Switchable Deep Beamformer
This addresses the issue of high scanner resource demands for ultrasound imaging by enabling versatile beamforming with a single network, though it is incremental as it builds on existing deep beamformer technology.
The paper tackles the problem of needing separate trained beamformers for each ultrasound imaging application by proposing a switchable deep beamformer that can produce multiple output types like DAS, speckle removal, and deconvolution using a single network with a simple switch via Adaptive Instance Normalization (AdaIN). Experimental results with B-mode focused ultrasound confirm the method's flexibility and efficacy.
Recent proposals of deep beamformers using deep neural networks have attracted significant attention as computational efficient alternatives to adaptive and compressive beamformers. Moreover, deep beamformers are versatile in that image post-processing algorithms can be combined with the beamforming. Unfortunately, in the current technology, a separate beamformer should be trained and stored for each application, demanding significant scanner resources. To address this problem, here we propose a {\em switchable} deep beamformer that can produce various types of output such as DAS, speckle removal, deconvolution, etc., using a single network with a simple switch. In particular, the switch is implemented through Adaptive Instance Normalization (AdaIN) layers, so that various output can be generated by merely changing the AdaIN code. Experimental results using B-mode focused ultrasound confirm the flexibility and efficacy of the proposed methods for various applications.