超音波影像重建中，與傳統成像相比平面波成像擁有極高的幀率，伴隨而來的是較差的影像品質，透過平面波復合的方法可以提升影像品質，這個方法需要以多角度的平面波數據合成，必須透過犧牲部份幀數換取影像品質此在平面波成像議題中一直存在著影像品質和幀率的權衡。本實驗的目的就是希望能以單角度的平面波射頻通道數據(radio frequency channel data)透過一個類神經網路的波束成型器重建出高品質的超音波影像。除此之外，在超音波領域中，目前除了影像診斷被廣泛應用在醫學上，也有許多研究致力於透過超音波計算血流、彈性等組織特性，計算這些組織特性所需的是擁有相位及振幅訊息的 IQ (In-phase and quadrature) 數據，因此本實驗設計架構是由單角度的平面波射頻通道數據(radio frequency channel data)生成 IQ 數據，希望未來可以將深度學習波數成型應用在更廣泛的領域而不局限於影像。
本實驗是以一個 Ecoder-Doder 的卷積神經網路 (CNN) 架構為基底，訓練資料為仿體 (phantom CIRS 040GSE) 及模擬資料，以人類頸動脈及開源資料庫 (PICMUS)為驗證結果，目的是為了使訓練資料及驗證資料之間結構不相關，確保神經網路不是以資料的結構學習而是學習如何實現波束成型。在實驗中訓練模型的確能把平面波射頻通道數據轉換為 IQ 數據並且得到比 Delay and Sum 更好的影像品質，也開闢了超音波波束成型另一個方向。

In the ultrasound image, plane wave imaging has ultra-fast frame rate compared with the conventional line-by-line imaging, but it accompanies by poor image quality. The image quality can be improved through the plane wave compounding method, multi-angle plane waves data synthesis is required. Therefore, there is always a trade-off between image quality and frame rate. The purpose of this experiment is using single angle plane wave radio frequency (RF) channel data to reconstruct high quality ultrasound images through a neural network. In addition to the widely used in medical imaging diagnosis, there are many studies devoted to the calculation of tissue characteristics such as blood flow and elasticity through ultrasound. The calculation of these tissue characteristics requires IQ (In-phase and quadrature) data with phase and amplitude information. The experimental design framework is to generate IQ data from single angle plane wave RF channel data. Hoping that deep learning beamformer can be applied to a wider range of fields, not only limited to images.The proposed method is based on an encoder and decoder convolutional neural network (CNN) architecture. the training data is simulated and phantom data. The evaluated results are based on the human carotid artery and the Plane-wave Imaging Challenge in Medical UltraSound (PICMUS) open source dataset. The purpose is to make the structure between training and testing are not related, to ensure the neural network does not learn from the structure of the data but learns how to beamforming. In our experiment, training a CNN can indeed convert single plane wave RF channel data into IQ data and get better image quality than Delay and Sum (DAS).

References
[1] M. Tanter and M. Fink, "Ultrafast imaging in biomedical ultrasound," IEEE
transactions on ultrasonics, ferroelectrics, and frequency control, vol. 61, no. 1, pp.
102-119, 2014.
[2] G. Wang, J. C. Ye, K. Mueller, and J. A. Fessler, "Image reconstruction is a new
frontier of machine learning," IEEE transactions on medical imaging, vol. 37, no. 6,
pp. 1289-1296, 2018.
[3] K. H. Jin, M. T. McCann, E. Froustey, and M. Unser, "Deep convolutional neural
network for inverse problems in imaging," IEEE Transactions on Image Processing,
vol. 26, no. 9, pp. 4509-4522, 2017.
[4] C. Bruneel, R. Torguet, K. Rouvaen, E. Bridoux, and B. Nongaillard, "Ultrafast
echotomographic system using optical processing of ultrasonic signals," Applied
Physics Letters, vol. 30, no. 8, pp. 371-373, 1977.
[5] B. Delannoy, R. Torguet, C. Bruneel, E. Bridoux, J. Rouvaen, and H. Lasota,
"Acoustical image reconstruction in parallel‐processing analog electronic systems,"
Journal of Applied Physics, vol. 50, no. 5, pp. 3153-3159, 1979.
[6] D. P. Shattuck, M. D. Weinshenker, S. W. Smith, and O. T. von Ramm, "Explososcan: A parallel processing technique for high speed ultrasound imaging with linear phased arrays," The Journal of the Acoustical Society of America, vol. 75, no. 4, pp. 1273-1282, 1984.
[7] M. Fink et al., "Time-reversed acoustics," Reports on progress in Physics, vol. 63,
no. 12, p. 1933, 2000.
[8] L. Sandrin, S. Catheline, M. Tanter, X. Hennequin, and M. Fink, "Time-resolved pulsed elastography with ultrafast ultrasonic imaging," Ultrasonic imaging, vol. 21,
no. 4, pp. 259-272, 1999.
[9] M. Tanter, J. Bercoff, L. Sandrin, and M. Fink, "Ultrafast compound imaging for 2-
D motion vector estimation: Application to transient elastography," IEEE
transactions on ultrasonics, ferroelectrics, and frequency control, vol. 49, no. 10, pp.
1363-1374, 2002.
[10] L. Sandrin, M. Tanter, S. Catheline, and M. Fink, "Shear modulus imaging with 2-D transient elastography," IEEE transactions on ultrasonics, ferroelectrics, and
frequency control, vol. 49, no. 4, pp. 426-435, 2002.
[11] J. Bercoff, M. Tanter, L. Sandrin, S. Catheline, and M. Fink, "Ultrafast compound
imaging for 2D displacement vector measurements: Application to transient
elastography and color flow mapping," in 2001 IEEE Ultrasonics Symposium.
Proceedings. An International Symposium (Cat. No. 01CH37263), 2001, vol. 2:
IEEE, pp. 1619-1622.
[12] J. Bercoff et al., "In vivo breast tumor detection using transient elastography,"
Ultrasound in medicine & biology, vol. 29, no. 10, pp. 1387-1396, 2003.
[13] J.-Y. Lu and J. Greenleaf, "Pulse-echo imaging using a nondiffracting beam
transducer," Ultrasound in medicine & biology, vol. 17, no. 3, pp. 265-281, 1991.
[14] J.-Y. Lu and J. F. Greenleaf, "Ultrasonic nondiffracting transducer for medical
imaging," IEEE transactions on ultrasonics, ferroelectrics, and frequency control,
vol. 37, no. 5, pp. 438-447, 1990.
[15] J.-Y. Lu and J. F. Greenleaf, "Experimental verification of nondiffracting X waves," IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control, vol. 39,
no. 3, pp. 441-446, 1992.
[16] J.-y. Lu, "2D and 3D high frame rate imaging with limited diffraction beams," IEEE transactions on ultrasonics, ferroelectrics, and frequency control, vol. 44, no. 4, pp. 839-856, 1997.
[17] J. Cheng and J.-y. Lu, "Extended high-frame rate imaging method with limiteddiffraction beams," IEEE transactions on ultrasonics, ferroelectrics, and frequency control, vol. 53, no. 5, pp. 880-899, 2006.
[18] G. Montaldo, M. Tanter, J. Bercoff, N. Benech, and M. Fink, "Coherent plane-wave compounding for very high frame rate ultrasonography and transient elastography," IEEE transactions on ultrasonics, ferroelectrics, and frequency control, vol. 56, no.
3, pp. 489-506, 2009.
[19] E. E. Konofagou, J. Luo, D. Saluja, D. O. Cervantes, J. Coromilas, and K. Fujikura,
"Noninvasive electromechanical wave imaging and conduction-relevant velocity
estimation in vivo," Ultrasonics, vol. 50, no. 2, pp. 208-215, 2010.
[20] P. Song, A. Manduca, J. D. Trzasko, and S. Chen, "Ultrasound small vessel imaging with block-wise adaptive local clutter filtering," IEEE transactions on medical
imaging, vol. 36, no. 1, pp. 251-262, 2016.
[21] X. P. Burgos-Artizzu et al., "Evaluation of deep convolutional neural networks for automatic classification of common maternal fetal ultrasound planes," Scientific
Reports, vol. 10, no. 1, pp. 1-12, 2020.
[22] B. Zeimarani, M. G. F. Costa, N. Z. Nurani, S. R. Bianco, W. C. D. A. Pereira, and
C. F. F. Costa Filho, "Breast lesion classification in ultrasound images using deep
convolutional neural network," IEEE Access, vol. 8, pp. 133349-133359, 2020.
