[1]SUN Meichen,SUN Zheng,HOU Yingsa.AAR-Net: a deep neural network for photoacoustic image reconstruction in heterogeneous acoustic media[J].CAAI Transactions on Intelligent Systems,2024,19(2):278-289.[doi:10.11992/tis.202212024]
Copy

AAR-Net: a deep neural network for photoacoustic image reconstruction in heterogeneous acoustic media

CAAI Transactions on Intelligent Systems[ISSN 1673-4785/CN 23-1538/TP] Volume: 19 Number of periods: 2024 2 Page number: 278-289 Column: 学术论文—机器学习 Public date: 2024-03-05
Title:
AAR-Net: a deep neural network for photoacoustic image reconstruction in heterogeneous acoustic media
Author(s):
SUN Meichen1;  SUN Zheng1; 2;  HOU Yingsa1
1. Department of Electronic and Communication Engineering, North China Electric Power University, Baoding 071003, China;
2. Hebei Key Laboratory of Power Internet of Things Technology, North China Electric Power University, Baoding 071003, China
Keywords:
image reconstruction; image enhancement; photoacoustic spectroscopy; acoustic properties; reflection; deep learning; deep neural networks; gradient methods
CLC:
TP391.41；R445
DOI:
10.11992/tis.202212024
Abstract:
Photoacoustic imaging suffers from degraded image quality owing to distorted and attenuated ultrasound waves propagating in an acoustic attenuating medium, phase deviation caused by changes in sound speed, and signal broadening related to acoustic attenuation. To address this issue, a deep learning method is proposed to reconstruct photoacoustic images of acoustically heterogeneous medium. A deep neural network is constructed, named acoustic artifacts removal network (AAR-Net) by combining deep gradient descent (DGD) network with U-Net. The DGD module aims to achieve the conversion from signal domain to image domain, which uses the gradient information to reduce the impact of heterogeneous acoustic properties on reconstructed image quality. U-Net module aims to optimize low-quality images output by the DGD module and realize the image-to-image conversion. The simulation, phantom and in vivo studies show that the proposed method outperforms traditional non-learning methods and the state-of-the-art post-processing based deep learning method. The image similarity and peak signal-to-noise ratio obtained by this method are improved by about 20% and 10%, respectively. AAR-Net enables reconstruction of high-quality images without any prior knowledge of acoustic properties of imaging objects.
References:
[1] 李娇, 李帅, 陈冀景, 等. 非接触光声成像研究进展及其在生物医学上的应用[J]. 中国激光, 2021, 48(19): 284–302
LI Jiao, LI Shuai, CHEN Jijing, et al. Progress and biomedical application of non-contact photoacoustic imaging[J]. Chinese journal of lasers, 2021, 48(19): 284–302
[2] 王雅慧, 王浩全, 任时磊. 滤波反投影算法在光声层析成像中的应用[J]. 国外电子测量技术, 2020, 39(5): 1–4
WANG Yahui, WANG Haoquan, REN Shilei. Application of filter back projection algorithm in photoacoustic tomography[J]. Foreign electronic measurement technology, 2020, 39(5): 1–4
[3] 韩朵朵, 孙正, 苑园. 血管内光声图像的时间反演重建方法[J]. 中国图象图形学报, 2016, 21(4): 442–450
HAN Duoduo, SUN Zheng, YUAN Yuan. Time-reversal based reconstruction of intravascular photoacoustic images[J]. Journal of image and graphics, 2016, 21(4): 442–450
[4] POUDEL J, LOU Yang, ANASTASIO M A. A survey of computational frameworks for solving the acoustic inverse problem in three-dimensional photoacoustic computed tomography[J]. Physics in medicine & biology, 2019, 64(14): 14TR01.
[5] 段爽, 孙正. 声学特性不均匀组织的光声层析图像重建研究进展[J]. 生物医学工程学杂志, 2019, 36(3): 486–492
DUAN Shuang, SUN Zheng. Review on photoacoustic tomographic image reconstruction for acoustically heterogeneous tissues[J]. Journal of biomedical engineering, 2019, 36(3): 486–492
[6] PETROSYAN T, THEODOROU M, BAMBER J, et al. Rapid scanning wide-field clutter elimination in epi-optoacoustic imaging using comb LOVIT[J]. Photoacoustics, 2018, 10: 20–30.
[7] LEDIJU B M A, KUO N, SONG D Y, et al. Short-lag spatial coherence beamforming of photoacoustic images for enhanced visualization of prostate brachytherapy seeds[J]. Biomedical optics express, 2013, 4(10): 1964–1977.
[8] NGUYEN H N Y, HUSSAIN A, STEENBERGEN W. Reflection artifact identification in photoacoustic imaging using multi-wavelength excitation[J]. Biomedical optics express, 2018, 9(10): 4613.
