Signal Processing for Diffuse Correlation Spectroscopy with Support Vector Regression

被引:0
|
作者
Zhang, Peng [1 ]
Gui, Zhiguo [1 ]
Ling, Hao [1 ]
Liu, Jiaxin [1 ]
Zhang, Xiaojuan [1 ]
Liu, Yiming [1 ]
Li, Andi [1 ]
Shang, Yu [1 ]
机构
[1] North Univ China, Shanxi Prov Key Lab Biomed Imaging & Big Data, Taiyuan, Shanxi, Peoples R China
来源
PROCEEDINGS OF THE INTERNATIONAL CONFERENCE ON SENSING AND IMAGING, 2018 | 2019年 / 606卷
基金
中国国家自然科学基金;
关键词
Diffuse correlation spectroscopy; Blood flow index; NL algorithm; Linear regression; Denoising; Support vector regression; BLOOD-FLOW; HEMODYNAMICS; PARAMETERS; ABSORPTION;
D O I
10.1007/978-3-030-30825-4_15
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
Many diseases would lead to abnormal blood flow in biological tissues. In order to extract the blood flow index (BFI) in tissues with heterogeneity and irregular geometry, we previously proposed an innovative Nth linear algorithm (i.e., NL algorithm) for technology of diffuse correlation spectroscopy (DCS), in which the DCS signals are fully utilized through iterative linear regression. With this approach, the BFI calculation is remarkably affected by the performance of linear regression. In this study, we proposed to use the support vector regression (SVR) method to denoise the DCS data by implementing the iterative linear regression. In addition, two other approaches (least-squared regression, least-absolute regression) were compared for quantitative evaluation. The DCS data generated from computer simulations with varied tissue models (i.e., flat tissue, human head, human limb, and mouse head) and those collected from the phantom experiments were utilized to evaluate the three approaches. Both simulation and phantom experiment results show that the SVR method has the best performance among three methods in extracting the BFI values, regardless of the tissue geometry and size.
引用
收藏
页码:173 / 184
页数:12
相关论文
共 50 条
  • [1] Support vector method for function approximation, regression estimation, and signal processing
    Vapnik, V
    Golowich, SE
    Smola, A
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 9: PROCEEDINGS OF THE 1996 CONFERENCE, 1997, 9 : 281 - 287
  • [2] Advanced signal processing based on support vector regression for LIDAR applications
    Gelfusa, M.
    Murari, A.
    Malizia, A.
    Lungaroni, M.
    Peluso, E.
    Parracino, S.
    Talebzadeh, S.
    Vega, J.
    Gaudio, P.
    IMAGE AND SIGNAL PROCESSING FOR REMOTE SENSING XXI, 2015, 9643
  • [3] Signal Processing for Diffuse Correlation Spectroscopy with Recurrent Neural Network of Deep Learning
    Zhang, Peng
    Gui, Zhiguo
    Hao, Ling
    Zhang, Xiaojuan
    Liu, Caicai
    Shang, Yu
    2019 IEEE FIFTH INTERNATIONAL CONFERENCE ON BIG DATA COMPUTING SERVICE AND APPLICATIONS (IEEE BIGDATASERVICE 2019), 2019, : 328 - 332
  • [4] Particularities of scattering signal processing in correlation spectroscopy
    Andreev A.N.
    Lazarenko A.G.
    Andreeva O.N.
    Lazarenko, A.G. (lazarenko@kpi.kharkov.ua), 1600, Begell House Inc. (76): : 315 - 325
  • [5] Improved Direction-of-Arrival Estimation of an Acoustic Source Using Support Vector Regression and Signal Correlation
    Alam, Faisal
    Usman, Mohammed
    Alkhammash, Hend I.
    Wajid, Mohd
    SENSORS, 2021, 21 (08)
  • [6] Support vector machines framework for linear signal processing
    Rojo-Alvarez, JL
    Camps-Valls, G
    Martínez-Ramón, M
    Soria-Olivas, E
    Navia-Vázquez, A
    Figueiras-Vidal, AR
    SIGNAL PROCESSING, 2005, 85 (12) : 2316 - 2326
  • [7] Support vector regression as a signal discriminator in high energy physics
    Whiteson, DO
    Naumann, NA
    NEUROCOMPUTING, 2003, 55 (1-2) : 251 - 264
  • [8] An adaptive support vector regression filter: A signal detection application
    Rosipal, R
    Girolami, M
    NINTH INTERNATIONAL CONFERENCE ON ARTIFICIAL NEURAL NETWORKS (ICANN99), VOLS 1 AND 2, 1999, (470): : 603 - 607
  • [9] Establishing the diffuse correlation spectroscopy signal relationship with blood flow
    Boas, David A.
    Sakadzic, Sava
    Selb, Juliette
    Farzam, Parisa
    Franceschini, Maria Angela
    Carp, Stefan A.
    NEUROPHOTONICS, 2016, 3 (03)
  • [10] Boundary processing of HHT using support vector regression machines
    Wang, Wu
    Li, Xueyao
    Zhang, Rubo
    COMPUTATIONAL SCIENCE - ICCS 2007, PT 3, PROCEEDINGS, 2007, 4489 : 174 - +