The application of artificial neural networks to intraventricular impedance imaging

An Intraventricular Impedance Imaging (III) system, that will be used for assessing electrical and mechanical cardiac properties via an intraventricular catheter, is presently under development. Existing methods for determining catheter position within a cardiac ventricle include X-ray, fluoroscopy and computer tomography, are accurate but cumbersome, expensive, and unable to ascertain the continuous real-time intraventricular catheter position. The purpose of this work was to perform a preliminary analysis to determine the suitability of using Artificial Neural Networks (ANN) as a tool for determining the continuous real-time intraventricular catheter position. Numerical simulations were performed using a model developed for a cylindrical catheter placed in an ellipsoidal heart ventricle. Data from these simulations are used in training a backpropagation network to determine the catheter position based on potentials measured along the catheter surface. The results indicate that ANN show great promise as a tool in determining the continuous real-time intraventricular catheter position