|
|
Complex Frequency Features for TCD Signal Analysis |
LIU Wei-xiang1, WANG Tian-fu1, CHEN Si-ping1, LUO Laurence2, WANG Xiao-yi2 |
1.Guangdong Provincial Key Laboratory of Biomedical Information Detection and Ultrasound Imaging, Shenzhen 518052, China;
2. Shenzhen Delicate Electronics Co., Ltd., Shenzhen 518054, China |
|
|
Abstract In this paper, we report on using pattern recognition techniques for embolic signal (ES) detection based on transcranial doppler ultrasound (TCD) audio data collected via machine EMS-9 (from Shenzhen Delicate Electronics, Co. Ltd). Firstly, we adopted complex discrete fourier transform to get spectra of audio recordings; secondly, we used principal component analysis (PCA) for the visualization of selected signals, which makes it easy and intuitive to verify whether a signal contains an embolic component; finally we designed the classifier with support vector machines (SVM) for detection. With contrast to traditional methods of ES detection systems, the proposed approach considers two channel signals from the audio data collected by single transducer, and there is no predefined features for classification. The primary experimental results on real data are promising.
|
Received: 28 December 2016
|
|
Fund:SZU R/D Fund; grant number: 201054; Natural Science Foundation of Shenzhen; grant number: JC201005280685A; Key Program of National Natural Science Foundation of China; grant number: 61031003 |
Corresponding Authors:
LIU Wei-xiang. E-mail: wxliu@szu.edu.cn
|
|
|
|
[1] Markus H. Transcranial doppler detection of circulating cerebral emboli: A review[J]. Stroke,1993, 24:1246-1250.
[2] Droste DW, Ringelstein EB. Detection of high intensity transient signals (HITS): How and why[J]? European Journal of Ultrasound, 1998, 7:23-29.
[3] Del Sette M, Angeli S, Gandolfo C. Transcranial Doppler detection of microembolic signals: a review[J]. The Italian Journal of Neurological Sciences, 1999, 20:155-159.
[4] Evans DH. Doppler detection of cerebral emboli: the state-of-the-art[J]. Ultrasound in Medicine and Biology, 2003, 29:38.
[5] Vukovic V, Lovrencic-Huzjan A, Demarin V. Microembolus detection by transcranial doppler sonography[J]. Technical and Clinical Aspects Acta Clina Croat, 2005, 44:33-45.
[6] Chung EML. Transcranial doppler embolus detection: A primer[J]. Ultrasound, 2006, 14:202-210.
[7] Azarpazhooh MR, Chambers BR. Clinical application of transcranial doppler monitoring for embolic signals[J]. Journal of Clinical Neuroscience, 2006, 13:799-810.
[8] White H, Venkatesh B. Applications of transcranial doppler in the ICU: a review[J]. Intensive Care Medicine, 2006, 32:981-994.
[9] Karahoca A, Kucur T, Aydin N. Data mining usage in emboli detection in ECSIS symposium on bio-inspired[J]. Learning, and Intelligent Systems for Security, 2007:159-162.
[10] Tripp LD, Warm JS. Transcranial doppler sonography[M]. Neuroergonomics: The brain at work, 2007:82-94.
[11] Keunen RWM, Hoogenboezem R Wijnands R, et al. Introduction of an embolus detection system based on analysis of the transcranial doppler audio-signal[J]. Journal of Medical Engineering & Technology, 2008, 32:296-304.
[12] Statements A. Transcranial doppler useful in assessing stroke risk in HbSC sickle cell disease[J]. Archives of Disease in Childhood, 2008, 93:138-141.
[13] Azarpazhooh MR, Velayati A, Chambers BR, et al. Microembolic signals in subarachnoid hemorrhage[J]. Journal of Clinical Neuroscience, 2009, 16:390-393.
[14] Markus HS, Brown MM. Differentiation between different pathological cerebral embolic materials using transcranial doppler in an in vitro model[J]. Stroke, 1993, 24:1.
[15] Markus HS, Tegeler CH. Experimental aspects of high-intensity transient signals in the detection of emboli[J]. Journal of Clinical Ultrasound, 1995, 23:81-88.
[16] Aydin N, Markus HS. Optimization of processing parameters for the analysis and detection of embolic signals[J]. European Journal of Ultrasound, 2000, 12:69-80.
[17] Droste DW, Hagedorn G, Notzold A, et al. Bigated transcranial doppler for the detection of clinically silent circulating emboli in normal persons and patients with prosthetic cardiac valves[J]. Stroke, 1997, 28:588.
[18] Droste DW, Dittrich R, Hermes S, et al. Four-gated transcranial doppler ultrasound in the detection of circulating microemboli[J]. European Journal of Ultrasound, 1999, 9:117-125.
[19] Fan L, Boni E, Tortoli P, et al. Multigate transcranial doppler ultrasound system with real-time embolic signal identification and archival[J]. IEEE Transactions on Ultrasonics, Ferroelectrics and Frequency Control, 2006, 53:1853-1861.
[20] Moehring MA, Spencer MP. Power M-mode doppler (PMD) for observing cerebral blood flow and tracking emboli[J]. Ultrasound in Medicine & Biology, 2002, 28:49-57.
[21] Mess WH, Willigers JM, Ledoux LAF, et al. Microembolic signal description: A reappraisal based on a customized digital postprocessing system[J]. Ultrasound in Medicine & Biology, 2002, 28:1447-1455.
[22] Cowe J, Gittins J, Naylor AR, et al. RF signals provide additional information on embolic events recorded during TCD monitoring[J]. Ultrasound in Medicine & Biology, 2005, 31:613-623.
[23] Aydin N, Evans DH. Implementation of directional doppler techniques using a digital signal processor[J]. Medical and Biological Engineering and Computing, 1994, 32:157-164.
[24] Markus H, Loh A, Brown MM. Computerized detection of cerebral emboli and discrimination from artifact using doppler ultrasound[J]. Stroke, 1993, 24:1667.
[25] Fan L, Evans DH, Naylor AR. Automated embolus identification using a rule-based expert system[J]. Ultrasound in Medicine & Biology, 2001, 27:1065.
[26] Serhatlioglu S, Hardalag F, Guler I. Classification of transcranial doppler signals using artificial neural network[J]. Journal of Medical Systems, 2003, 27:205-214.
[27] Aydin N. DWT Based Adaptive Threshold Determination in Embolic Signal Detection[C]. Nasa/esa Conference on Adaptive Hardware & Systems, 2007: 214-219.
[28] Chen Y, Wang Y. Doppler embolic signal detection using the adaptive wavelet packet basis and neurofuzzy classification[J]. Pattern Recognition Letters, 2008.
[29] Smith SW. The scientist and engineers guide to digital signal processing[M]. California Technical Publishing, 2009.
[30] Chang Chih-Chung, Lin Chih-Jen. LIBSVM: A library for support vector machines[J]. ACM Transactions on Intelligent Systems and Technology, 2011, 2(27):1-27.
[31] Jolliffe IT. Principal component analysis[J]. Springer Series in Statistics Springer, NY2nd ed. 2002.
[32] Palanchon P, Bouakaz A, Klein J, et al. Emboli detection using a new transducer design[J]. Ultrasound in Medicine & Biology, 2004, 30:123-126.
[33] Qin Zhengdi, Chen Siping, Chen Xin. Coded transmission for ultrasound doppler detection using truncated long code[C]. The 3rd International Conference on Biomedical Engineering and Informatics, 2010: 159-161. |
|
|
|