Switchable deep beamformer for high-quality and real-time passive acoustic mapping
This work addresses the need for real-time, high-quality monitoring of microbubble cavitation in ultrasound therapy, offering a practical solution for medical applications, though it is incremental as it builds on existing deep learning and beamforming techniques.
The paper tackled the problem of high computational cost in data-adaptive beamformers for passive acoustic mapping (PAM) by developing a deep beamformer based on a generative adversarial network, which reduced computational cost by three orders of magnitude to 10.5 ms per image while maintaining image quality comparable to data-adaptive methods and improving signal-to-noise ratio by 9.3-22.9 dB compared to baseline methods.
Passive acoustic mapping (PAM) is a promising tool for monitoring acoustic cavitation activities in the applications of ultrasound therapy. Data-adaptive beamformers for PAM have better image quality compared to the time exposure acoustics (TEA) algorithms. However, the computational cost of data-adaptive beamformers is considerably expensive. In this work, we develop a deep beamformer based on a generative adversarial network, which can switch between different transducer arrays and reconstruct high-quality PAM images directly from radio frequency ultrasound signals with low computational cost. The deep beamformer was trained on the dataset consisting of simulated and experimental cavitation signals of single and multiple microbubble clouds measured by different (linear and phased) arrays covering 1-15 MHz. We compared the performance of the deep beamformer to TEA and three different data-adaptive beamformers using the simulated and experimental test dataset. Compared with TEA, the deep beamformer reduced the energy spread area by 18.9%-65.0% and improved the image signal-to-noise ratio by 9.3-22.9 dB in average for the different arrays in our data. Compared to the data-adaptive beamformers, the deep beamformer reduced the computational cost by three orders of magnitude achieving 10.5 ms image reconstruction speed in our data, while the image quality was as good as that of the data-adaptive beamformers. These results demonstrated the potential of the deep beamformer for high-resolution monitoring of microbubble cavitation activities for ultrasound therapy.