CNN-Based Ultrasound Image Reconstruction for Ultrafast Displacement Tracking

Perdios, Dimitris; Vonlanthen, Manuel; Martinez, Florian; Arditi, Marcel; Thiran, Jean‐Philippe

doi:10.1109/tmi.2020.3046700

Cited by 22 publications

(7 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Pregnant women with early severe preeclampsia usually have spasm of arterioles and vessel walls throughout the body, lumen stenosis, villous retardation, reduced blood flow to the umbilical artery, and increased blood flow resistance. Color Doppler ultrasound can detect that the umbilical artery-systolic/diastolic (UA-S/D) values increased, which affects the normal development of the fetus [9][10][11]. During clinical diagnosis, the ultrasonic imaging effect is poor because of the inherent patch noise and texture characteristics of ultrasonic instrument.…”

Section: Introductionmentioning

confidence: 99%

Value of Ultrasonic Image Features in Diagnosis of Perinatal Outcomes of Severe Preeclampsia on account of Deep Learning Algorithm

Wang

Liu

2022

Computational and Mathematical Methods in Medicine

View full text Add to dashboard Cite

This study is aimed at discussing the value of ultrasonic image features in diagnosis of perinatal outcomes of severe preeclampsia on account of deep learning algorithm. 140 pregnant women singleton with severe preeclampsia were selected as the observation group. At the same time, 140 normal singleton pregnant women were selected as the control group. The hemodynamic indexes were detected by color Doppler ultrasound. The CNN algorithm was used to classify ultrasound images of two groups of pregnant women. The differential scanning calorimetry (DSC), mean pixel accuracy (MPA), and mean intersection of union (MIOU) values of CNN algorithm were 0.9410, 0.9228, and 0.8968, respectively. Accuracy, precision, recall, and F 1 -score were 93.44%, 95.13%, 95.09%, and 94.87%, respectively. The differences were statistically significant ( P < 0.05 ). Compared with the normal control group, the umbilical artery (UA), uterine artery-systolic/diastolic (UTA-S/D), uterine artery (UTA), and digital video (DV) of pregnant women in the observation group were remarkably increased; the minimum alveolar effective concentration (MCA) of the observation group was obviously lower than the MCA of the control group, and the differences between groups were statistically valid ( P < 0.05 ). Logistic regression analysis showed that UA-S/D, UA-resistance index (UA-RI), UTA-S/D, UTA-pulsatility index (UTA-PI), DV-peak velocity index for veins (DV-PVIV), and MCA-S/D were independent risk factors for the outcome of perinatal children with severe preeclampsia. In the perinatal management of severe epilepsy, the combination of the above blood flow indexes to select the appropriate delivery time had positive significance to improve the pregnancy outcome and reduce the perinatal mortality.

show abstract

Section: Introductionmentioning

confidence: 99%

Value of Ultrasonic Image Features in Diagnosis of Perinatal Outcomes of Severe Preeclampsia on account of Deep Learning Algorithm

Wang

Liu

2022

Computational and Mathematical Methods in Medicine

View full text Add to dashboard Cite

show abstract

“…Our initial experiments in the context of pulse-echo synthetic aperture (SA) imaging indicated that we could reduce the computing time by approximately two orders magnitude, considering consumer-level central processing units (CPUs) (for Field II) and GPUs (for the proposed approach). Note that the initial goal of developing this approach was to enable us generating a sufficient amount of data for the purpose of training convolutional neural network (CNN)based image reconstruction methods in the context of US imaging (Perdios et al, 2020(Perdios et al, , 2021.…”