[9] KUNIYIL A S M, STEENBERGEN W. Photoacoustic-guided focused ultrasound (PAFUSion) for identifying reflection artifacts in photoacoustic imaging[J]. Photoacoustics, 2015, 3(4): 123–131.
[10] SCHWAB H M, BECKMANN M F, SCHMITZ G. Photoacoustic clutter reduction by inversion of a linear scatter model using plane wave ultrasound measurements[J]. Biomedical optics express, 2016, 7(4): 1468.
[11] HIRSCH L, GONZ?LEZ M G, REY V L. On the robustness of model-based algorithms for photoacoustic tomography: comparison between time and frequency domains[J]. Review of scientific instruments, 2021, 92(11): 114901.
[12] DE?N-BEN X L, ?ZBEK A, L?PEZ-SCHIER H, et al. Acoustic scattering mediated single detector optoacoustic tomography[J]. Physical review letters, 2019, 123(17): 174301.
[13] YIN Jie, TAO Chao, CAI Peng, et al. Photoacoustic tomography based on the Green’s function retrieval with ultrasound interferometry for sample partially behind an acoustically scattering layer[J]. Applied physics letters, 2015, 106(23): 234101.
[14] RUI Wei, TAO Chao, LIU Xiaojun. Photoacoustic imaging in scattering media by combining a correlation matrix filter with a time reversal operator[J]. Optics express, 2017, 25(19): 22840.
[15] RAJENDRAN P, SHARMA A, PRAMANIK M. Photoacoustic imaging aided with deep learning: a review[J]. Biomedical engineering letters, 2022, 12(2): 155–173.
[16] MANWAR R, ZAFAR M, XU Qiuyun. Signal and image processing in biomedical photoacoustic imaging: a review[J]. Optics, 2020, 2(1): 1–24.
[17] FARNIA P, MOHAMMADI M, NAJAFZADEH E, et al. High-quality photoacoustic image reconstruction based on deep convolutional neural network: towards intra-operative photoacoustic imaging[J]. Biomedical physics & engineering express, 2020, 6(4): 045019.
[18] SUN Zheng, WANG Xinyu, YAN Xiangyang. An iterative gradient convolutional neural network and its application in endoscopic photoacoustic image formation from incomplete acoustic measurement[J]. Neural computing and applications, 2021, 33(14): 8555–8574.
[19] JOSEPH F K, ARORA A, KANCHARLA P, et al. Generative adversarial network-based photoacoustic image reconstruction from bandlimited and limited-view data[C]//Proc SPIE 11642, Photons Plus Ultrasound: Imaging and Sensing. [S.l.: s.n.], 2021: 208-213.
[20] VU T, LI Mucong, HUMAYUN H, et al. A generative adversarial network for artifact removal in photoacoustic computed tomography with a linear-array transducer[J]. Experimental biology and medicine, 2020, 245(7): 597–605.
[21] SUN Zheng, YAN Xiangyang. A deep learning method for limited-view intravascular photoacoustic image reconstruction[J]. Journal of medical imaging and health informatics, 2020, 10(11): 2707–2713.
[22] GODEFROY G, ARNAL B, BOSSY E. Compensating for visibility artefacts in photoacoustic imaging with a deep learning approach providing prediction uncertainties[J]. Photoacoustics, 2021, 21: 100218.
[23] 宋宜昌, 邢达. 用蒙特卡罗方法模拟光在多层组织中的吸收特性[J]. 激光生物学报, 2002, 11(1): 10–14
[24] TREEBY B E, COX B T. Modeling power law absorption and dispersion for acoustic propagation using the fractional Laplacian[J]. The journal of the acoustical society of America, 2010, 127(5): 2741–2748.
[25] LA RIVI?RE P J, ZHANG Jin, ANASTASIO M A. Image reconstruction in optoacoustic tomography for dispersive acoustic media[J]. Optics letters, 2006, 31(6): 781.
[26] MOHAMMADI L, BEHNAM H, TAVAKKOLI J, et al. Skull’s photoacoustic attenuation and dispersion modeling with deterministic ray-tracing: towards real-time aberration correction[J]. Sensors, 2019, 19(2): 345.
[27] 齐梦雨, 严壮志, 赵丽丽. 基于有限元和k空间伪谱法的光声成像仿真平台[J]. 中国医疗器械杂志, 2018, 42(6): 413–416,427
QI Mengyu, YAN Zhuangzhi, ZHAO Lili. Simulation platform of photoacoustic imaging based on finite element and k-space pseudospectral method[J]. Chinese journal of medical instrumentation, 2018, 42(6): 413–416,427
[28] ADLER J, ?KTEM O. Solving ill-posed inverse problems using iterative deep neural networks[J]. Inverse problems, 2017, 33(12): 124007.
[29] KINGMA D P, BA J. Adam: a method for stochastic optimization[EB/OL]. (2014-12-22)[2022-01-01]. https://arxiv.org/abs/1412.6980.pdf.
[30] TREEBY B E, COX B T. K-Wave: MATLAB toolbox for the simulation and reconstruction of photoacoustic wave fields[J]. Journal of biomedical optics, 2010, 15(2): 021314.
Similar References:

Memo

-

Last Update: 1900-01-01

Copyright © CAAI Transactions on Intelligent Systems