[Ultrafast Imaging of Coherent Plane-wave Compouding Based on a Small Size Ultrasound Transducer].

The ultrasound endoscopic probes with very small size transducers are normally imaging by focused ultrasound beamforming technology. So the imaging frame rate is not very high, which cannot meet the needs of some clinical applications based on high imaging rate. In recent years, plane-wave ultrafast imaging technology can obtain high image frame rate and guarantee the image quality. In this paper, a plane wave ultra-fast imaging technique based on a home-made small line array ultrasound transducer is presented. Feasibility of the method is verified by simulation estimations and phantom experiments. The results show that for the small size transducer design of plane wave ultrafast imaging, it is necessary to fully consider the combination of the array element width and the number of array elements. So that a good plane wave imaging quality can be obtained. It lays a foundation for the ultra-fast imaging of plane wave in the interventional ultrasound imaging and ultrasound endoscopy.

[Multi-angle Plane-wave Beamforming Algorithm Based on CUDA].

Multi-angle plane-wave beamforming algorithm is the basis of ultra-fast ultrasonic imaging. It can be used to improve the imaging frame rate and resolution of traditional focused ultrasound. However, the existing multi-angle plane-wave technology can not satisfy the real-time imaging requirements due to the huge amount of computation required by CPU. In this paper, We proposed a parallel processing method to reduce the computation time based on compute unified device architecture(CUDA). Simulation analysis and contrast experiment were conducted to verify its performance. Experimental results show that the execution time based on GPU is much less than that based on CPU, thus the computational speed is accelerated significantly to satisfy the demand of ultrafast imaging.

Eigenspace-based beamformer using oblique signal subspace projection for ultrasound plane-wave imaging.

BACKGROUND: The Eigenspace-based beamformers, by orthogonal projection of signal subspace, can remove a large part of the noise, and provide better imaging contrast upon the minimum variance beamformer. However, wrong estimate of signal and noise component may bring dark-spot artifacts and distort the signal intensity. The signal component and noise and interference components are considered uncorrelated in conventional eigenspace-based beamforming methods. In ultrasound imaging, however, signal and noise are highly correlated. Therefore, the oblique projection instead of orthogonal projection should be taken into account in the denoising procedure of eigenspace-based beamforming algorithm. METHODS: In this paper, we propose a novel eigenspace-based beamformer based on the oblique subspace projection that allows for consideration of the signal and noise correlation. Signal-to-interference-pulse-noise ratio and an eigen-decomposing scheme are investigated to propose a new signal and noise subspaces identification. To calculate the beamformer weights, the minimum variance weight vector is projected onto the signal subspace along the noise subspace via an oblique projection matrix. RESULTS: We have assessed the performance of proposed beamformer by using both simulated software and real data from Verasonics system. The results have exhibited the improved imaging qualities of the proposed beamformer in terms of imaging resolution, speckle preservation, imaging contrast, and dynamic range. CONCLUSIONS: Results have shown that, in ultrasound imaging, oblique projection is more sensible and effective than orthogonal subspace projection. Better signal and speckle preservation could be obtained by oblique projection compare to orthogonal projection. Also shadowing artifacts around the hyperechoic targets have been eliminated. Implementation the new subspace identification has enhanced the imaging resolution of the minimum variance beamformer due to the increasing the signal power in direction of arrival. Also it has offered better sidelobe suppression and a higher dynamic range.

A progressively dual reconstruction network for plane wave beamforming with both paired and unpaired training data.

High-frame-rate plane wave (PW) imaging suffers from unsatisfactory image quality due to the absence of focus in transmission. Although coherent compounding from tens of PWs can improve PW image quality, it in turn results in a decreased frame rate, which is limited for tracking fast moving tissues. To overcome the trade-off between frame rate and image quality, we propose a progressively dual reconstruction network (PDRN) to achieve adaptive beamforming and enhance the image quality via both supervised and transfer learning in the condition of single or a few PWs transmission. Specifically, the proposed model contains a progressive network and a dual network to form a close loop and provide collaborative supervision for model optimization. The progressive network takes the channel delay of each spatial point as input and progressively learns coherent compounding beamformed data with increased numbers of steered PWs step by step. The dual network learns the downsampling process and reconstructs the beamformed data with decreased numbers of steered PWs, which reduces the space of the possible learning functions and improves the model's discriminative ability. In addition, the dual network is leveraged to perform transfer learning for the training data without sufficient steered PWs. The simulated, in vivo, vocal cords (VCs), and public available CUBDL dataset are collected for model evaluation.

A robust cascaded deep neural network for image reconstruction of single plane wave ultrasound RF data.

Reconstruction of ultrasound data from single plane wave Radio Frequency (RF) data is a challenging task. The traditional Delay and Sum (DAS) method produces an image with low resolution and contrast, if employed with RF data from only a single plane wave. A Coherent Compounding (CC) method that reconstructs the image by coherently summing the individual DAS images was proposed to enhance the image quality. However, CC relies on a large number of plane waves to accurately sum the individual DAS images, hence it produces high quality images but with low frame rate that may not be suitable for time-demanding applications. Therefore, there is a need for a method that can create a high quality image with higher frame rates. Furthermore, the method needs to be robust against the input transmission angle of the plane wave. To reduce the method's dependence on the input angle, we propose to unify the RF data at different angles by learning a linear data transformation from different angled data to a common, 0° data. We further propose a cascade of two independent neural networks to reconstruct an image, similar in quality to CC, by making use of a single plane wave. The first network, denoted as "PixelNet", is a fully Convolutional Neural Network (CNN) which takes in the transformed time-delayed RF data as input. PixelNet learns optimal pixel weights that get element-wise multiplied with the single angle DAS image. The second network is a conditional Generative Adversarial Network (cGAN) which is used to further enhance the image quality. Our networks were trained on the publicly available PICMUS and CPWC datasets and evaluated on a completely separate, CUBDL dataset obtained from different acquisition settings than the training dataset. The results thus obtained on the testing dataset, demonstrate the networks' ability to generalize well on unseen data, with frame rates better than the CC method. This paves the way for applications that require high-quality images reconstructed at higher frame rates.