A Deep Learning Approach for Beamforming and Contrast Enhancement of Ultrasound Images in Monostatic Synthetic Aperture Imaging: A Proof-of-Concept.

Goal: In this study, we demonstrate that a deep neural network (DNN) can be trained to reconstruct high-contrast images, resembling those produced by the multistatic Synthetic Aperture (SA) method using a 128-element array, leveraging pre-beamforming radiofrequency (RF) signals acquired through the monostatic SA approach. Methods: A U-net was trained using 27200 pairs of RF signals, simulated considering a monostatic SA architecture, with their corresponding delay-and-sum beamformed target images in a multistatic 128-element SA configuration. The contrast was assessed on 500 simulated test images of anechoic/hyperechoic targets. The DNN's performance in reconstructing experimental images of a phantom and different in vivo scenarios was tested too. Results: The DNN, compared to the simple monostatic SA approach used to acquire pre-beamforming signals, generated better-quality images with higher contrast and reduced noise/artifacts. Conclusions: The obtained results suggest the potential for the development of a single-channel setup, simultaneously providing good-quality images and reducing hardware complexity.

Virtual Real-Time for High PRF Multiline Vector Doppler on ULA-OP 256.

The recent development of high-frame-rate (HFR) imaging/Doppler methods based on the transmission of plane or diverging waves has proposed new challenges to echographic data management and display. Due to the huge amount of data that need to be processed at very high speed, the pulse repetition frequency (PRF) is typically limited to hundreds hertz or few kilohertz. In Doppler applications, a PRF limitation may result unacceptable since it inherently translates to a corresponding limitation in the maximum detectable velocity. In this article, the ULA-OP 256 implementation of a novel ultrasound modality, called virtual real-time (VRT), is described. First, for a given HFR RT modality, the scanner displays the processed results while saving channel data into an internal buffer. Then, ULA-OP 256 switches to VRT mode, according to which the raw data stored in the buffer are immediately reprocessed by the same hardware used in RT. In the two phases, the ULA-OP 256 calculation power can be differently distributed to increase the acquisition frame rate or the quality of processing results. VRT was here used to extend the PRF limit in a multiline vector Doppler (MLVD) application. In RT, the PRF was maximized at the expense of the display quality; in VRT, data were reprocessed at a lower rate in a high-quality display format, which provides more detailed flow information. Experiments are reported in which the MLVD technique is shown capable of working at 16-kHz PRF, so that flow jet velocities higher up to 3 m/s can be detected.

In Vivo Comparison of Multiline Transmission and Diverging Wave Imaging for High-Frame-Rate Speckle-Tracking Echocardiography.

High-frame-rate (HFR) speckle-tracking echocardiography (STE) assesses myocardial function by quantifying motion and deformation at high temporal resolution. Among the proposed HFR techniques, multiline transmission (MLT) and diverging wave (DW) imaging have been used in this context both being characterized by specific advantages and disadvantages. Therefore, in this article, we directly contrast both approaches in an in vivo setting while operating at the same frame rate (FR). First, images were recorded at baseline (resting condition) from healthy volunteers and patients. Next, additional acquisitions during stress echocardiography were performed on volunteers. Each scan was contoured and processed by a previously proposed 2-D HFR STE algorithm based on cross correlation. Then, strain curves and their end-systolic (ES) values were extracted for all myocardial segments for further statistical analysis. The baseline acquisitions did not reveal differences in estimated strain between the acquisition modes ( ); myocardial segments ( ); or an interaction between imaging mode and depth ( ). Similarly, during stress testing, no difference ( p = 0.7 ) was observed for the two scan sequences, stress levels or an interaction sequence-stress level ( p = 0.94 ). Overall, our findings show that MLT and DW compoundings give comparable HFR STE strain values and that the choice for using one method or the other may thus rather be based on other factors, for example, system requirements or computational cost.

Architecture of an Ultrasound System for Continuous Real-Time High Frame Rate Imaging.

High frame rate (HFR) imaging methods based on the transmission of defocused or plane waves rather than focused beams are increasingly popular. However, the production of HFR images poses severe requirements both in the transmission and the reception sections of ultrasound scanners. In particular, major technical difficulties arise if the images must be continuously produced in real-time, i.e., without any acquisition interruption nor loss of data. This paper presents the implementation of the real-time HFR-compounded imaging application in the ULA-OP 256 research platform. The beamformer sustains an average output sample rate of 470 MSPS. This allows continuously producing coherently compounded images, each of 64 lines by 1280 depths (here corresponding to 15.7 mm width and 45 mm depth, respectively), at frame rates up to 5.3 kHz. Imaging tests addressed to evaluate the achievable speed and quality performance were conducted on phantom. Results obtained by real-time compounding frames obtained with different numbers of steering angles between +7.5° and -7.5° are presented.

ULA-OP 256: A 256-Channel Open Scanner for Development and Real-Time Implementation of New Ultrasound Methods.

Open scanners offer an increasing support to the ultrasound researchers who are involved in the experimental test of novel methods. Each system presents specific performance in terms of number of channels, flexibility, processing power, data storage capability, and overall dimensions. This paper reports the design criteria and hardware/software implementation details of a new 256-channel ultrasound advanced open platform. This system is organized in a modular architecture, including multiple front-end boards, interconnected by a high-speed (80 Gb/s) ring, capable of finely controlling all transmit (TX) and receive (RX) signals. High flexibility and processing power (equivalent to 2500 GFLOP) are guaranteed by the possibility of individually programming multiple digital signal processors and field programmable gate arrays. Eighty GB of on-board memory are available for the storage of prebeamforming, postbeamforming, and baseband data. The use of latest generation devices allowed to integrate all needed electronics in a small size ( 34 cm ×30 cm ×26 cm). The system implements a multiline beamformer that allows obtaining images of 96 lines by 2048 depths at a frame rate of 720 Hz (expandable to 3000 Hz). The multiline beamforming capability is also exploited to implement a real-time vector Doppler scheme in which a single TX and two independent RX apertures are simultaneously used to maintain the analysis over a full pulse repetition frequency range.