Using back propagation neural network for cardiac wall motion detection on angiocardiography

We used back propagation neural network for cardiac wall motion detection on catheterization angiocardiography. Phantom images of two circular discs were generated to simulate the left ventricle. Training data sets were selected from the phantom images. After training, the neural network can perform cardiac wall motion detection for the phantom images and for all series of patients´ angiocardiographic images. The angiocardiography of one patient with normal cardiac wall motion and two patients with abnormal cardiac wall motion were acquired for cardiac wall motion detection. The results were displayed in the formats of vector fields superimposed on the original angiocardiographic images. The study showed that back propagation neural network was useful in the evaluation of cardiac wall motion on catheterization angiocardiography.