[23] K. S. Sundar, K. T. Rajamani, and S. S. S. Sai, "Exploring image classification of
thyroid ultrasound images using deep learning," in International Conference on
ISMAC in Computational Vision and Bio-Engineering, 2018: Springer, pp. 1635-
1641.
[24] J. Ma, F. Wu, T. a. Jiang, J. Zhu, and D. Kong, "Cascade convolutional neural
networks for automatic detection of thyroid nodules in ultrasound images," Medical physics, vol. 44, no. 5, pp. 1678-1691, 2017.
[25] E. Smistad and L. Løvstakken, "Vessel detection in ultrasound images using deep convolutional neural networks," in Deep Learning and Data Labeling for Medical Applications: Springer, 2016, pp. 30-38.
[26] M. H. Yap et al., "Automated breast ultrasound lesions detection using convolutional neural networks," IEEE journal of biomedical and health informatics, vol. 22, no. 4, pp. 1218-1226, 2017.
[27] Y.-C. Li, T.-Y. Shen, C.-C. Chen, W.-T. Chang, P.-Y. Lee, and C.-C. J. Huang,
"Automatic detection of atherosclerotic plaque and calcification from intravascular
ultrasound images by using deep convolutional neural networks," IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control, vol. 68, no. 5, pp. 1762-1772, 2021.
[28] Z. Wang, "Deep learning in medical ultrasound image segmentation: A review," arXiv preprint arXiv:2002.07703, 2020.
[29] R. Zhou, A. Fenster, Y. Xia, J. D. Spence, and M. Ding, "Deep learning‐based carotid media‐adventitia and lumen‐intima boundary segmentation from three‐dimensional ultrasound images," Medical physics, vol. 46, no. 7, pp. 3180-3193, 2019.
[30] Z. Zhuang et al., "Nipple segmentation and localization using modified u-net on breast ultrasound images," Journal of Medical Imaging and Health Informatics, vol. 9, no. 9, pp. 1827-1837, 2019.
[31] Y. Lei et al., "Ultrasound prostate segmentation based on multidirectional deeply supervised V‐Net," Medical physics, vol. 46, no. 7, pp. 3194-3206, 2019.
[32] T. Zhou, J. Luo, and X. Liu, "Deep learning for super-resolution localization microscopy," in Optics in Health Care and Biomedical Optics VIII, 2018, vol. 10820:
International Society for Optics and Photonics, p. 1082023.
[33] M. Gasse, F. Millioz, E. Roux, D. Garcia, H. Liebgott, and D. Friboulet, "Highquality plane wave compounding using convolutional neural networks," IEEE transactions on ultrasonics, ferroelectrics, and frequency control, vol. 64, no. 10, pp. 1637-1639, 2017.
[34] D. Perdios, M. Vonlanthen, A. Besson, F. Martinez, M. Arditi, and J.-P. Thiran, "Deep convolutional neural network for ultrasound image enhancement," in 2018 IEEE International Ultrasonics Symposium (IUS), 2018: IEEE, pp. 1-4.
[35] D. Perdios, M. Vonlanthen, F. Martinez, M. Arditi, and J.-P. Thiran, "CNN-based
image reconstruction method for ultrafast ultrasound imaging," arXiv preprint
arXiv:2008.12750, 2020.[36] Z. Zhou, Y. Wang, J. Yu, Y. Guo, W. Guo, and Y. Qi, "High spatial–temporal
resolution reconstruction of plane-wave ultrasound images with a multichannel
multiscale convolutional neural network," IEEE transactions on ultrasonics,
ferroelectrics, and frequency control, vol. 65, no. 11, pp. 1983-1996, 2018.
[37] A. A. Nair, M. R. Gubbi, T. D. Tran, A. Reiter, and M. A. L. Bell, "A fully
convolutional neural network for beamforming ultrasound images," in 2018 IEEE
International Ultrasonics Symposium (IUS), 2018: IEEE, pp. 1-4.
[38] D. Hyun, L. L. Brickson, K. T. Looby, and J. J. Dahl, "Beamforming and speckle
reduction using neural networks," IEEE transactions on ultrasonics, ferroelectrics,
and frequency control, vol. 66, no. 5, pp. 898-910, 2019.
