TY - GEN
T1 - Deep learning implementation of super-resolution ultrasound imaging for tissue decluttering and contrast agent localization
AU - Brown, Katherine
AU - Waggener, Scott Chase
AU - Redfern, Arthur David
AU - Hoyt, Kenneth
N1 - Funding Information:
ACKNOWLEDGMENT The authors would like to thank Arthur J. Redfern for many helpful discussions on the details of network architectures. This research was supported in part by NIH grant R01EB025841 and Texas CPRIT award RP180670.
Publisher Copyright:
© 2020 IEEE.
PY - 2020/9/7
Y1 - 2020/9/7
N2 - Super-resolution ultrasound (SR-US) imaging improves ultrasound (US) resolution by up to ten-fold. However, translation to the clinical setting has been hindered by long computation times. Conventional algorithms used to detect and localize a microbubble (MB) contrast agent during SR-US image construction suffer from high complexity and computational intensity. Deep learning methods have been used to help implement solutions to these two key SR-US image processing steps. Such developments allow frame processing on the time scale of milliseconds. The goal of this study was to combine a single deep network to both detect and localize MBs for use during SR-US imaging. We propose SRUSnet, which is a fully convolutional network architecture based on MobileNetV3 with enhancements for 2 + 1D input data, fast convergence time, and support for high-resolution data output. The architecture features both a classification and a regression head to provide a flexible level of increased resolution for the output SR-US image. Training was performed with synthetic in silico data computed as a sequence of images with MBs flowing at different rates against a background of tissue. In vitro imaging of a flow phantom perfused with MBs was performed using a programmable US scanner (Vantage 256, Verasonics Inc.) equipped with an L11-4v linear array transducer. The network operating on in silico data exceeded 99% detection accuracy and averaged less than the resolution of a pixel in localization accuracy (i.e. ?/8). The processing time for a 128 × 128-pixel image averaged 25.9 ms on a Nvidia GeForce 2080Ti GPU. Overall, these preliminary results are a promising advance in moving towards a real-time implementation of SR-US imaging.
AB - Super-resolution ultrasound (SR-US) imaging improves ultrasound (US) resolution by up to ten-fold. However, translation to the clinical setting has been hindered by long computation times. Conventional algorithms used to detect and localize a microbubble (MB) contrast agent during SR-US image construction suffer from high complexity and computational intensity. Deep learning methods have been used to help implement solutions to these two key SR-US image processing steps. Such developments allow frame processing on the time scale of milliseconds. The goal of this study was to combine a single deep network to both detect and localize MBs for use during SR-US imaging. We propose SRUSnet, which is a fully convolutional network architecture based on MobileNetV3 with enhancements for 2 + 1D input data, fast convergence time, and support for high-resolution data output. The architecture features both a classification and a regression head to provide a flexible level of increased resolution for the output SR-US image. Training was performed with synthetic in silico data computed as a sequence of images with MBs flowing at different rates against a background of tissue. In vitro imaging of a flow phantom perfused with MBs was performed using a programmable US scanner (Vantage 256, Verasonics Inc.) equipped with an L11-4v linear array transducer. The network operating on in silico data exceeded 99% detection accuracy and averaged less than the resolution of a pixel in localization accuracy (i.e. ?/8). The processing time for a 128 × 128-pixel image averaged 25.9 ms on a Nvidia GeForce 2080Ti GPU. Overall, these preliminary results are a promising advance in moving towards a real-time implementation of SR-US imaging.
KW - Contrast-enhanced ultrasound
KW - Deep learning
KW - Microbubbles
KW - Plane waves
KW - Super-resolution ultrasound
KW - Ultrasound
UR - http://www.scopus.com/inward/record.url?scp=85097902143&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85097902143&partnerID=8YFLogxK
U2 - 10.1109/IUS46767.2020.9251701
DO - 10.1109/IUS46767.2020.9251701
M3 - Conference contribution
AN - SCOPUS:85097902143
T3 - IEEE International Ultrasonics Symposium, IUS
BT - IUS 2020 - International Ultrasonics Symposium, Proceedings
PB - IEEE Computer Society
T2 - 2020 IEEE International Ultrasonics Symposium, IUS 2020
Y2 - 7 September 2020 through 11 September 2020
ER -