云南大学信息学院电子工程系,云南昆明 650091
[ "崔旺 男,1999年7月出生于陕西省渭南市.现为云南大学信息学院硕士研究生.主要研究方向为超快超声彩色血流测速及成像. E-mail: c_1679464553@163.com" ]
[ "何冰冰 女,1993年3月出生于内蒙古乌兰浩特市.2021年毕业于云南大学信息与通信工程专业.现为云南大学信息学院副教授.主要研究方向为医学超声信号处理、医学超声成像. E-mail: hebingbing@ynu.edu.cn" ]
收稿:2024-12-20,
录用:2025-06-09,
纸质出版:2025-08-25
移动端阅览
崔旺, 何冰冰, 邹良辰, 等. 基于DCNN的超快超声彩色血流成像[J]. 电子学报, 2025, 53(08): 2843-2853.
CUI Wang, HE Bing-bing, ZOU Liang-chen, et al. Ultrafast Ultrasound Color Blood Flow Imaging Based on the DCNN[J]. Acta Electronica Sinica, 2025, 53(08): 2843-2853.
崔旺, 何冰冰, 邹良辰, 等. 基于DCNN的超快超声彩色血流成像[J]. 电子学报, 2025, 53(08): 2843-2853. DOI:10.12263/DZXB.20241148
CUI Wang, HE Bing-bing, ZOU Liang-chen, et al. Ultrafast Ultrasound Color Blood Flow Imaging Based on the DCNN[J]. Acta Electronica Sinica, 2025, 53(08): 2843-2853. DOI:10.12263/DZXB.20241148
多角度平面波相干复合(Multi-angle Plane Wave Coherent Compounding,MPWCC)实现了高帧率超声扫描,有助于彩色血流成像技术提供更准确的血流信息和组织图像.然而,MPWCC的低通效应会导致血流速度估计值偏低,且无法通过计算的方式确定杂波抑制滤波器的最佳阈值.对此,本文提出一种基于深度卷积神经网络(Deep Convolutional Neural Network,DCNN)的超快超声彩色血流成像方法.基于Field II平台搭建颈动脉仿真模型,以获得不同速度的血流超声多普勒信号,该信号经过奇异值分解(Singular Value Decomposition,SVD)、归一化等处理转换为训练数据.DCNN模型通过对训练数据进行有监督学习实现对不同速度多普勒信号的特征学习和杂波抑制,随后将特征信息转化为速度信息用于彩色成像.与高通滤波(High Pass Filtering,HPF)或SVD相结合的自相关测速法相比,本文方法在仿真、人体颈动脉的测试数据上均表现出了更好的性能:在估计正反向的仿真血流速度剖面时,该方法的归一化均方根误差(Normalized Root Mean Square Error,NRMSE)比HPF和SVD平均降低了45.65%和41.95%;在仿真及人体数据的彩色成像结果中,该方法呈现出最好的杂波抑制效果和血管完整度.综上,该方法能够实现超快超声彩色血流成像,在血流流态可视化方面具有应用价值.
Multi-angle plane wave coherent compounding (MPWCC) can achieve high frame rate ultrasound scanning
which aids color flow imaging technology in providing more accurate blood flow information and tissue images. However
the low-pass effect of the MPWCC results in underestimated blood flow velocities and the optimal threshold for clutter suppression filters cannot be determined computationally. To address this
this paper proposes an ultra fast ultrasound color blood flow imaging based on deep convolutional neural networks (DCNN). Based on the Field II ultrasound simulator
the carotid artery model is built to acquire ultrasound doppler signals with different blood flow velocities. These signals are processed with the singular value decomposition (SVD) and then normalized to generate training dataset. The DCNN model learns the characteristics of Doppler signals with different velocities through supervised learning
enabling clutter suppression and conversion of feature information into velocity information for color flow imaging. Compared to the autocorrelation velocimetry by combining high pass filtering (HPF) or SVD
the superior performance of the proposed method has been demonstrated in both simulation and human carotid artery test dataset. When blood flow velocity profiles in both forward and reverse directions are estimated
the normalized root mean square error (NRMSE) of the proposed method is reduced by an average of 45.65% and 41.95% than these of the HPF and SVD
respectively. In the results of color flow imaging in simulation and human data
the proposed method shows the best clutter suppression effect and vessel integrity. In summary
this method achieves ultrafast ultrasound color blood flow imaging and is applicable for visualizing blood flow dynamics.
