access icon free Accumulated grey-level image representation for classification of lung cancer genetic mutations employing 2D principle component analysis

Lung cancer is an insidious disease, producing no symptoms until the disease spreads widely in the human body. Mutations of genes are the first alarm of such a disease in the human body. Therefore, classifying these mutations could provide guidance for the treatment decisions for lung cancer. In this Letter, a novel accumulated grey-level image (AGLI) method for gene representation is introduced, where each base in gene sequence is represented by accumulated number based on its order in gene sequence and then reflected into image domain. AGLI is incorporated with 2D principle component analysis to build accurate and low-dimensional algorithm for classifying the genetic mutations. Proposed algorithm was applied on the top 10 effective genes in lung cancer, where an accuracy of 99.27% was achieved. Experimental results show that the proposed algorithm enhanced the accuracy of classification and reduced the classification time for mutation in lung cancer relative to the existing methods.

Inspec keywords: lung; patient treatment; image representation; medical image processing; cancer; principal component analysis

Other keywords: treatment decisions; gene mutations; AGLI method; low-dimensional algorithm; 2D principle component analysis; insidious disease; gene sequence; gene representation; lung cancer genetic mutations; accumulated grey-level image method; accumulated grey-level image representation; image domain

Subjects: Optical, image and video signal processing; Other topics in statistics; Other topics in statistics; Patient diagnostic methods and instrumentation; Patient care and treatment; Computer vision and image processing techniques; Biology and medical computing; Patient care and treatment; Probability theory, stochastic processes, and statistics

References

    1. 1)
    2. 2)
    3. 3)
    4. 4)
    5. 5)
      • 3. Nguyen, T.T., Nguyen, L.M., Shimazu, A.: ‘Improving the accuracy of question classification with machine learning’. IEEE Int. Conf. Research, Innovation and Vision for the Future, Hanoi, Vietnam, March 2007, pp. 234241, doi: 10.1109/RIVF.2007.369162.
    6. 6)
    7. 7)
      • 9. CCDS. Available at https://www.ncbi.nlm.nih.gov/projects/CCDS/CcdsBrowse.cgi, accessed January 2017.
    8. 8)
    9. 9)
      • 8. COSMIC. Available at http://cancer.sanger.ac.uk/cosmic, accessed January 2017.
    10. 10)
http://iet.metastore.ingenta.com/content/journals/10.1049/el.2017.1890
Loading

Related content

content/journals/10.1049/el.2017.1890
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading
Correspondence
This article has following corresponding article(s):
in brief