深度学习在光声成像中的应用现状

doi:10.11896/JsJkx.190700046

摘要/Abstract

摘要： 光声成像(Photoacoustic Imaging,PAI)是一种多物理场耦合的无创生物医学功能成像技术,它将纯光学成像的高对比度与超声成像的高空间分辨率相结合,可同时获得生物组织的结构和功能成分信息。近年来,随着深度学习算法在医学图像处理中的广泛应用,基于深度学习的光声成像算法也成为该领域的研究热点。对深度学习在PAI图像重建中的应用现状进行综述,归纳和总结现有的算法,分析目前存在的问题,并展望未来可能的发展趋势。

关键词: 光声成像, 深度学习, 卷积神经网络, 图像重建, 有限角度扫描

Abstract: Photoacoustic imaging (PAI) is a multi-physics coupled non-invasive biomedical functional imaging technology.It combines the high contrast of pure optical imaging with the high spatial resolution of ultrasonic imaging,and can obtain the morpho-logy and functional components information of target tissues at the same time.In recent years,deep learning (DL) has been widely applied in medical image processing.The PAI imaging algorithms based on DL have attracted more and more attention of researchers.This paper reviewed the current application of DL in PAI image reconstruction,summarized the existing algorithms,analyzed their limits and forecasted the possible improvements in the future.

Key words: Photoacoustic imaging, Deep learning, Convolutional neural network, Image reconstruction, Limited-angle scanning

中图分类号:

TP391.4

孙正, 王新宇. 深度学习在光声成像中的应用现状[J]. 计算机科学, 2020, 47(6A): 148-152.

SUN Zheng and WANG Xin-yu. Application of Deep Learning in Photoacoustic Imaging[J]. Computer Science, 2020, 47(6A): 148-152.

