Efficient B-Mode Ultrasound Image Reconstruction From Sub-Sampled RF Data Using Deep Learning

Yoon, Yeo Hun; Khan, Shujaat; Huh, Jaeyoung; Ye, Jong Chul

doi:10.1109/tmi.2018.2864821

Cited by 116 publications

(84 citation statements)

References 54 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The contrast of the Deep BF, especially at anechoic regions, are very close to the full sampled case, whereas the other methods generates artifacts like patterns. Quantitatively, for 4× sub-sampled in vivo test dataset, the Deep RF interpolation [27] achieves CNR, GCNR, PSNR, and SSIM values of 1.31, 0.63 units, 22.15 dB and 0.82 units, which are 0.07, 0.02 units, 1.4 dB and 0.05 units inferior to the proposed method respectively. Here we would like to point out that, in [27], deep learning approach was designed for interpolating missing RF data, which are later used as input for standard beamformer.…”

Section: Discussionmentioning

confidence: 89%

“…The results clearly show that the proposed method with end-to-end learning to generate IQ data with the combination of training with multiple subsampling rates and multiple depths, provided the best quantitative values. We also compared our method with Deep RF interpolation method [27]. Again, the proposed method also outperform the Deep RF interpolation method [27].…”

Section: Discussionmentioning

confidence: 90%

“…We also compared our method with Deep RF interpolation method [27]. Again, the proposed method also outperform the Deep RF interpolation method [27]. Fig 10 shows reconstruction results of various methods at 4× subsampling rate, which is compared with the full data reconstruction.…”

Section: Discussionmentioning

confidence: 97%

“…Reconstruction results of standard DAS beam-former, Deep RF Interpolation[27] and the proposed DeepBF for 4× sub-sampled in vivo data. The window levels are same for all images (0 ∼ −60dB).…”

mentioning

confidence: 99%

See 3 more Smart Citations

Adaptive and Compressive Beamforming Using Deep Learning for Medical Ultrasound

Khan

Huh

2020

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

Self Cite

View full text Add to dashboard Cite

In ultrasound (US) imaging, various types of adaptive beamforming techniques have been investigated to improve the resolution and contrast to noise ratio of the delay and sum (DAS) beamformers. Unfortunately, the performance of these adaptive beamforming approaches degrade when the underlying model is not sufficiently accurate and the number of channels decreases. To address this problem, here we propose a deep learning-based end-to-end beamformer to generate significantly improved images over widely varying measurement conditions and channel subsampling patterns. In particular, our deep neural network is designed to directly process full or sub-sampled radio-frequency (RF) data acquired at various subsampling rates and detector configurations so that it can generate high quality ultrasound images using a single beamformer. The origin of such adaptivity is also theoretically analyzed. Experimental results using B-mode focused ultrasound confirm the efficacy of the proposed methods.

show abstract

Section: Discussionmentioning

confidence: 89%

Section: Discussionmentioning

confidence: 90%

Section: Discussionmentioning

confidence: 97%

mentioning

confidence: 99%

See 2 more Smart Citations

Adaptive and Compressive Beamforming Using Deep Learning for Medical Ultrasound

Khan

Huh

2020

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

Self Cite

View full text Add to dashboard Cite

show abstract

“…They offer solution to several practical problems that occur in different areas ranging from medical sciences [1], [2], [3] to control of complicated industrial processes [4]. With the advent of high power computing systems and deep network architectures enormous success has been achieved in diverse applications [3], [5]. However, deep learning typically demands very large amount of data to extract the useful information from training samples.…”

Section: Introductionmentioning

confidence: 99%

Chaotic Time Series Prediction using Spatio-Temporal RBF Neural Networks

Sadiq

Ibrahim

Usman

et al. 2018

2018 3rd International Conference on Emerging Trends in Engineering, Sciences and Technology (ICEEST)

Self Cite

View full text Add to dashboard Cite

Due to the dynamic nature, chaotic time series are difficult predict. In conventional signal processing approaches signals are treated either in time or in space domain only. Spatio-temporal analysis of signal provides more advantages over conventional uni-dimensional approaches by harnessing the information from both the temporal and spatial domains. Herein, we propose an spatio-temporal extension of RBF neural networks for the prediction of chaotic time series. The proposed algorithm utilizes the concept of time-space orthogonality and separately deals with the temporal dynamics and spatial nonlinearity(complexity) of the chaotic series. The proposed RBF architecture is explored for the prediction of Mackey-Glass time series and results are compared with the standard RBF. The spatio-temporal RBF is shown to out perform the standard RBFNN by achieving significantly reduced estimation error.

show abstract

Self‐supervised learning for accelerated 3D high‐resolution ultrasound imaging

et al. 2021

View full text Add to dashboard Cite

Purpose Ultrasound (US) imaging has been widely used in diagnosis, image‐guided intervention, and therapy, where high‐quality three‐dimensional (3D) images are highly desired from sparsely acquired two‐dimensional (2D) images. This study aims to develop a deep learning‐based algorithm to reconstruct high‐resolution (HR) 3D US images only reliant on the acquired sparsely distributed 2D images. Methods We propose a self‐supervised learning framework using cycle‐consistent generative adversarial network (cycleGAN), where two independent cycleGAN models are trained with paired original US images and two sets of low‐resolution (LR) US images, respectively. The two sets of LR US images are obtained through down‐sampling the original US images along the two axes, respectively. In US imaging, in‐plane spatial resolution is generally much higher than through‐plane resolution. By learning the mapping from down‐sampled in‐plane LR images to original HR US images, cycleGAN can generate through‐plane HR images from original sparely distributed 2D images. Finally, HR 3D US images are reconstructed by combining the generated 2D images from the two cycleGAN models. Results The proposed method was assessed on two different datasets. One is automatic breast ultrasound (ABUS) images from 70 breast cancer patients, the other is collected from 45 prostate cancer patients. By applying a spatial resolution enhancement factor of 3 to the breast cases, our proposed method achieved the mean absolute error (MAE) value of 0.90 ± 0.15, the peak signal‐to‐noise ratio (PSNR) value of 37.88 ± 0.88 dB, and the visual information fidelity (VIF) value of 0.69 ± 0.01, which significantly outperforms bicubic interpolation. Similar performances have been achieved using the enhancement factor of 5 in these breast cases and using the enhancement factors of 5 and 10 in the prostate cases. Conclusions We have proposed and investigated a new deep learning‐based algorithm for reconstructing HR 3D US images from sparely acquired 2D images. Significant improvement on through‐plane resolution has been achieved by only using the acquired 2D images without any external atlas images. Its self‐supervision capability could accelerate HR US imaging.

show abstract

Efficient B-Mode Ultrasound Image Reconstruction From Sub-Sampled RF Data Using Deep Learning

Cited by 116 publications

References 54 publications

Adaptive and Compressive Beamforming Using Deep Learning for Medical Ultrasound

Adaptive and Compressive Beamforming Using Deep Learning for Medical Ultrasound

Chaotic Time Series Prediction using Spatio-Temporal RBF Neural Networks

Self‐supervised learning for accelerated 3D high‐resolution ultrasound imaging

Contact Info

Product

Resources

About