The Journal of the Acoustical Society of Korea (한국음향학회지)

The Acoustical Society of Korea (한국음향학회)
권호 표지
DOI QR코드

DOI QR Code

Development of deep learning-based holographic ultrasound generation algorithm

딥러닝 기반 초음파 홀로그램 생성 알고리즘 개발

  • 이문환 (대구경북과학기술원 정보통신융합전공) ;
  • 황재윤 (대구경북과학기술원 정보통신융합전공)
  • Received : 2021.01.18
  • Accepted : 2021.02.27
  • Published : 2021.03.31
Download PDF
⟨ Previous Next ⟩

Abstract

Recently, an ultrasound hologram and its applications have gained attention in the ultrasound research field. However, the determination technique of transmit signal phases, which generate a hologram, has not been significantly advanced from the previous algorithms which are time-consuming iterative methods. Thus, we applied the deep learning technique, which has been previously adopted to generate an optical hologram, to generate an ultrasound hologram. We further examined the Deep learning-based Holographic Ultrasound Generation algorithm (Deep-HUG). We implement the U-Net-based algorithm and examine its generalizability by training on a dataset, which consists of randomly distributed disks, and testing on the alphabets (A-Z). Furthermore, we compare the Deep-HUG with the previous algorithm in terms of computation time, accuracy, and uniformity. It was found that the accuracy and uniformity of the Deep-HUG are somewhat lower than those of the previous algorithm whereas the computation time is 190 times faster than that of the previous algorithm, demonstrating that Deep-HUG has potential as a useful technique to rapidly generate an ultrasound hologram for various applications.

최근 입자 조작, 신경 자극 등을 위해 초음파 홀로그램과 그 응용에 대해 연구가 활발히 되고 있다. 하지만 홀로그램을 생성할 송신 신호 위상의 결정은 이전의 시간 소모적인 반복 최적화 방법에서 크게 벗어나지 않고 있다. 이에 본 연구에서는 광학 홀로그램 생성을 위해 활용된 바 있는 딥러닝 기법을 초음파 홀로그램 생성을 위해 적용하여 소개한다. U-Net을 기반으로 알고리즘을 구성하였으며 원 모양의 데이터셋에 대해 학습하고 영어 알파벳에 대해 평가함으로써 그 일반화 가능성을 검증하였다. 또한 시뮬레이션을 통해 기존 알고리즘과 계산속도, 정확도, 균일도 측면에서 비교하였다. 결과적으로 정확도와 균일도는 기존에 비해 다소 떨어지지만 계산속도가 약 190배 빨라졌다. 따라서, 이 결과를 통해 딥러닝 기반 초음파 홀로그램 생성 알고리즘은 기존 방법보다 초음파 홀로그램을 빠르게 형성할 수 있는 것을 확인할 수 있었다.

