딥러닝 기반 초음파 홀로그램 생성 알고리즘 개발 = Development of deep learning-based holographic ultrasound generation algorithm

다국어 초록 (Multilingual 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.

참고문헌 (Reference)

1 Z. Zhou, "Unet++: A nested u-net architecture for medical image segmentation" 3-11, 2018

2 O. Ronneberger, "U-net: Convolutional networks for biomedical image segmentation" 234-241, 2015

3 Y. Hertzberg, "Towards multifocal ultrasonic neural stimulation:pattern generation algorithms" 7 : 056002-, 2010

4 A. Franklina, "Three-dimensional ultrasonic trapping of microparticles in water with a simple and compact twoelement transducer" 111 : 094101-, 2017

5 X. Tang, "Simultaneously shaping the intensity and phase of light for optical nanomanipulation"

6 Y. Cai, "Rapid tilted-plane Gerchberg-Saxton algorithm for holographic optical tweezers" 28 : 12729-12739, 2020

7 W. Yao, "Pixel-wise regression using U-Net and its application on pansharpening" 312 : 364-371, 2018

8 K. Melde, "Particle assembly and object propulsion using acoustic holograms" 144 : 1895-1895, 2018

9 J. Zhang, "Multifocal point beam forming by a single ultrasonic transducer with 3D printed holograms" 113 : 243502-243502, 2018

10 B. E. Treeby, "Modeling nonlinear ultrasound propagation in heterogeneous media with power law absorption using a k-space pseudospectral method" 131 : 4324-4336, 2012

11 S. Jiménez-Gambín, "Holograms to focus arbitrary ultrasonic fields through the skull" 12 : 14016-14016, 2019

12 K. Melde, "Holograms for acoustics" 537 : 518-522, 2016

13 G. Situ, "Generalized iterative phase retrieval algorithms and their applications" 15505881-, 2015

14 G. Whyte, "Experimental demonstration of holographic three-dimensional light shaping using a Gerchberg-Saxton algorithm" 7 : 117-, 2005

15 X. Zeng, "Evaluation of the angular spectrum approach for simulations of nearfield pressures" 123 : 68-76, 2008

16 L. Xiao, "DeepFocus: learned image synthesis for computational displays" 37 : 200-, 2018

17 R. Horisaki, "Deep-learninggenerated holography" 57 : 3859-3863, 2018

18 M. H. Eybposh, "Deep CGH: 3D computer-generated holography using deep learning" 28 : 26636-26650, 2020

19 Y. Hertzberg, "Bypassing absorbing objects in focused ultrasound using computer generated holographic technique" 38 : 6407-6415, 2011

20 Y. Nishizaki, "Analysis of non-iterative phase retrieval based on machine learning" 27 : 136-141, 2020

21 Z. Ma, "Acoustic holographic cell patterning in a biocompatible hydrogel" 32 : e1904181-, 2020

22 L. Cox, "Acoustic hologram enhanced phased arrays for ultrasonic particle manipulation" 12 : 064055-, 2019

23 R. W. Gerchberg, "A practical algorithm for the determination of phase from image and diffraction plane pictures" 35 : 237-246, 1972