A Deep Learning Approach to Ultrasound Image Recovery

Based on the success of deep neural networks for image recovery, we propose a new paradigm for the compression and decompression of ultrasound~(US) signals which relies on stacked denoising autoencoders. The first layer of the network is used to compress the signals and the remaining layers perform the reconstruction. We train the network on simulated US signals and evaluate its quality on images of the publicly available PICMUS dataset. We demonstrate that such a simple architecture outperforms state-of-the art methods, based on the compressed sensing framework, both in terms of image quality and computational complexity.


Published in:
2017 Ieee International Ultrasonics Symposium (Ius)
Presented at:
IEEE International Ultrasonics Symposium, Washington, D.C., USA, September 6-9, 2017
Year:
2017
Publisher:
New York, Ieee
ISSN:
1948-5719
ISBN:
978-1-5386-3383-0
Keywords:
Laboratories:




 Record created 2017-09-06, last modified 2018-03-17

Preprint:
Download fulltextPDF
Presentation handout:
Download fulltextPDF
External link:
Download fulltextURL
Rate this document:

Rate this document:
1
2
3
 
(Not yet reviewed)