"Refining Image Quality: Deep Neural Network Applications in Plane Wave Medical Imaging"

With the goal to attain a high frame rate, plane wave imaging (PWI), a common swift ultrasonography imaging in medicine method, uses a solitary plane wave emission with no focal point. However, as compared to the widely utilized targeted line scan mode, the imaging quality is significantly reduced. Imaging performance can be enhanced with conventional adaptive beamformers, albeit at the expense of more processing. In the present study, we suggest employing a deep neural network (DNN) to maintain a high frame rate despite improving PWI performance. Specifically, the key contribution of this technology is The network input is the PWI response from a single point target, and the narrower scan response from the same point appears as the desired output. An amalgam of phantom investigations, in vivo research, and computations are used to assess the effectiveness of the suggested approach. For comparison coherence factor (CF), a prior anticipated deep learning-based technique, the delay-and-sum (DAS), and the DAS with a customized scan are employed. The performance is measured using numerical metrics, such as the speckle the contrast ratio (CR), signal-to-noise ratio, and contrast-to-noise ratio (CNR) (SSNR). The outcomes show that the suggested strategy is capable of achieving better contrast and resolution. In particular, the suggested approach outperforms the DAS across the board. While the CF offers a greater CR, the suggested The SSNR and CNR of this strategy are significantly greater. In addition, the total performance is comparable with concentrated scan performance and superior to the conventional deep learning technique. Furthermore, the suggested technique ensures good temporal resolution with less additional computation needed comparison to the DAS. The aforementioned results confirm that the suggested strategy is capable of producing high-quality images while preserving the high frame rate required for PWI.