Section: Comparison With Other Strategiesmentioning

confidence: 99%

A spline-based spatial impulse response simulator

Perdios¹,

Martinez²,

Arditi³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

The spatial impulse response (SIR) method is a well-known approach to calculate transient acoustic fields of arbitrary-shape transducers. It involves the evaluation of a time-dependent surface integral. Although analytic expressions of the SIR exist for some geometries, numerical methods based on the discretization of transducer surfaces have become the standard. The proposed method consists of representing the transducer as a non-uniform rational B-spline (NURBS) surface, and decomposing it into smooth Bézier patches onto which quadrature rules can be deployed. The evaluation of the SIR can then be expressed in B-spline bases, resulting in a sum of shifted-and-weighted basis functions. Field signals are eventually obtained by a convolution of the basis coefficients, derived from the excitation waveform, and the basis SIR. The use of NURBS enables exact representations of common transducer elements. High-order Gaussian quadrature rules enable high accuracy with few quadrature points. High-order B-spline bases are ideally suited to exploit efficiently the bandlimited property of excitation waveforms. Numerical experiments demonstrate that the proposed approach enables sampling the SIR at low sampling rates, as required by the excitation waveform, without introducing additional errors on simulated field signals.[https://doi.org(DOI number)][XYZ] Pages: 1-12The need for fast and accurate ultrasound (US) simulation tools is as great as ever. Such tools have been and continue to be extensively used for the design and characterization of US transducers (Hunt et al., 1983;Kino, 1987). The use of end-to-end US scanner simulators is also increasing for the training and evaluation of physicians and sonographers (Lewiss et al., 2014;Ziv et al., 2006), as they eliminate the need for volunteers or patients and can provide on-demand exposure to specific care and diagnosis scenarios. Simulation tools are also crucial for the development, assessment, and validation of image analysis and image reconstruction methods. This includes, for example, the analysis and characterization of speckle patterns (Foster et al., 1983;Wagner et al., 1983), the optimization of application-specific acquisition sequences (Jensen et al., 2016), the fine-tuning and benchmarking of image reconstruction parameters and methods (Rindal et al., 2019), or the development of image quality metrics (Rodriguez-Molares et al., 2020). The recent breakthrough of deep learning-based methods in medical image analysis (

show abstract

“…The authors in [4] proposed a CNN-based US image reconstruction method that not only reduces artifacts and restores the speckle patterns of single ultrafast acquisitions but also can be used for displacement estimation [16]. Although this approach showed potential for recovering high-quality images from single unfocused acquisitions using simulated data, the quality improvement dropped significantly when applied to in vivo data due to the domain shift between in vivo and simulated data [4].…”

Section: Introductionmentioning

confidence: 99%

A KL Divergence-Based Loss for In Vivo Ultrafast Ultrasound Image Enhancement with Deep Learning

Viñals,

Thiran

2023

J. Imaging

Self Cite

View full text Add to dashboard Cite

Ultrafast ultrasound imaging, characterized by high frame rates, generates low-quality images. Convolutional neural networks (CNNs) have demonstrated great potential to enhance image quality without compromising the frame rate. However, CNNs have been mostly trained on simulated or phantom images, leading to suboptimal performance on in vivo images. In this study, we present a method to enhance the quality of single plane wave (PW) acquisitions using a CNN trained on in vivo images. Our contribution is twofold. Firstly, we introduce a training loss function that accounts for the high dynamic range of the radio frequency data and uses the Kullback–Leibler divergence to preserve the probability distributions of the echogenicity values. Secondly, we conduct an extensive performance analysis on a large new in vivo dataset of 20,000 images, comparing the predicted images to the target images resulting from the coherent compounding of 87 PWs. Applying a volunteer-based dataset split, the peak signal-to-noise ratio and structural similarity index measure increase, respectively, from 16.466 ± 0.801 dB and 0.105 ± 0.060, calculated between the single PW and target images, to 20.292 ± 0.307 dB and 0.272 ± 0.040, between predicted and target images. Our results demonstrate significant improvements in image quality, effectively reducing artifacts.

show abstract

CNN-Based Ultrasound Image Reconstruction for Ultrafast Displacement Tracking

Cited by 22 publications

References 38 publications

Value of Ultrasonic Image Features in Diagnosis of Perinatal Outcomes of Severe Preeclampsia on account of Deep Learning Algorithm

Value of Ultrasonic Image Features in Diagnosis of Perinatal Outcomes of Severe Preeclampsia on account of Deep Learning Algorithm

A spline-based spatial impulse response simulator

A KL Divergence-Based Loss for In Vivo Ultrafast Ultrasound Image Enhancement with Deep Learning

Contact Info

Product

Resources

About