A switchable deep beamformer for passive acoustic mapping

Passive acoustic mapping (PAM) has been proposed as a tool for monitoring cavitation activities in ultrasound therapy. Data adaptive beamformers for PAM have better image quality compared to the "delay and sum" operation-based methods, such as the time exposure acoustics (TEA) algorithm. However, the computational cost of data adaptive beamformers is considerably expensive. In this work, we develop a deep neural network based beamformer that can switch between different transducer arrays and reconstruct high quality PAM images with low computational cost. Using the simulated and experimental test dataset, the performance of the deep beamformer is evaluated.