参考文献

[1] YAO J,WANG LV.Recent progress in photoacoustic molecular imaging.Current Opinion in Chemical Biology,2018,45:104-112.
[2] POUDEL J,LOU Y,ANASTASIO M A.A survey of computational frameworks for solving the acoustic inverse problem in three-dimensional photoacoustic computed tomography.doi:10.1088/1361-6560/ab2017.
[3] BU S,YAMAKAWAY M,SHIINA T.Interpolation method for model-based 3-D planar photoacoustic tomography reconstruction//MBE,医用?生体工学研究会.2011:139-142.
[4] SYED TA,KRISHNAN VP,SIVASWAMY J.Numerical inversion of circular arc Radon transform.IEEE Transactions on Computational Imaging,2016,2(4):540-549.
[5] WANG J,WANG Y.An Efficient compensation method for limited-view photoacoustic imaging reconstruction based on Gerchberg-Papoulis extrapolation.Applied Sciences,2017,7(5):505.
[6] SUNNEGRDH J,DANIELSSON P E.Regularized iterative weighted filtered backproJection for helical cone-beam CT.Medical Physics,2008,35(9):4173-4185.
[7] ANTHOLZER S,SCHWAB J,BAUER-MARSCHALLINGER J,et al.NETT regularization for compressed sensing photoacoustic tomography//Proceedings of SPIE International Conference on Photons Plus Ultrasound:Imaging and Sensing 2019.2019:108783B.
[8] SYED T A,KRISHNAN V P,SIVASWAMY J.Numerical inversion of circular arc radon transform .IEEE Transactions on Computational Imaging,2017,2(4):540-549.
[9] GUO W.Research on Reconstruction Algorithms of CT with Incomplete ProJection Data .Changshun:Jilin University,2011.
[10] SU B L,ZHANG Y H,PENG L H,et al.Simultaneous iterative reconstruction technique for electrical capacitance tomography .Journal of Tsinghua University(Science and Technology),2000(9):90-92.
[11] CHEN X,HU H L,GAO X X,et al.Comparison of Algebraic Reconstruction Technique and Simultaneous Iterative Reconstruction Technique in Electrical Capacitance Tomography Image Reconstruction .Journal of Xi’an Jiaotong University,2011,45(4):25-29.
[12] YANG D W,XING D,ZHAO X,et al.A combined reconstruction algorithm for limited-view multi-element photoacoustic imaging .Chinese Physics Letters,2010,27(5):144-147.
[13] CHAUDHARY G,ROUMELIOTIS M,CARSON J J L,et al.Comparison of reconstruction algorithms for sparse-array detection photo-acoustic tomography //Proceedings of SPIE International Conference on Photons Plus Ultrasound:Imaging and Sensing.2010,7564:756434.
[14] WANG Q,WU Y N.New Analytical Solution to Extrapolation Problem for Band-Limited Signals .Journal of Electronics and Information Technology,1999,21(6):825-828.
[15] LIU X Y,PENG D,GUO W,et al.Compressed sensing photoacoustic imaging based on fast alternating direction algorithm .International Journal of Biomedical Imaging,2012,2012:206-214.
[16] VASWANI N,LU W.Modified-CS:modifying compressive sensing for problems with partially known support .IEEE Transactions on Signal Processing,2010,58(9):4595-4607.
[17] MENG J,WANG LV,YING L,et al.Compressed-sensing photoacoustic computed tomography in vivo with partially known support .Medical & Biological Imaging.2012,20(15):16510-16523.
[18] LIANG D,ZHANG H F,YING L.Compressed-sensing photoacoustic imaging based on random optical illumination .International Journal of Functional Informatics & Personalised Medicine,2009,2(4):394-406.
[19] ARRIDGE S,BEARD P,BETCKE M,et al.Accelerated high-resolution photoacoustic tomography via compressed sensing .Physics in Medicine & Biology,2016,61(24):8908.
[20] MENG J,JIANG Z,WANG LV,et al.High-speed,sparse-sampling three-dimensional photoacoustic computed tomography in vivo based on principal component analysis.Journal of Biomedical Lptics,2016,21(7):076007.
[21] LITJENS G,KOOI T,BEJNORDI B E,et al.A survey on deep learning in medical image analysis.Medical Image Analysis,2017,42(9):60-88.
[22] WANG G,YE J C,MUELLER K,et al.Image reconstruction is a new frontier of machine learning.IEEE Transactions on Medical Imaging,2018,37(6):1289-1296.
[23] LUCAS A,ILIADIS M,MOLINA R,et al.Using deep neural networks for inverse problems in imaging:beyond analytical methods.IEEE Signal Processing Magazine,2018,35(1):20-36.
[24] HALTMEIER M,ANTHOLZER S,SCHWAB J,et al.Photoacoustic image reconstruction via deep learning//Proceedings of SPIE International Conference on Photons Plus Ultrasound:Imaging and Sensing 2018.2018:104944U.
[25] KELLY B,MATTHEWS T P,ANASTASIO M A.Deep lear-ning-guided image reconstruction from incomplete data//Proceedings of 31st Annual Conference on Neural Information Processing Systems (NIPS 2017).Long Beach,CA,USA,2017.
[26] HAUPTMANN A,LUCKA F,BETCKE M,et al.Model based learning for accelerated,limited-view 3D photoacoustic tomography.IEEE Transactions on Medical Imaging,2018,37(6):1382-1393.
