Deep neural networks for ultrasound beamforming

Luchies, Adam; Byram, Brett

doi:10.1109/ultsym.2017.8092159

Cited by 40 publications

(52 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Several attempts to use machine learning and deep learning for US-based disease diagnosis and characterisation have been reported [8]. For instance, super-resolution in US localisation microscopy and beamforming uses deep learning techniques for the removal of artefacts in element-wise complex in-phase and quadrature data [9]. Computer-aided US diagnosis methods for breast cancer imaging have been researched, incorporating features relating to shape, margin, orientation, echo patterns and acoustic shadowing [10].…”

Section: Introductionmentioning

confidence: 99%

A Learning-Based Microultrasound System for the Detection of Inflammation of the Gastrointestinal Tract

Yang

Lemke

Cox

et al. 2021

IEEE Trans. Med. Imaging

View full text Add to dashboard Cite

Inflammation of the gastrointestinal (GI) tract accompanies several diseases, including Crohn's disease. Currently, video capsule endoscopy and deep bowel enteroscopy are the main means for direct visualisation of the bowel surface. However, the use of optical imaging limits visualisation to the luminal surface only, which makes early-stage diagnosis difficult. In this study, we propose a learning enabled microultrasound (µUS) system that aims to classify inflamed and non-inflamed bowel tissues. µUS images of the caecum, small bowel and colon were obtained from mice treated with agents to induce inflammation. Those images were then used to train three deep learning networks and to provide a ground truth of inflammation status. The classification accuracy was evaluated using 10-fold evaluation and additional B-scan images. Our deep learning approach allowed robust differentiation between healthy tissue and tissue with early signs of inflammation that is not detectable by current endoscopic methods or by human inspection of the µUS images. The methods may be a foundation for future early GI disease diagnosis and enhanced management with computer-aided imaging.

show abstract

Section: Introductionmentioning

confidence: 99%

A Learning-Based Microultrasound System for the Detection of Inflammation of the Gastrointestinal Tract

Yang

Lemke

Cox

et al. 2021

IEEE Trans. Med. Imaging

View full text Add to dashboard Cite

show abstract

“…Another class of ultrasound-based deep learning approaches produces high-quality images with reduced data sampling in order to increase frame rates [12]- [19]. Deep learning has also been used to replace portions of the beamforming process by learning the parameters of a model created during an intermediary beamforming step [20]- [24]. However, none of these methods provide an end-to-end transformation that learns information directly from raw channel data.…”

Section: Introductionmentioning

confidence: 99%

Deep Learning to Obtain Simultaneous Image and Segmentation Outputs From a Single Input of Raw Ultrasound Channel Data

Nair

Washington

Tran

et al. 2020

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

View full text Add to dashboard Cite

Single plane wave transmissions are promising for automated imaging tasks requiring high ultrasound frame rates over an extended field of view. However, a single plane wave insonification typically produces suboptimal image quality. To address this limitation, we are exploring the use of deep neural networks (DNNs) as an alternative to delay-and-sum beamforming. The objectives of this work are to obtain information directly from raw channel data and to simultaneously generate both a segmentation map for automated ultrasound tasks and a corresponding ultrasound B-mode image for interpretable supervision of the automation. We focus on visualizing and segmenting anechoic targets surrounded by tissue and ignoring or de-emphasizing less important surrounding structures. DNNs trained with Field II simulations were tested with simulated, experimental phantom, and in vivo datasets that were not included during training. With unfocused input channel data (i.e., prior to the application of receive time delays), simulated, experimental phantom, and in vivo test datasets achieved mean ± standard deviation Dice similarity coefficients of 0.92 ± 0.13, 0.92±0.03, and 0.77±0.07, respectively, and generalized contrastto-noise ratios (gCNR) of 0.95±0.08, 0.93±0.08, and 0.75±0.14, respectively. With subaperture beamformed channel data and a modification to the input layer of the DNN architecture to accept these data, the fidelity of image reconstruction increased (e.g., mean gCNR of multiple acquisitions of two in vivo breast cysts ranged 0.89-0.96), but DNN display frame rates were reduced from 395 Hz to 287 Hz. Overall, the DNNs successfully translated feature representations learned from simulated data to phantom and in vivo data, which is promising for this novel approach to simultaneous ultrasound image formation and segmentation.

show abstract

“…Meanwhile, deep neural networks (DNNs) have attracted a growing interest recently and shown promising results for many tasks including ultrasound image processing. Luchies et al [17] developed a feed-forward multi-layer fully connected network for suppressing off-axis scattering in ultrasound channel data. Hyun et al [18] introduced two modifications on the L1 norm, L2 norm, and MS-SSIM loss functions to make them more appropriate for ultrasound, and then employed a CNN for beamforming and speckle reduction.…”

Section: Introductionmentioning

confidence: 99%

Phase Aberration Correction: A Convolutional Neural Network Approach

2020

View full text Add to dashboard Cite

One of the main sources of image degradation in ultrasound imaging is the phase aberration effect, which imposes limitations to both data acquisition and reconstruction. Phase aberration is induced by spatial changes in sound velocity compared to the default values and degrades the quality of beam focusing. In addition, it prevents received channel signals to be summed coherently. In this paper, for the first time, we propose a method to estimate the aberrator profile from an ultrasound B-mode image using a deep convolutional neural network (CNN) in order to compensate for the phase aberration effect. In contrast to traditional methods, which mostly apply time-consuming processing techniques on channel RF signals and need several iterations for a reasonable accuracy, the proposed approach is computationally efficient, and utilizes only the B-mode image to estimate the aberrator profile in one shot with a high accuracy. We experimentally investigate main characteristics of the proposed approach and present a quantitative evaluation of the estimated aberrator profile. The proposed method is compared with the conventional delay-and-sum (DAS) method and a method based on nearest-neighbor cross-correlation (NNCC). Results demonstrate that the proposed CNN method substantially outperforms other methods. INDEX TERMS Convolutional neural networks, deep learning, phase aberration, ultrasound.

show abstract

Deep neural networks for ultrasound beamforming

Cited by 40 publications

References 4 publications

A Learning-Based Microultrasound System for the Detection of Inflammation of the Gastrointestinal Tract

A Learning-Based Microultrasound System for the Detection of Inflammation of the Gastrointestinal Tract

Deep Learning to Obtain Simultaneous Image and Segmentation Outputs From a Single Input of Raw Ultrasound Channel Data

Phase Aberration Correction: A Convolutional Neural Network Approach

Contact Info

Product

Resources

About