Pose Estimation of Ultrasound Probe Using CNN and RNN with Image Reconstruction Loss

It is necessary to estimate the pose of the probe with high accuracy to reconstruct 3D ultrasound (US) images only from US image sequences scanned by a 1D-array probe. We propose the probe pose estimation method using Convolutional Neural Network (CNN) with training by image reconstruction loss. To calculate the image reconstruction loss, we use the image reconstruction network which consists of an encoder that extracts features from the two US images and a decoder that reconstructs the intermediate US image between the two images. CNN is trained to minimize the image reconstruction loss between the ground-truth image and the reconstructed image. Through experiments, we demonstrate that the proposed method exhibits efficient performance compared with the conventional methods.