Deep Learning Beamforming for Sub-Sampled Ultrasound Data
Simson W, Paschali M, Navab N, Zahnd G (2018)
Publication Type: Conference contribution
Publication year: 2018
Journal
Publisher: IEEE Computer Society
Book Volume: 2018-October
Conference Proceedings Title: IEEE International Ultrasonics Symposium, IUS
Event location: Kobe, JPN
ISBN: 9781538634257
DOI: 10.1109/ULTSYM.2018.8579818
Abstract
In medical imaging tasks, such as cardiac imaging, ultrasound acquisition time is crucial, however traditional high-quality beamforming techniques are computationally expensive and their performance is hindered by sub-sampled data. To this end, we propose DeepFormer, a method to reconstruct high quality ultrasound images in real-time on sub-sampled raw data by performing an end-to-end deep learning-based reconstruction. Results on an in vivo dataset of 19 participants show that DeepFormer offers promising advantages over traditional processing of sub-sampled raw-ultrasound data and produces reconstructions that are both qualitatively and visually equivalent to fully-sampled DeepFormed images.
Involved external institutions
Germany (DE)How to cite
APA:
Simson, W., Paschali, M., Navab, N., & Zahnd, G. (2018). Deep Learning Beamforming for Sub-Sampled Ultrasound Data. In IEEE International Ultrasonics Symposium, IUS. Kobe, JPN: IEEE Computer Society.
MLA:
Simson, Walter, et al. "Deep Learning Beamforming for Sub-Sampled Ultrasound Data." Proceedings of the 2018 IEEE International Ultrasonics Symposium, IUS 2018, Kobe, JPN IEEE Computer Society, 2018.
BibTeX: Download