[27] HALTMEIER M,ANTHOLZER S,SCHWAB J,et al.Photoacoustic image reconstruction via deep learning//Proceedings of SPIE International Conference on Photons Plus Ultrasound:Imaging and Sensing 2018.2018:104944U.
[28] SCHWAB J,ANTHOLZER S,NUSTER R,et al.Real-time photoacoustic proJection imaging using deep learning.arXiv:1801.06693,2018.
[29] SCHWAB J,ANTHOLZER S,HALTMEIER M.Learned backproJection for sparse and limited view photoacoustic tomography//Proceedings of SPIE International Conference on Photons Plus Ultrasound:Imaging and Sensing 2019.2019:1087837
[30] SUN Z,HAN D,YUAN Y.2-D image reconstruction of photoacoustic endoscopic imaging based on time-reversal.Compu-ters in Biology and Medicine,2016,76:60-68.
[31] WAIBEL D J E.Photoacoustic image reconstruction to solve the acoustic inverse problem with deep learning.University of Heidelberg,2018.
[32] WAIBEL D,GRHL J,ISENSEE F,et al.Reconstruction of ini-tial pressure from limited view photoacoustic images using deep learning//Proceedings of SPIE International Conference on Photons Plus Ultrasound:Imaging and Sensing 2018.2018:104942S.
[33] SCHWAB J,ANTHOLZER S,NUSTER R,et al.DALnet: high-resolution photoacoustic proJection imaging using deep learning.arXiv:1801.06693,2018.
[34] ANTHOLZER S,HALTMEIER M,SCHWAB J.Deep learning for photoacoustic tomography from sparse data.Inverse Problems in Science and Engineering,2018,27(6):1-19.
[35] SCHWAB J,ANTHOLZER S,HALTMEIER M.Deep null space learning for inverse problems:Convergence analysis and rates.arXiv:1806.06137,2018.
[36] ANTHOLZER S,SCHWAB J,HALTMEIER M.Deep learning versus l₁-minimization for compressed sensing photoacoustic tomography.arXiv:1901.06510,2019.
[37] AWASTHI N,PRABHAKAR K R,KALVA S K,et al.PAFuse:deep supervised approach for the fusion of photoacoustic images with distinct reconstruction characteristics.Biomedi-cal Optics Express,2019,10(5):2227-2243.
[38] ADLER J,KTEM O.Solving ill-posed inverse problems using iterative deep neural networks.Inverse Problems,2017,33(12):124007.
[39] LI H,SCHWAB J,ANTHOLZER S,et al.NETT_solving inverse problems with deep neural networks.arXiv:1803.00092,2018.
[40] ARRIDGE S,BEARD P,BETCKE M,et al.Accelerated high-resolution photoacoustic tomography via compressed sensing.Physics in Medicine and Biology,2016,61(24):8908-8940.
[41] SCHWAB J,ANTHOLZER S,HALTMEIER M.Big in Japan:regularizing networks for solving inverse problems.arXiv:1812.00965,2018.
[42] ANTHOLZER S,SCHWAB J,MARSCHALLINGER J B,et al.NETT regularization for compressed sensing photoacoustic tomography.arXiv:1901.11158v1,2019.
[43] SCHWAB J,ANTHOLZER S,NUSTER R,et al.Deep learning of truncated singular values for limited view photoacoustic tomography//Proceedings of SPIE International Conference on Photons Plus Ultrasound:Imaging and Sensing 2019.2019:1087836.
[44] ANDRYCHOWICZ M,DENIL M,GOMEZ S,et al.Learning to learn by gradient descent by gradient descent//Proceedings of 30th Annual Conference on Neural Information Processing Systems 2016 (NIPS2016).Barcelona,Spain,2016:3981-3989.
[45] HAUPTMANN A,COX B,LUCKA F,et al.Approximate kspace models and deep learning for fast photoacoustic reconstruction//Machine Learning for Medical Image Reconstruction (MLMIR 2018).Lecture Notes in Computer Science.Cham:Springer,2018:103-111.
[46] SUN Z,ZHENG L.Progress in Quantitative photoacoustictomography.Chinese Journal of Luminescence,2017,38(9):1222-1232.
[47] JIN H,ZHANG R,LIU S,et al.A single sensor dual-modality photoacoustic fusion imaging for compensation of light fluence variation.IEEE Transactions on Biomedical Engineering,2019,66(6):1810-1813.
[48] CAI C,DENG K,MA C,et al.End-to-end deep neural network for optical inversion in quantitative photoacoustic imaging.Optics Letters,2018,43(12):2752-2755.
[49] KIRCHNER T,GRHL J,MAIER-HEIN L.Context encoding enables machine learning-based quantitative photoacoustics.Journal of Biomedical Optics,2018,23(5):056008.
[50] GRHL J,KIRCHNER T,ADLER T,et al.Confidence estimation for machine learning-based quantitative photoacoustics.Journal of Imaging,2018,4:147.
[51] TREEBY B E,COX B T.k-Wave:MATLAB toolbox for the simulation and reconstruction of photoacoustic wave fields.Journal of Biomedical Optics,2010,15(2):1-12.
[52] JACQUES S L.Coupling 3D Monte Carlo light transport in optically heterogeneous tissues to photoacoustic signal generation.Photoacoustics,2014,2(4):137-142.
[53] SUN Z,YUAN Y,HAN D.A computer-based simulator for intravascular photoacoustic images.Computers in biology and medicine,2017,81:176-187.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed