Bayesian respiratory motion model to estimate and resolve uncertainty in image-guided cardiac interventions

► A novel respiratory motion model for image-guided cardiac interventions is presented. ► A Bayesian framework combines live 3D echo images and a cardiac respiratory motion model. ► Respiratory motion variability is estimated by the model and resolved by echo images. ► The Bayesian model is evaluated using nine simulated echo and four real echo datasets. ► The Bayesian model outperforms five comparative respiratory motion estimation methods.