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

In portable, 3-D, and ultra-fast ultrasound imaging systems, there is an increasing demand for the reconstruction of high-quality images from a limited number of radio-frequency (RF) measurements due to receiver (Rx) or transmit (Xmit) event sub-sampling. However, due to the presence of side lobe artifacts from RF sub-sampling, the standard beamformer often produces blurry images with less contrast, which are unsuitable for diagnostic purposes. Existing compressed sensing approaches often require either hardware changes or computationally expensive algorithms, but their quality improvements are limited. To address this problem, in this paper, we propose a novel deep learning approach that directly interpolates the missing RF data by utilizing redundancy in the Rx–Xmit plane. Our extensive experimental results using sub-sampled RF data from a multi-line acquisition B-mode system confirm that the proposed method can effectively reduce the data rate without sacrificing the image quality.

[1]  Thierry Blu,et al.  Sampling signals with finite rate of innovation , 2002, IEEE Trans. Signal Process..

[2]  Denis Friboulet,et al.  Compressed Sensing Reconstruction of 3D Ultrasound Data Using Dictionary Learning and Line-Wise Subsampling , 2015, IEEE Transactions on Medical Imaging.

[3]  Jong Chul Ye,et al.  Compressive dynamic aperture B-mode ultrasound imaging using annihilating filter-based low-rank interpolation , 2016, 2016 IEEE 13th International Symposium on Biomedical Imaging (ISBI).

[4]  Lei Zhang,et al.  Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising , 2016, IEEE Transactions on Image Processing.

[5]  Jong Chul Ye,et al.  Framing U-Net via Deep Convolutional Framelets: Application to Sparse-View CT , 2017, IEEE Transactions on Medical Imaging.

[6]  Michael Unser,et al.  Deep Convolutional Neural Network for Inverse Problems in Imaging , 2016, IEEE Transactions on Image Processing.

[7]  Jørgen Arendt Jensen,et al.  Ultrasound imaging using coded signals , 2001 .

[8]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[9]  Jonas Adler,et al.  Learned Primal-Dual Reconstruction , 2017, IEEE Transactions on Medical Imaging.

[10]  G.R. Lockwood,et al.  Real-time 3-D ultrasound imaging using sparse synthetic aperture beamforming , 1998, IEEE Transactions on Ultrasonics, Ferroelectrics and Frequency Control.

[11]  Thomas Pock,et al.  Learning a variational network for reconstruction of accelerated MRI data , 2017, Magnetic resonance in medicine.

[12]  Jong Chul Ye,et al.  A General Framework for Compressed Sensing and Parallel MRI Using Annihilating Filter Based Low-Rank Hankel Matrix , 2015, IEEE Transactions on Computational Imaging.

[13]  Jong Chul Ye,et al.  ${k}$ -Space Deep Learning for Accelerated MRI , 2020, IEEE Transactions on Medical Imaging.

[14]  Bruce R. Rosen,et al.  Image reconstruction by domain-transform manifold learning , 2017, Nature.

[15]  Jong Chul Ye,et al.  Annihilating Filter-Based Low-Rank Hankel Matrix Approach for Image Inpainting , 2015, IEEE Transactions on Image Processing.

[16]  B. Nelson,et al.  Use of ultrasound by emergency medical services: a review , 2008, International journal of emergency medicine.

[17]  H. Sebastian Seung,et al.  Learning the parts of objects by non-negative matrix factorization , 1999, Nature.

[18]  Muyinatu A. Lediju Bell,et al.  A machine learning method to identify and remove reflection artifacts in photoacoustic channel data , 2017, 2017 IEEE International Ultrasonics Symposium (IUS).

[19]  Mickael Tanter,et al.  Ultrafast imaging in biomedical ultrasound , 2014, IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control.

[20]  M. Fink,et al.  Functional ultrasound imaging of the brain , 2011, Nature Methods.

[21]  Jaejun Yoo,et al.  Deep Convolutional Framelet Denosing for Low-Dose CT via Wavelet Residual Network , 2018, IEEE Transactions on Medical Imaging.

[22]  Jong Chul Ye,et al.  MRI artifact correction using sparse + low‐rank decomposition of annihilating filter‐based hankel matrix , 2017, Magnetic resonance in medicine.

[23]  H. Sebastian Seung,et al.  Unsupervised Learning by Convex and Conic Coding , 1996, NIPS.

