• DocumentCode
    2553133
  • Title

    Extension Artificial Immune System approach in MRI classification

  • Author

    Wang, Chuin-Mu ; Chu, Shao-Wei ; Su, Ching-Yuan

  • Author_Institution
    Dept. of Comput. Sci. & Inf. Eng., Nat. Chin-Yi Univ. of Technol., Taichung, Taiwan
  • fYear
    2011
  • fDate
    21-25 June 2011
  • Firstpage
    855
  • Lastpage
    859
  • Abstract
    Magnetic Resonance Imaging (MRI) has become a useful modality because it provides unparallel capability of revealing soft tissue characterization as well as 3-D visualization. Immune system is regarded a remarkable mechanism capable of self-organizing to best strengthen its function for defending outside attacks. As such, the Artificial Immune System (AIS) theory is gradually adopted in designing optimal computation systems. In the study, an extension AIS(EAIS) shows antibody affinity to deal with enormous spectrum data and also characterizes Gray Matter (GM), White Matter (WM) and Cerebral Spinal Fluid (CSF) to highly benefit doctors and patients. According to the comparing results, the EAIS is better than C-means in classification.
  • Keywords
    artificial immune systems; biological tissues; biomedical MRI; brain; data visualisation; image classification; medical image processing; 3D visualization; AIS theory; MRI classification; antibody affinity; cerebral spinal fluid; extension AIS; extension artificial immune system; gray matter; magnetic resonance imaging; optimal computation system; outside attack; soft tissue characterization; spectrum data; white matter; Biomedical imaging; Cancer; Computer science; Correlation; Immune system; Magnetic resonance imaging; Artificial Immune System (AIS); Magnetic Resonance Imaging (MRI); classification; extension;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Intelligent Control and Automation (WCICA), 2011 9th World Congress on
  • Conference_Location
    Taipei
  • Print_ISBN
    978-1-61284-698-9
  • Type

    conf

  • DOI
    10.1109/WCICA.2011.5970636
  • Filename
    5970636