Keywords

References

  1. K. Melde, A. G. Mark, T. Qiu, and P. Ficher, "Holograms for acoustics," Nature, 537, 518-22 (2016). https://doi.org/10.1038/nature19755
  2. A. Franklina, A. Marzo, R. Malkin, and B. W. Drinkwater, "Three-dimensional ultrasonic trapping of micro-particles in water with a simple and compact two-element transducer," Appl. Phys. Lett. 111, 094101 (2017). https://doi.org/10.1063/1.4992092
  3. L. Cox, K. Melde, A. Croxford, P. Fischer, and B. W. Drinkwater, "Acoustic hologram enhanced phased arrays for ultrasonic particle manipulation," Phys. Rev. Applied, 12, 064055 (2019). https://doi.org/10.1103/PhysRevApplied.12.064055
  4. Z. Ma, A. W. Holle, K. Melde, T. Qiu, K. Poeppel, V. M. Kadiri, and P. Fischer, "Acoustic holographic cell patterning in a biocompatible hydrogel," Adv Mater. 32, e1904181 (2020).
  5. K. Melde and P. Fischer, "Particle assembly and object propulsion using acoustic holograms," J. Acoust. Soc. Am. 144, 1895-1895 (2018).
  6. Y. Hertzberg, O. Naor, A. Volovick, and S. Shoham, "Towards multifocal ultrasonic neural stimulation: pattern generation algorithms," J. Neural Eng. 7, 056002 (2010). https://doi.org/10.1088/1741-2560/7/5/056002
  7. Y. Hertzberg and G. Navon, "Bypassing absorbing objects in focused ultrasound using computer generated holographic technique," Med. Phys. 38, 6407-15 (2011). https://doi.org/10.1118/1.3651464
  8. S. Jimenez-Gambin, N. Jimenez, J. M. Benlloch, and F. Camarena, "Holograms to focus arbitrary ultrasonic fields through the skull," Phys. Rev. Applied, 12, 14016-14016 (2019). https://doi.org/10.1103/PhysRevApplied.12.014016
  9. J. Zhang, Y. Yang, B. Zhu, X. Li, J. Jin, Z. Chen, Y. Chen, and Q. Zhou, "Multifocal point beam forming by a single ultrasonic transducer with 3D printed holograms," Appl. Phys. Lett. 113, 243502-243502 (2018). https://doi.org/10.1063/1.5058079
  10. Y. Cai, S. Yan, Z. Wang, R. Li, Y. Liang, Y. Zhou, X. Li, X. Yu, M. Lei, and B. Yao, "Rapid tilted-plane Gerchberg-Saxton algorithm for holographic optical tweezers," Opt. Express, 28, 12729-12739 (2020). https://doi.org/10.1364/oe.389897
  11. G. Whyte and J. Courtial, "Experimental demonstration of holographic three-dimensional light shaping using a Gerchberg-Saxton algorithm," New J. Phys. 7, 117 (2005). https://doi.org/10.1088/1367-2630/7/1/117
  12. X. Tang, F.Nan, F. Han, and Z. Yan, "Simultaneously shaping the intensity and phase of light for optical nanomanipulation," arXiv: physics Optics. 1910.08244 (2019).
  13. R. W. Gerchberg and W. O. Saxton, "A practical algorithm for the determination of phase from image and diffraction plane pictures," Optik, 35, 237-246 (1972).
  14. G. Situ, J. Suo, and Q. Dai, "Generalized iterative phase retrieval algorithms and their applications," Proc. INDIN. 15505881 (2015).
  15. M. H. Eybposh, N. W. Caira, and M. Atisa, "Deep CGH: 3D computer-generated holography using deep learning," Opt. Express, 28, 26636-26650 (2020). https://doi.org/10.1364/OE.399624
  16. R. Horisaki, R. Takagi, and J. Tanida, "Deep-learning-generated holography," Applied Optics, 57, 3859-3863 (2018). https://doi.org/10.1364/ao.57.003859
  17. Y. Nishizaki, R. Horisaki, K. Kitaguchi, M. Saito, and J. Tanida, "Analysis of non-iterative phase retrieval based on machine learning," Optical Review, 27, 136-141 (2020). https://doi.org/10.1007/s10043-019-00574-8
  18. B. E. Treeby, J. Jaros, A. P. Rendell, and B. T. Cox, "Modeling nonlinear ultrasound propagation in heterogeneous media with power law absorption using a k-space pseudospectral method," J. Acoust. Soc. Am. 131, 4324-4336 (2012). https://doi.org/10.1121/1.4712021
  19. O. Ronneberger, P. Fischer, and T. Brox, "U-net: Convolutional networks for biomedical image segmentation," Proc. MICCAI. 234-241 (2015).
  20. W. Yao, Z. Zengb, C. Lian, and H. Tang, "Pixel-wise regression using U-Net and its application on pan-sharpening," Neurocomputing, 312, 364-371 (2018). https://doi.org/10.1016/j.neucom.2018.05.103
  21. Z. Zhou, M. M. R. Siddiquee, N. Tajbakhsh, and J. Liang, "Unet++: A nested u-net architecture for medical image segmentation," Proc. DLMIA. 3-11 (2018).
  22. L. Xiao, A. Kaplanyan, and A. Fix, "DeepFocus: learned image synthesis for computational displays," ACM Trans. Graph. 37, 200 (2018).
  23. X. Zeng and R. J. McGough, "Evaluation of the angular spectrum approach for simulations of near-field pressures," J. Acoust. Soc. Am. 123, 68-76 (2008). https://doi.org/10.1121/1.2812579