王中群 , 袁伟 , 杨永宗 , 等 . 动脉粥样硬化病变位点特异性研究新进展 [J ] . 中华老年心脑血管病杂志 , 2013 , 15 ( 4 ): 436 - 437 .
WANG Z Q , YUAN W , YANG Y Z , et al . New progress in site specificity of atherosclerotic lesions [J ] . Chinese Journal of Geriatric Heart Brain and Vessel Diseases , 2013 , 15 ( 4 ): 436 - 437 . (in Chinese)
沈瑾 , 李明辉 . 颈动脉超声对短暂性脑缺血发作与颈动脉粥样硬化间关系评定的临床价值分析 [J ] . 临床和实验医学杂志 , 2019 , 18 ( 5 ): 545 - 548 .
SHEN J , LI M H . Clinical significance of carotid ultrasound in evaluating the relationship between transient ischemic attack and carotid atherosclerosis [J ] . Journal of Clinical and Experimental Medicine , 2019 , 18 ( 5 ): 545 - 548 . (in Chinese)
BENTZON J F , OTSUKA F , VIRMANI R , et al . Mechanisms of plaque formation and rupture [J ] . Circulation Research , 2014 , 114 ( 12 ): 1852 - 1866 .
龙盛蓉 , 陈尧 , 孔庆茹 , 等 . 基于符号相干因子加权的双层介质频域相干复合平面波成像 [J ] . 仪器仪表学报 , 2022 , 43 ( 3 ): 32 - 39 .
LONG S R , CHEN Y , KONG Q R , et al . Fourier-domain coherent plane wave compounding imaging for two-layered medium based on sign coherence factor [J ] . Chinese Journal of Scientific Instrument , 2022 , 43 ( 3 ): 32 - 39 . (in Chinese)
BERCOFF J , MONTALDO G , LOUPAS T , et al . Ultrafast compound Doppler imaging: Providing full blood flow characterization [J ] . IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control , 2011 , 58 ( 1 ): 134 - 147 .
BERCOFF J , CHAFFAI S , TANTER M , et al . In vivo breast tumor detection using transient elastography [J ] . Ultrasound in Medicine & Biology , 2003 , 29 ( 10 ): 1387 - 1396 .
赵金鑫 , 汪源源 , 郭威 , 等 . 基于广义相干系数的超声平面波复合成像 [J ] . 仪器仪表学报 , 2014 , 35 ( S2 ): 186 - 190 .
ZHAO J X , WANG Y Y , GUO W , et al . Ultrasound plane-wave compounding based on the generalized coherence factor [J ] . Chinese Journal of Scientific Instrument , 2014 , 35 ( S2 ): 186 - 190 . (in Chinese)
MONTALDO G , TANTER M , BERCOFF J , et al . Coherent plane-wave compounding for very high frame rate ultrasonography and transient elastography [J ] . IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control , 2009 , 56 ( 3 ): 489 - 506 .
郑驰超 , 彭虎 , 赵巍 . 符号相干系数加权的超声平面波复合成像算法 [J ] . 电子学报 , 2018 , 46 ( 1 ): 31 - 38 .
ZHENG C C , PENG H , ZHAO W . Ultrasound imaging based on coherent plane wave compounding weighted by sign coherence factor [J ] . Acta Electronica Sinica , 2018 , 46 ( 1 ): 31 - 38 . (in Chinese)
DEMENÉ C , DEFFIEUX T , PERNOT M , et al . Spatiotemporal clutter filtering of ultrafast ultrasound data highly increases doppler and ultrasound sensitivity [J ] . IEEE Transactions on Medical Imaging , 2015 , 34 ( 11 ): 2271 - 2285 .
LEONOV D V , KULBERG N S , FIN V A , et al . Clutter filtering for diagnostic ultrasound color flow imaging [J ] . Biomedical Engineering , 2019 , 53 ( 3 ): 217 - 221 .
EKROLL I K , SWILLENS A , SEGERS P , et al . Simultaneous quantification of flow and tissue velocities based on multi-angle plane wave imaging [J ] . IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control , 2013 , 60 ( 4 ): 727 - 738 .
