CNN-Based Image Reconstruction Method for Ultrafast Ultrasound Imaging

CNN-Based Ultrasound Image Reconstruction for Ultrafast Displacement Tracking

“…To obtain high-quality images from single-shot unfocused acquisitions, we relied on our CNN-based image reconstruction method proposed in [17], briefly summarized hereafter.…”

“…We considered a US acquisition system composed of a 9L-D transducer (GE Healthcare, Chicago, Illinois, USA) and a Vantage 256 system (Verasonics, Kirkland, WA, USA), identical to the one considered in [17]. Relevant imaging configuration parameters are summarized in Table I.…”

“…In [17], we introduced a method for reconstructing highquality US images from single unfocused acquisitions. It consists of a backprojection-based DAS operation followed by the application of a convolutional neural network (CNN), specifically trained to reduce the diffraction artifacts inherent to the deployed ultrafast US imaging setup.…”

“…In this work, we propose an approach for estimating 2-D inter-frame displacements at maximum frame rates, by combining our single-shot CNN-based image reconstruction method [17] with a state-of-the-art 2-D speckle tracking algorithm. Although estimating the axial displacement (only) remains the standard in US imaging, 2-D displacement estimation is increasingly gaining attention in both flow and tissue motion applications [5], [19], [20], as it allows the analysis of more complex motion patterns.…”

“…Since our aim is to tackle displacement estimation at maximum frame rates, the proposed approach relies only on single unfocused acquisitions to reconstruct consecutive frames and on two consecutive frames only to obtain 2-D displacement estimates. The primary goal of this work was to assess whether the diffraction artifact reduction and speckle restoration capabilities of our CNN-based image reconstruction method [17] could allow accurate estimation of displacements in zones initially shadowed by GL, SL, and EW artifacts. This work was conducted in the context of PW imaging with a linear transducer array (Section II).…”