English

High frame-rate cardiac ultrasound imaging with deep learning

Computer Vision and Pattern Recognition 2018-08-24 v1

Abstract

Cardiac ultrasound imaging requires a high frame rate in order to capture rapid motion. This can be achieved by multi-line acquisition (MLA), where several narrow-focused received lines are obtained from each wide-focused transmitted line. This shortens the acquisition time at the expense of introducing block artifacts. In this paper, we propose a data-driven learning-based approach to improve the MLA image quality. We train an end-to-end convolutional neural network on pairs of real ultrasound cardiac data, acquired through MLA and the corresponding single-line acquisition (SLA). The network achieves a significant improvement in image quality for both 55- and 77-line MLA resulting in a decorrelation measure similar to that of SLA while having the frame rate of MLA.

Keywords

Cite

@article{arxiv.1808.07823,
  title  = {High frame-rate cardiac ultrasound imaging with deep learning},
  author = {Ortal Senouf and Sanketh Vedula and Grigoriy Zurakhov and Alex M. Bronstein and Michael Zibulevsky and Oleg Michailovich and Dan Adam and David Blondheim},
  journal= {arXiv preprint arXiv:1808.07823},
  year   = {2018}
}

Comments

To appear in the Proceedings of MICCAI, 2018