Journal of Shandong University (Health Sciences) ›› 2023, Vol. 61 ›› Issue (3): 57-62.doi: 10.6040/j.issn.1671-7554.0.2022.1299

• 基础医学 • Previous Articles    

Electrical impedance recognition of spine tissue in vitro based on support vector machine

CHEN Bingrong1, SHI Yongwang2, LI Jiahao1, ZHAI Jiliang1, LIU Liang3, LIU Wenyong4, HU Lei5, ZHAO Yu1   

  1. 1. Department of Orthopaedic Surgery, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing 100730, China;
    2. Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing 100730, China;
    3. China Astronaut Research and Training Center, Beijing 100094, China;
    4. Department of Biomedical Engineering, Beihang University, Beijing 100191, China;
    5. Department of Mechanical Engineering and Automation, Beihang University, Beijing 100191, China
  • Published:2023-03-24

PDF (PC)

59

Abstract: Objective To measure impedances of different spinal tissues, to develop a tissue classification algorithm based on the impedance data using support vector machine(SVM), in order to verify the accuracy of the algorithm and to search for thresholds for impedance classification of different tissues. Methods Isolated spinal tissue was collected, and the electrical impedances of cortical bone, cancellous bone, spinal cord, muscle, and nucleus pulposus were collected using an electrochemical analyzer in the frequency range of 10-100 kHz. The data sets of two pigs were used as training set and test set, respectively. Principal component analysis(PCA)was used to reduce the dimensionality to two-dimensional data, and SVM based classification algorithm was trained and validated. Ensemble learning method was used to calculate the electrical impedance threshold for different tissue classifications. Results The electrical impedances of the five tissues were significantly different(P<0.001)within the measurement frequency of 10-100 kHz. The accuracy of PCA dimensionality reduction based SVM classification algorithm was 100%. Ensemble learning based multi-classifiers were used to compute impedance classification thresholds for different tissues. Conclusion Accurate identification of the electrical impedance of tissues in spinal surgery can be achieved based on support vector machines, which are expected to help surgeons improve the accuracy of tissue identification.

Key words: Bioelectrical impedance, Tissue recognition, Support vector machine, Principal component analysis, Ensemble learning

CLC Number: 

