Pilikos, G;
Horchens, L;
Batenburg, KJ;
Leeuwen, TV;
Lucka, F;
(2020)
Fast ultrasonic imaging using end-to-end deep learning.
In:
Proceedings of 2020 IEEE International Ultrasonics Symposium (IUS).
IEEE: Las Vegas, NV, USA.
Preview |
Text
2009.02194.pdf - Accepted Version Download (2MB) | Preview |
Abstract
Ultrasonic imaging algorithms used in many clinical and industrial applications consist of three steps: A data pre-processing, an image formation and an image post-processing step. For efficiency, image formation often relies on an approximation of the underlying wave physics. A prominent example is the Delay-And-Sum (DAS) algorithm used in reflectivity-based ultrasonic imaging. Recently, deep neural networks (DNNs) are being used for the data pre-processing and the image postprocessing steps separately. In this work, we propose a novel deep learning architecture that integrates all three steps to enable end-to-end training. We examine turning the DAS image formation method into a network layer that connects data pre-processing layers with image post-processing layers that perform segmentation. We demonstrate that this integrated approach clearly outperforms sequential approaches that are trained separately. While network training and evaluation is performed only on simulated data, we also showcase the potential of our approach on real data from a non-destructive testing scenario.
| Type: | Proceedings paper |
|---|---|
| Title: | Fast ultrasonic imaging using end-to-end deep learning |
| Event: | 2020 IEEE International Ultrasonics Symposium (IUS) |
| ISBN: | 978-1-7281-5448-0 |
| ISBN-13: | 978-1-7281-5449-7 |
| Open access status: | An open access version is available from UCL Discovery |
| DOI: | 10.1109/IUS46767.2020.9251550 |
| Publisher version: | http://doi.org/10.1109/IUS46767.2020.9251550 |
| Language: | English |
| Additional information: | This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions. |
| Keywords: | deep learning, end-to-end training, Delay-And-Sum, fast ultrasonic imaging, approximate inversion |
| UCL classification: | UCL UCL > Provost and Vice Provost Offices > UCL BEAMS UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science |
| URI: | https://discovery.ucl.ac.uk/id/eprint/10110741 |
Loading...
Loading...Loading...| 1. |  United States | 2 |
| 2. |  Russian Federation | 1 |
| 3. |  Europe | 1 |
| 4. |  Romania | 1 |
| 5. |  China | 1 |
Archive Staff Only
 |
View Item |
