Ultrasound imaging is caught between the quest for the highest image quality, and the necessity for clinical usability. Our contribution is two-fold: First, we propose a novel fully convolutional neural network for ultrasound reconstruction. Second, a custom loss function tailored to the modality is employed for end-to-end training of the network. We demonstrate that training a network to map time-delayed raw data to a minimum variance ground truth offers performance increases in a clinical environment. In doing so, a path is explored towards improved clinically viable ultrasound reconstruction. The proposed method displays both promising image reconstruction quality and acquisition frequency when integrated for live ultrasound scanning. A clinical evaluation is conducted to verify the diagnostic usefulness of the proposed method in a clinical setting.
@article{arxiv.1904.04696,
title = {End-to-End Learning-Based Ultrasound Reconstruction},
author = {Walter Simson and Rüdiger Göbl and Magdalini Paschali and Markus Krönke and Klemens Scheidhauer and Wolfgang Weber and Nassir Navab},
journal= {arXiv preprint arXiv:1904.04696},
year = {2019}
}