[39] S. Khan, J. Huh, and J. C. Ye, "Adaptive and compressive beamforming using deep
learning for medical ultrasound," IEEE transactions on ultrasonics, ferroelectrics,
and frequency control, vol. 67, no. 8, pp. 1558-1572, 2020.
[40] A. C. Luchies and B. C. Byram, "Deep neural networks for ultrasound
beamforming," IEEE transactions on medical imaging, vol. 37, no. 9, pp. 2010-2021,
2018.
[41] Y. H. Yoon, S. Khan, J. Huh, and J. C. Ye, "Efficient B-mode ultrasound image
reconstruction from sub-sampled RF data using deep learning," IEEE transactions
on medical imaging, vol. 38, no. 2, pp. 325-336, 2018.
[42] J. Zhang, Q. He, Y. Xiao, H. Zheng, C. Wang, and J. Luo, "Ultrasound image
reconstruction from plane wave radio-frequency data by self-supervised deep neural network," Medical Image Analysis, vol. 70, p. 102018, 2021.
[43] K. K. Shung, "Diagnostic ultrasound: Imaging and blood flow measurements.," CRC press, 2015.
[44] K. Kim, S. Park, J. Kim, S.-B. Park, and M. Bae, "A fast minimum variance
beamforming method using principal component analysis," IEEE transactions on
ultrasonics, ferroelectrics, and frequency control, vol. 61, no. 6, pp. 930-945, 2014.
[45] Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner, "Gradient-based learning applied to document recognition," Proceedings of the IEEE, vol. 86, no. 11, pp. 2278-2324, 1998.
[46] A. Krizhevsky, I. Sutskever, and G. E. Hinton, "Imagenet classification with deep
convolutional neural networks," Advances in neural information processing systems, vol. 25, pp. 1097-1105, 2012.
[47] C. Szegedy et al., "Going deeper with convolutions," in Proceedings of the IEEE
conference on computer vision and pattern recognition, 2015, pp. 1-9.
[48] C. Szegedy, S. Ioffe, V. Vanhoucke, and A. Alemi, "Inception-v4, inception-resnet and the impact of residual connections on learning (2016)," arXiv preprint
arXiv:1602.07261, 2016.
[49] K. He, X. Zhang, S. Ren, and J. Sun, "Deep residual learning for image recognition," in Proceedings of the IEEE conference on computer vision and pattern recognition, 2016, pp. 770-778.
[50] G. Huang, Z. Liu, L. Van Der Maaten, and K. Q. Weinberger, "Densely connected
convolutional networks," in Proceedings of the IEEE conference on computer vision
and pattern recognition, 2017, pp. 4700-4708.
[51] J. Long, E. Shelhamer, and T. Darrell, "Fully convolutional networks for semantic segmentation," in Proceedings of the IEEE conference on computer vision and pattern recognition, 2015, pp. 3431-3440.
[52] A. Creswell, T. White, V. Dumoulin, K. Arulkumaran, B. Sengupta, and A. A.
Bharath, "Generative adversarial networks: An overview," IEEE Signal Processing
Magazine, vol. 35, no. 1, pp. 53-65, 2018.
[53] J.-Y. Zhu, T. Park, P. Isola, and A. A. Efros, "Unpaired image-to-image translation using cycle-consistent adversarial networks," in Proceedings of the IEEE
international conference on computer vision, 2017, pp. 2223-2232.
[54] C. Ledig et al., "Photo-realistic single image super-resolution using a generative adversarial network. CoRR abs/1609.04802 (2016)," arXiv preprint
arXiv:1609.04802, 2016.
[55] H. Liebgott, A. Rodriguez-Molares, F. Cervenansky, J. A. Jensen, and O. Bernard,
"Plane-wave imaging challenge in medical ultrasound," in 2016 IEEE International
ultrasonics symposium (IUS), 2016: IEEE, pp. 1-4.
[56] D. P. Kingma and J. Ba, "Adam: A method for stochastic optimization," arXiv
preprint arXiv:1412.6980, 2014.
[57] L. Zhang, L. Zhang, X. Mou, and D. Zhang, "FSIM: A feature similarity index for
image quality assessment," IEEE transactions on Image Processing, vol. 20, no. 8,
pp. 2378-2386, 2011