Using Neural Network for Cardiac Motion Analysis of Tc-99m Labeled RBC Radionuclide Angiography

In this study we investigated the utilization of back propagation neural network for cardiac left ventricular motion analysis of Tc-99m labeled RBC radionuclide angiography. Serial spherical phantom images were generated to simulate cardiac motion of left ventricle, and as training data. After the neural network was trained and showed convergence, the neural network can perform motion analysis for all serial images and also for all series of patients' images. The results of motion analysis were displayed in the format of vector fields superimposed on the original medical images. The study showed that cardiac ventricular motion analysis by back propagation neural network was useful in the evaluation of Tc-99m labeled RBC radionuclide angiography.