Spectroscopy and Spectral Analysis, Volume. 41, Issue 10, 3123(2021)

Spectral Discrimination of Rabbit Liver VX2 Tumor and Normal Tissue Based on Genetic Algorithm-Support Vector Machine

Chen-yang LIU1、*, Huang-rong XU2、2; 3;, Feng DUAN4、4;, Tai-sheng WANG1、1;, Zhen-wu LU1、1;, and Wei-xing YU3、3; *;
Author Affiliations
  • 11. State Key Laboratory of Applied Optics, Changchun Institute of Optics, Fine Mechanics & Physics, Chinese Academy of Sciences, Changchun 130033, China
  • 22. University of Chinese Academy of Sciences, Beijing 100049, China
  • 33. Key Laboratory of Spectral Imaging Technology, Xi’an Institute of Optics and Precision Mechanics, Chinese Academy of Science, Xi’an 710119, China
  • 44. Department of Interventional Radiology, the General Hospital of Chinese People’s Liberation Army, Beijing 100853, China
  • show less
    Figures & Tables(6)
    Experimental apparatus for measuring VX2 tumor tissue and normal tissue in rabbit liver
    Reflection of VX2 tumor tissue and normal tissue in rabbit liver (a) and spectral reflection of normal liver tissue in non-bleeding living body, VX2 tumor tissue in non-bleeding living body, normal liver tissue in bleeding isolated and VX2 tumor tissue in bleeding isolated (b)
    The predicted and true values of two categories (a) and four categories (b) of SVM parameters are optimized by using 5-K cross validation
    Fitness curves (a) and (b), classification results (c) and (d) of Two categories and Four categories optimized by genetic algorithm
    • Table 1. Compares the results of Two categories and Four categories of SVM parameters optimized by two methods

      View table
      View in Article

      Table 1. Compares the results of Two categories and Four categories of SVM parameters optimized by two methods

      Classification
      method
      Parameter optimization
      method
      Optimal values
      of c
      parameters
      Optimal values of
      kernel function
      parameter g
      The accuracy of
      the calibration
      set
      The accuracy
      of the prediction
      set
      Two categories5-fold cross validation40.125 0100%(130/130)100%(30/30)
      Genetic algorithm0.845 60.121 1100%(130/130)100%(30/30)
      Four categories5-fold cross validation80.062 599.242 4%(130/129)93.333%(30/27)
      Genetic algorithm5.530 70.068 599.242 4%(130/129)100%(30/30)
    • Table 2. The results of Two categories and Four categories under different number variables of SVM parameter optimized by Genetic algorithm

      View table
      View in Article

      Table 2. The results of Two categories and Four categories under different number variables of SVM parameter optimized by Genetic algorithm

      Classification
      method
      Optimal values
      of c
      parameters
      Optimal values
      of kernel function
      parameter g
      The number
      of variables
      Running time
      of algorithm
      /s
      The accuracy of
      the calibration
      set/%
      The accuracy of
      the prediction
      set/%
      Genetic
      algorithm-
      Two categories
      0.845 60.121 11 401340.26100100
      5.220 60.294 4902221.026100100
      1.213 21.463 428083.7410096.67
      2.604 11.539 814044.2810096.67
      5.600 71.857 59432.9010096.67
      5.532 12.919 47027.3610096.67
      3.341 61.686 35619.5110096.67
      7.952 82.465 04720.22100100
      8.252 61.590 53517.5499.2496.67
      9.911 71.363 31411.4199.2493.33
      Genetic
      algorithm-
      Four categories
      5.530 70.068 51 401490.9999.24100
      7.670 80.062 3902298.9799.2493.33
      7.177 70.292 628083.6410093.33
      3.604 40.957 114072.0599.2493.33
      5.538 00.813 59448.5999.2493.33
      6.360 32.011 97045.1710096.67
      9.107 51.019 65635.3799.2496.67
      3.909 32.436 14731.8498.4896.67
      7.675 21.633 23527.8798.4893.33
      5.741 34.335 51421.0299.2493.33
    Tools

    Get Citation

    Copy Citation Text

    Chen-yang LIU, Huang-rong XU, Feng DUAN, Tai-sheng WANG, Zhen-wu LU, Wei-xing YU. Spectral Discrimination of Rabbit Liver VX2 Tumor and Normal Tissue Based on Genetic Algorithm-Support Vector Machine[J]. Spectroscopy and Spectral Analysis, 2021, 41(10): 3123

    Download Citation

    EndNote(RIS)BibTexPlain Text
    Save article for my favorites
    Paper Information

    Category: Research Articles

    Received: Sep. 11, 2020

    Accepted: --

    Published Online: Oct. 29, 2021

    The Author Email: Chen-yang LIU (chenyang9015@163.com)

    DOI:10.3964/j.issn.1000-0593(2021)10-3123-06

    Topics