[24]  Brett Byram,et al.  Deep neural networks for ultrasound beamforming , 2017, 2017 IEEE International Ultrasonics Symposium (IUS).

[25]  Eero P. Simoncelli,et al.  Image quality assessment: from error visibility to structural similarity , 2004, IEEE Transactions on Image Processing.

[26]  J. C. Ye,et al.  Acceleration of MR parameter mapping using annihilating filter‐based low rank hankel matrix (ALOHA) , 2016, Magnetic resonance in medicine.

[27]  Jong Chul Ye,et al.  Deep Convolutional Framelets: A General Deep Learning Framework for Inverse Problems , 2017, SIAM J. Imaging Sci..

[28]  Yonina C. Eldar,et al.  Compressed Beamforming in Ultrasound Imaging , 2012, IEEE Transactions on Signal Processing.

[29]  O T von Ramm,et al.  Explososcan: A Parallel Processing Technique For High Speed Ultrasound Imaging With Linear Phased Arrays , 1985, Medical Imaging.

[30]  Yoshua Bengio,et al.  Understanding the difficulty of training deep feedforward neural networks , 2010, AISTATS.

[31]  Yuan Yu,et al.  TensorFlow: A system for large-scale machine learning , 2016, OSDI.

[32]  Daniel Rueckert,et al.  A Deep Cascade of Convolutional Neural Networks for Dynamic MR Image Reconstruction , 2017, IEEE Transactions on Medical Imaging.

[33]  Jong Chul Ye,et al.  A deep convolutional neural network using directional wavelets for low‐dose X‐ray CT reconstruction , 2016, Medical physics.

[34]  Jong Chul Ye,et al.  Compressive Sampling Using Annihilating Filter-Based Low-Rank Interpolation , 2015, IEEE Transactions on Information Theory.

[35]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[36]  Kyoung Mu Lee,et al.  Accurate Image Super-Resolution Using Very Deep Convolutional Networks , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[37]  H. Sebastian Seung,et al.  Algorithms for Non-negative Matrix Factorization , 2000, NIPS.

[38]  Max A. Viergever,et al.  Generative Adversarial Networks for Noise Reduction in Low-Dose CT , 2017, IEEE Transactions on Medical Imaging.

[39]  Justin P. Haldar,et al.  Low-Rank Modeling of Local $k$-Space Neighborhoods (LORAKS) for Constrained MRI , 2014, IEEE Transactions on Medical Imaging.

[40]  Jong Chul Ye,et al.  Reference‐free single‐pass EPI Nyquist ghost correction using annihilating filter‐based low rank Hankel matrix (ALOHA) , 2016, Magnetic resonance in medicine.

[41]  Jaejun Yoo,et al.  Deep Residual Learning for Accelerated MRI Using Magnitude and Phase Networks , 2018, IEEE Transactions on Biomedical Engineering.

[42]  Denis Friboulet,et al.  Pre-beamformed RF signal reconstruction in medical ultrasound using compressive sensing. , 2013, Ultrasonics.

[43]  Colas Schretter,et al.  Ultrasound Imaging From Sparse RF Samples Using System Point Spread Functions , 2018, IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control.

[44]  Hu Chen,et al.  Low-dose CT via convolutional neural network. , 2017, Biomedical optics express.

[45]  Adrian Basarab,et al.  3D Compressed sensing ultrasound imaging , 2010, 2010 IEEE International Ultrasonics Symposium.

[46]  Jong Chul Ye,et al.  Deep Learning for Accelerated Ultrasound Imaging , 2017, 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[47]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[48]  S.W. Smith,et al.  High-speed ultrasound volumetric imaging system. II. Parallel processing and image display , 1991, IEEE Transactions on Ultrasonics, Ferroelectrics and Frequency Control.

[49]  Andrea Vedaldi,et al.  MatConvNet: Convolutional Neural Networks for MATLAB , 2014, ACM Multimedia.

[50]  Leslie Ying,et al.  Accelerating magnetic resonance imaging via deep learning , 2016, 2016 IEEE 13th International Symposium on Biomedical Imaging (ISBI).

[51]  Feng Lin,et al.  Low-Dose CT With a Residual Encoder-Decoder Convolutional Neural Network , 2017, IEEE Transactions on Medical Imaging.

[52]  François Laviolette,et al.  Domain-Adversarial Training of Neural Networks , 2015, J. Mach. Learn. Res..

[53]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.