Page 36 - 《应用声学》2021年第1期
P. 36

32                                                                                   2021 年 1 月


                 preprint: 1909.10342v1, Signal Processing, 2019.  sonics, Ferroelectrics, and Frequency Control, 2020.
             [42] Khan S, Huh J, Ye J C, et al. Adaptive and compres-  DOI: 10.1109/TUFFC.2020.2993779.
                 sive beamforming using deep learning for medical ultra-  [46] Hyun D, Brickson L L, Looby K T, et al.  Beam-
                 sound[J]. arXiv preprint: Image and Video Processing,  forming and speckle reduction using neural networks[J].
                 2019: 1–11.                                       IEEE Transactions on Ultrasonics, Ferroelectrics, and Fre-
             [43] Wiacek A, Gonzalez E, Bell M A L. CohereNet:     quency Control, IEEE, 2019, 66(5): 898–910.
                 a  deep  learning  architecture  for  ultrasound  spa-  [47] Brickson L L, Hyun D, Dahl J. Reverberation noise sup-
                 tial  correlation  estimation  and  coherence-based  pression in the aperture domain using 3D fully convolu-
                 beamforming[J].  IEEE  Transactions  on  Ultrason-  tional neural networks[C]. IEEE International Ultrasonics
                 ics,  Ferroelectrics,  and  Frequency  Control,  2020.  Symposium, IUS. 2018.
                 DOI: 10.1109/TUFFC.2020.2982848.               [48] Gasse M, Millioz F, Roux E, et al.  High-quality
             [44] Luchies A C, Byram B C. Deep neural networks for ul-  plane wave compounding using convolutional neural net-
                 trasound beamforming[J]. IEEE Transactions on Medical  works[J]. IEEE Transactions on Ultrasonics Ferroelectrics
                 Imaging, 2018, 37(9): 2010–2021.                  and Frequency Control, 2017, 64(10): 1637–1639.
             [45] Nair A A, Washington K N, Tran T D, et al.    [49] Zhang X, Liu J, He Q, et al. High quality reconstruc-
                 Deep learning to obtain simultaneous image and seg-  tion of plane-wave imaging using generative adversarial
                 mentation outputs from a single input of raw ultra-  network[C]. IEEE International Ultrasonics Symposium,
                 sound channel data[J]. IEEE Transactions on Ultra-  IUS. 2018.
   31   32   33   34   35   36   37   38   39   40   41