3-D heart contour delineation and motion tracking of ultrasound images using continuous distance transform neural networks

We apply the previously proposed continuous distance transform neural network (CDTNN) to effectively represent the 3-D endocardial (inner) and epicardial (outer) contours and track the motion of the left ventricle (principal pumping chamber) of the heart from ultrasound images. This CDTNN has many good properties as the conventional distance transforms which are suitable for 3-D object representation and deformation estimation. In addition, this continuous and differentiable representation is parametric so that very low memory storage is needed. We have successfully represented the 3-D epicardial and endocardial walls of the left ventricle of the heart using CDTNNs based on 7.5% to 25% of manually traced training data. The absolute error measured compares favorably with the human interobserver variability reported for analyzing distances.