Abstract
Phase aberration in biomedical ultrasound imaging creates focusing error and reduces the imaging contrast and spatial resolution. Many works attempt to solve the phase aberration problem by using pre-beamformed channel data, but the computational complexity and memory consumption are heavy in the channel-data domain. To address this issue, we propose a novel adaptive ultrasound imaging technique using point spread function (PSF) reshaping filtering for phase aberration correction that works on beamformed baseband data (i.e., IQ data), available for almost all types of biomedical ultrasound imaging systems. The PSF reshaping filter is designed with the underlying phase aberrated PSF estimated by using a convolutional neural network and the corresponding aberration free PSF. Simulations and results on clinical data (not shown here) show that the reshaping filter can reduce the focusing error caused by phase aberration and increase imaging contrast and spatial resolution.