何冰冰 , 张榆锋 , 李支尧 , 等 . 超声多角度平面波相干复合血流速度检测的参数研究 [J ] . 电子学报 , 2022 , 50 ( 10 ): 2478 - 2488 .
HE B B , ZHANG Y F , LI Z Y , et al . Study on the parameter configuration of the multi-angle ultrasound plane wave compounding for the blood flow velocity measurement [J ] . Acta Electronica Sinica , 2022 , 50 ( 10 ): 2478 - 2488 . (in Chinese)
AUSTENG A , NILSEN C C , JENSEN A C , et al . Coherent plane-wave compounding and minimum variance beamforming [C ] // 2011 IEEE International Ultrasonics Symposium . Piscataway : IEEE , 2012 : 2448 - 2451 .
COHEN R , ELDAR Y C . Sparse convolutional beamforming for ultrasound imaging [J ] . IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control , 2018 , 65 ( 12 ): 2390 - 2406 .
LIEBGOTT H , PROST R , FRIBOULET D . Pre-beamformed RF signal reconstruction in medical ultrasound using compressive sensing [J ] . Ultrasonics , 2013 , 53 ( 2 ): 525 - 533 .
WANG C Z , PENG X , LIANG D , et al . Plane-wave ultrasound imaging based on compressive sensing with low memory occupation [C ] // 2015 IEEE International Ultrasonics Symposium . Piscataway : IEEE , 2015 : 1 - 4 .
CHEN Y L , LOU Y , YEN J . Dynamic transmit-receive beamforming by spatial matched filtering for ultrasound imaging with plane wave transmission [J ] . Ultrasonic Imaging , 2017 , 39 ( 4 ): 207 - 223 .
CHEN Y , KONG Q R , XIONG Z H , et al . Improved coherent plane-wave compounding using sign coherence factor weighting for frequency-domain beamforming [J ] . Ultrasound in Medicine & Biology , 2023 , 49 ( 3 ): 802 - 819 .
PARIDAR R , ASL B M . Frame rate improvement in ultrafast coherent plane wave compounding [J ] . Ultrasonics , 2023 , 135 : 107136 .
CHEN Y , XIONG Z H , KONG Q R , et al . Circular statistics vector for improving coherent plane wave compounding image in Fourier domain [J ] . Ultrasonics , 2023 , 128 : 106856 .
WANG Y D , FENG S , PAN J W , et al . Random matrix theory-based Wiener postfilter combined with eigenspace and spatial coherence-based minimum variance beamformer for coherent plane-wave adaptive compounding [J ] . IEEE Transactions on Instrumentation and Measurement , 2024 , 73 : 4503317 .
郭凯红 , 崔明茜 , 刘婷婷 . 模糊知识测度下图像脉冲噪声去除方法 [J ] . 电子学报 , 2023 , 51 ( 11 ): 3248 - 3261 .
GUO K H , CUI M X , LIU T T . Removal of impulse noise in grayscale images under fuzzy knowledge measure [J ] . Acta Electronica Sinica , 2023 , 51 ( 11 ): 3248 - 3261 . (in Chinese)
EKROLL I K , VOORMOLEN M M , STANDAL O K V , et al . Coherent compounding in Doppler imaging [J ] . IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control , 2015 , 62 ( 9 ): 1634 - 1643 .
CHAN P , WOO P . Ultrasound speckle decorrelation-based blood flow measurements [J ] . Ultrasound in Medicine & Biology , 2023 , 49 ( 7 ): 1491 - 1498 .
SEUNG L , HONG P , JOON L . Artificial intelligence-based speckle featurization and localization for ultrasound speckle tracking velocimetry [J ] . Ultrasonics , 2024 , 138 : 107241 .
HE B B , LEI J , LANG X , et al . Ultra-fast ultrasound blood flow velocimetry for carotid artery with deep learning [J ] . Artificial Intelligence in Medicine , 2023 , 144 : 102664 .
HUNTINK L M . High-Speed Planar Ultrasound Blood Flow Velocimetry Using Deep Learning [D ] . Enschede : University of Twente , 2024 .
0
浏览量
5
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构
京公网安备11010802024621