Haemodynamic monitoring is necessary for the effective management of critically ill cardiac patients. Pulmonary artery catheterization has been used for monitoring the circulation, for measurement of intracardiac pressures and to estimate preload and afterload. However, pressures may not be accurate reflection of the circulation and simultaneous measurement of volumes would improve patient treatment. However, measurement of cardiac volumes especially of the right ventricle is difficult in everyday clinical practice In this work we propose the use of pulmonary artery catheter (PAC) with ultrasonic sensors built on it, to calculate the right ventricular end-diastolic (RVEDV) and end-systolic volume (RVESV). This is achieved by using the Ultrasonic (US) beam, to measure the distances between the transducers on the catheter and the RV walls. These distances, will be used as an input to a Volume calculating algorithm, which finally provides the RVEDV and RVESV, using a Neural Network (NN). For that reason, we have used cardiac Magnetic Resonance Imaging (MRI) and have modeled the catheter and the US transducers, to get as input the distances to the surface of the cavity. With these distances, and the known cardiac volumes (calculated using MR images) we trained and validated a NN for volume calculation. The results show that the algorithm accurately calculates the RVEDV. For the RVESV, greater deviations are observed between values calculated with our algorithm and cardiac MRI.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.