Abstract
Tissue elasticity can be locally estimated using shear-wave elastography (SWE), an advanced technique that measures the speed of laterally-traveling shear waves induced by a sequence of acoustic radiation force "push" pulses. However, SWE is not available on all ultrasound machines due to e.g. power, equipment, and procedural requirements; in particular, wireless devices would face challenges delivering the required power. Here, we propose a fully-convolutional deep neural network for the synthesis of an SWE image given the corresponding B-mode (side-by-side-view) image. Fifty patients diagnosed with prostate cancer underwent a transrectal SWE examination with SWE imaging regions chosen such that they covered the entire or parts of the prostate. The network was trained with the images of 40 patients and subsequently tested using 30 image planes from the remaining 10 patients. The neural network was able to accurately map the B-mode images to sSWE images with a pixel-wise mean absolute error of 4.8 kPa in terms of Young's modulus. Qualitatively, tumour sites characterized by high stiffness were mostly preserved (as validated by histopathology). Despite the need for further validation, our results already suggest that deep learning is a viable way to retrieve elasticity values from conventional B-mode images and can potentially provide valuable information for cancer diagnosis using devices on which no SWE imaging is available.
Original language | English |
---|---|
Title of host publication | 2019 IEEE International Ultrasonics Symposium, IUS 2019 |
Place of Publication | Piscataway |
Publisher | IEEE Computer Society |
Pages | 108-110 |
Number of pages | 3 |
ISBN (Electronic) | 9781728145969 |
DOIs | |
Publication status | Published - Oct 2019 |
Event | 2019 IEEE International Ultrasonics Symposium, IUS 2019 - Glasgow, United Kingdom Duration: 6 Oct 2019 → 9 Oct 2019 |
Conference
Conference | 2019 IEEE International Ultrasonics Symposium, IUS 2019 |
---|---|
Country/Territory | United Kingdom |
City | Glasgow |
Period | 6/10/19 → 9/10/19 |
Funding
This research was conducted in the framework of the IMPULS2 program within the Eindhoven University in collaboration with Philips. It also received funding from the Dutch Cancer Society (#UVA2013-5941) and a European Research Council Starting Grant (#280209). Furthermore, the authors would like to acknowledge SuperSonic Imagine (Aix-en-Provence, France) for providing the Aixplorer ultrasound scanner as well as NVIDIA Corporation for granting the Titan XP graphics processing unit.
Keywords
- B-mode Ultrasound
- Convolutional Neural Networks
- Deep Learning
- Shear-Wave Elastography