Learning beamforming in ultrasound imaging
This work addresses image quality issues in medical ultrasound imaging, which is incremental as it builds on existing beamforming techniques but introduces a novel learning-based approach.
The authors tackled the problem of improving ultrasound image quality by replacing the traditional processing pipeline with a data-driven, learnable method, resulting in significant improvements, particularly when learning both transmit beam patterns and reconstruction simultaneously.
Medical ultrasound (US) is a widespread imaging modality owing its popularity to cost efficiency, portability, speed, and lack of harmful ionizing radiation. In this paper, we demonstrate that replacing the traditional ultrasound processing pipeline with a data-driven, learnable counterpart leads to significant improvement in image quality. Moreover, we demonstrate that greater improvement can be achieved through a learning-based design of the transmitted beam patterns simultaneously with learning an image reconstruction pipeline. We evaluate our method on an in-vivo first-harmonic cardiac ultrasound dataset acquired from volunteers and demonstrate the significance of the learned pipeline and transmit beam patterns on the image quality when compared to standard transmit and receive beamformers used in high frame-rate US imaging. We believe that the presented methodology provides a fundamentally different perspective on the classical problem of ultrasound beam pattern design.