A pseudo non-linear method for fast simulations of ultrasonic reverberation

We investigate the use of deep neural networks (DNNs) for suppressing off-axis scattering in ultrasound channel data. Our implementation operates in the frequency domain via the short-time Fourier transform. The inputs to the DNN consisted of the separated real and imaginary components (i.e. in-phase and quadrature components) observed across the aperture of the array, at a single frequency and for a single depth. Different networks were trained for different frequencies. The output had the same structure as the input and the real and imaginary components were combined as complex data before an inverse short-time Fourier transform was used to reconstruct channel data. Using simulation, physical phantom experiment, and in vivo scans from a human liver, we compared this DNN approach to standard delay-and-sum (DAS) beamforming and an adaptive imaging technique that uses the coherence factor (CF). For a simulated point target, the side lobes when using the DNN approach were about 60 dB below those of standard DAS. For a simulated anechoic cyst, the DNN approach improved contrast ratio (CR) and contrast-to-noise (CNR) ratio by 8.8 dB and 0.3 dB, respectively, compared to DAS. For an anechoic cyst in a physical phantom, the DNN approach improved CR and CNR by 17.1 dB and 0.7 dB, respectively. For two in vivo scans, the DNN approach improved CR and CNR by 13.8 dB and 9.7 dB, respectively. We also explored methods for examining how the networks in this work function.

show abstract

“…Training data for networks to suppress acoustic reverberation could be created using simulation methods developed by Byram et al . [28]. …”

Section: Discussionmentioning

confidence: 99%

Deep Neural Networks for Ultrasound Beamforming

Luchies

Byram

2018

IEEE Trans. Med. Imaging

146

View full text Add to dashboard Cite

show abstract

“…4. A similar shifting method was implemented to simulate artifacts in ultrasound channel data [37]. To compare our two shifting methods, two networks were trained with the noiseless photoacoustic data containing finely spaced sources noted in Table I.…”

Section: Methodsmentioning

confidence: 99%

Photoacoustic Source Detection and Reflection Artifact Removal Enabled by Deep Learning

Allman

Reiter

Bell

2018

IEEE Trans. Med. Imaging

189

138

View full text Add to dashboard Cite

Interventional applications of photoacoustic imaging typically require visualization of point-like targets, such as the small, circular, cross-sectional tips of needles, catheters, or brachytherapy seeds. When these point-like targets are imaged in the presence of highly echogenic structures, the resulting photoacoustic wave creates a reflection artifact that may appear as a true signal. We propose to use deep learning techniques to identify these types of noise artifacts for removal in experimental photoacoustic data. To achieve this goal, a convolutional neural network (CNN) was first trained to locate and classify sources and artifacts in pre-beamformed data simulated with -Wave. Simulations initially contained one source and one artifact with various medium sound speeds and 2-D target locations. Based on 3,468 test images, we achieved a 100% success rate in classifying both sources and artifacts. After adding noise to assess potential performance in more realistic imaging environments, we achieved at least 98% success rates for channel signal-to-noise ratios (SNRs) of -9dB or greater, with a severe decrease in performance below -21dB channel SNR. We then explored training with multiple sources and two types of acoustic receivers and achieved similar success with detecting point sources. Networks trained with simulated data were then transferred to experimental waterbath and phantom data with 100% and 96.67% source classification accuracy, respectively (particularly when networks were tested at depths that were included during training). The corresponding mean ± one standard deviation of the point source location error was 0.40 ± 0.22 mm and 0.38 ± 0.25 mm for waterbath and phantom experimental data, respectively, which provides some indication of the resolution limits of our new CNN-based imaging system. We finally show that the CNN-based information can be displayed in a novel artifact-free image format, enabling us to effectively remove reflection artifacts from photoacoustic images, which is not possible with traditional geometry-based beamforming.

show abstract

“…This could be studied by introducing artefacts into these simulations, e.g. by following the strategy described in [43]. …”

Section: Resultsmentioning

confidence: 99%

Evaluation of the Transverse Oscillation Technique for Cardiac Phased Array Imaging: A Theoretical Study

Heyde

Bottenus

D'hooge

et al. 2017

IEEE Trans. Ultrason., Ferroelect., Freq. Contr.

View full text Add to dashboard Cite

The transverse oscillation (TO) technique can improve the estimation of tissue motion perpendicular to the ultrasound beam direction. TOs can be introduced using plane wave (PW) insonification and bi-lobed Gaussian apodisation (BA) on receive (abbreviated as PWTO). Furthermore, the TO frequency can be doubled after a heterodyning demodulation process is performed (abbreviated as PWTO*). This study is concerned with identifying the limitations of the PWTO technique in the specific context of myocardial deformation imaging with phased arrays and investigating the conditions in which it remains advantageous over traditional focused (FOC) beamforming. For this purpose, several tissue phantoms were simulated using Field II, undergoing a wide range of displacement magnitudes and modes (lateral, axial and rotational motion). The Cramer-Rao lower bound (CRLB) was used to optimize TO beamforming parameters and theoretically predict the fundamental tracking performance limits associated with the FOC, PWTO and PWTO* beamforming scenarios. This framework was extended to also predict performance for BA functions which are windowed by the physical aperture of the transducer, leading to higher lateral oscillations. It was found that windowed BA functions resulted in lower jitter errors compared to tradional BA functions. PWTO* outperformed FOC at all investigated SNR levels but only up to a certain displacement, with the advantage rapidly decreasing when SNR increased. These results suggest that PWTO* improves lateral tracking performance, but only when inter-frame displacements remain relatively low. The study concludes by translating these findings to a clinical environment by suggesting optimal scanner settings.

show abstract

A pseudo non-linear method for fast simulations of ultrasonic reverberation

Cited by 13 publications

References 15 publications

Deep Neural Networks for Ultrasound Beamforming

Deep Neural Networks for Ultrasound Beamforming

Photoacoustic Source Detection and Reflection Artifact Removal Enabled by Deep Learning

Evaluation of the Transverse Oscillation Technique for Cardiac Phased Array Imaging: A Theoretical Study

Contact Info

Product

Resources

About