  • R687.1
[1] Shlobin NA, Raz E, Shapiro M, et al. Spinal neurovascular complications with anterior thoracolumbar spine surgery: a systematic review and review of thoracolumbar vascular anatomy[J]. Neurosurg Focus, 2020, 49(3): E9.
[2] QU H, ZHAO Y. Advances in tissue state recognition in spinal surgery: a review[J]. Front Med, 2021, 15(4): 575-584.
[3] Heileman K, Daoud J, Tabrizian M. Dielectric spectroscopy as a viable biosensing tool for cell and tissue characterization and analysis[J]. Biosens Bioelectron, 2013, 49: 348-359. doi:10.1016/j.bios.2013.04.017.
[4] Park J, Choi WM, Kim K, et al. Biopsy needle integrated with electrical impedance sensing microelectrode array towards real-time needle guidance and tissue discrimination[J]. Sci Rep, 2018, 8(1): 264.
[5] Cervantes J, Garcia LF, Rodríguez ML, et al. A comprehensive survey on support vector machine classification: Applications, challenges and trends[J]. Neurocomputing, 2020, 408: 189-215. doi: 10.1016/j.neucom.2019.10.118
[6] Wang M, Chen H. Chaotic multi-swarm whale optimizer boosted support vector machine for medical diagnosis[J]. Applied Soft Computing, 2020, 88: 105946. doi: 10.1016/j.asoc.2019.105946.
[7] Liang X, Zhu L, Huang D. Multi-task ranking SVM for image cosegmentation[J]. Neurocomputing, 2017, 247: 126-136. doi: 10.1016/j.neucom.2017.03.060.
[8] Wu SX, Wai HT, LI L, et al. A review of distributed algorithms for principal component analysis[J]. Proceedings of the IEEE, 2018, 106(8): 1321-1340.
[9] Zhou J, Jiang Z, Chung F, et al. Formulating ensemble learning of SVMs into a single SVM formulation by negative agreement learning[J]. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 2021, 51(10): 6015-6028.
[10] Dong X, Yu Z, Cao W, et al. A survey on ensemble learning[J]. Front Comput Sci, 2020, 14(2): 241-258.
[11] Sidey-Gibbons JAM, Sidey-Gibbons CJ. Machine learning in medicine: a practical introduction[J]. BMC Med Res Methodol, 2019, 19(1): 64.
[12] Kalvøy H, Frich L, Grimnes S, et al. Impedance-based tissue discrimination for needle guidance[J]. Physiol Meas, 2009, 30(2): 129-140.
[13] Cheng Z, Carobbio ALC, Soggiu L, et al. SmartProbe: a bioimpedance sensing system for head and neck cancer tissue detection[J]. Physiol Meas, 2020, 41(5): 054003.
[14] CHENG Z, Davies BL, Caldwell DG, et al. A new venous entry detection method based on electrical bio-impedance sensing[J]. Ann Biomed Eng, 2018, 46(10): 1558-1567.
[15] Kent B, Rossa C. Electric impedance spectroscopy feature extraction for tissue classification with electrode embedded surgical needles through a modified forward stepwise method[J]. Comput Biol Med, 2021, 135: 104522. doi:10.1016/j.compbiomed.2021.
[16] Halonen S, Kari J, Ahonen P, et al. Real-time bioimpedance-based biopsy needle can identify tissue type with high spatial accuracy[J]. Ann Biomed Eng, 2019, 47(3): 836-851.
[17] Bolger C, Carozzo C, Roger T, et al. A preliminary study of reliability of impedance measurement to detect iatrogenic initial pedicle perforation(in the porcine model)[J]. Eur Spine J, 2006, 15(3): 316-320.
[18] 孟云, 米宽, 郑诚功, 等. AD5933生物阻抗实时监测的椎弓根内固定辅助系统[J]. 中国科技论文, 2015, 10(5): 580-583. MENG Yun, MI Kuan, ZHENG Chenggong, et al. Bioelectrical impedance aided surgery system for transpedicle screws fixation based on AD5933[J]. China Science Paper, 2015, 10(5): 580-583.
[19] 钟胜河, 朱浩, 郭劲松, 等. 基于生物电阻抗法的椎弓根螺钉植入导航系统[J]. 电子技术应用, 2013, 39(4): 112-114. ZHONG Shenghe, ZHU Hao, GUO Jinsong, et al. Study of pedicle screw implantation navigation system based on bioelectric-impedance method[J]. Application of Electronic Technique, 2013, 39(4): 112-114.
[20] 赵硕峰, 王智运, 邓亲恺, 等. 家猪骨与软组织电阻抗特性研究[J]. 中国医疗设备, 2011, 26(4): 17-21. ZHAO Shuofeng, WANG Zhiyun, DENG Qinkai, et al. Study on impedance characteristics of pigs bones[J]. China Medical Devices, 2011, 26(4): 17-21.
[21] Jensen B, Braun W, Both M, et al. Configuration of bioelectrical impedance measurements affects results for phase angle[J]. Med Eng Phys, 2020, 84: 10-15. doi:10.1016/j.medengphy.2020.07.021.
[22] Jaeho Park, Sanghyeok Kim, Inkyu Park. A multi-pair electrode based impedance sensing biopsy needle for tissue discrimination during biopsy process[J]. Annu Int Conf IEEE Eng Med Biol Soc, 2014, 2014: 1695-1698. doi:10.1109/embc.2014.6943933.
[23] Qu H, Geng B, Chen B, et al. Force perception and bone recognition of vertebral lamina milling by robot-assisted ultrasonic bone scalpel based on backpropagation neural network[J]. IEEE Access, 2021, 9:52101-52112. doi: 10.1109/ACCESS.2021.3069549.
[24] Jair C, Farid GL, Asdrúbal LC, et al. Data selection based on decision tree for SVM classification on large data sets[J]. APPL Soft Comput, 2015, 37: 797-798. doi: 10.1016/j.asoc.2015.08.048.
[25] Alam S, Moonsoo K, Jae YP, et al. Performance of classification based on PCA, linear SVM, and Multi-kernel SVM [C] // Eighth International Conference on Ubiquitous & Future Networks. IEEE, 2016: 987-989.
[26] Xu S, Wang P, Dong Y. Measuring electrolyte impedance and noise simultaneously by triangular waveform voltage and principal component analysis[J]. Sensors(Basel), 2016, 16(4): E576.
[27] Liu B. BioSeq-analysis: a platform for DNA, RNA and protein sequence analysis based on machine learning approaches[J]. Brief Bioinform, 2019, 20(4): 1280-1294.
[28] Liu Bin, Wang SY, Long R, et al. iRSpot-EL: identify recombination spots with an ensemble learning approach[J]. Bioinformatics, 2017, 33(1): 35-41.
[29] Liu B, Yang F, Chou K. 2L-piRNA: a two-layer ensemble classifier for identifying piwi-interacting RNAs and their function[J]. Mol Ther Nucleic Acids, 2017, 7: 267-277. doi:10.1016/j.omtn.2017.04.008.
[1] WANG Shao-Qing, LIU Yi-Hui, FU Ting-Ting, CHENG Jin-Yong, LIU Qiang. Classification of 31P MRS data for hepatocellular carcinoma [J]. JOURNAL OF SHANDONG UNIVERSITY (HEALTH SCIENCES), 2209, 47(6): 42-46.
[2] GONG Xiaoyun, SHEN Xiaotao, XU Jing, ZHANG Tao, ZHU Zhengjiang, XUE Fuzhong. Influence of normality of metabolomics data on the classification accuracy of diseases [J]. JOURNAL OF SHANDONG UNIVERSITY (HEALTH SCIENCES), 2016, 54(4): 89-93.
[3] ZHANG Xin-xin1， LI YU1， JI Yu-jia2， WANG Peng2， ZHANG Yong-qing2， XUE Fu-zhong1. Discrimination of properties of Chinese Traditional Medicine with
principal component analysis-linear discriminant analysis [J]. JOURNAL OF SHANDONG UNIVERSITY (HEALTH SCIENCES), 2012, 50(1): 143-146.
[4] YU Lian-long1, WANG Ju-sheng2, WANG Shu-e1, ZHANG Feng-feng3, ZHAO Chang-feng1. Principal components of 6 trace elements in the serum of middle-aged and elder people with dyslipidemias [J]. JOURNAL OF SHANDONG UNIVERSITY (HEALTH SCIENCES), 2012, 50(1): 140-142.
[5] GAO Qing-song, XUE Fu-zhong. Applications of the kernel principal component analysis-based logistic  regression model on nonlinear association study [J]. JOURNAL OF SHANDONG UNIVERSITY (HEALTH SCIENCES), 2011, 49(5): 140-.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
Copyright 2018 © Editorial office of Journal of Shandong University (Health Sciences)
Supported by Beijing Magtech Co.Ltd