• DocumentCode
    11211
  • Title

    Variable Hidden Neuron Ensemble for Mass Classification in Digital Mammograms [Application Notes]

  • Author

    Leod, P.M. ; Verma, Brijesh

  • Author_Institution
    Central Queensland Univ., Rockhampton, QLD, Australia
  • Volume
    8
  • Issue
    1
  • fYear
    2013
  • fDate
    Feb. 2013
  • Firstpage
    68
  • Lastpage
    76
  • Abstract
    Digital Mammograms are the gold standard for the early detection and diagnosis of breast cancer. Breast cancer is one of the main causes of cancer deaths in women worldwide. One in nine women in Australia will be diagnosed with breast cancer in their lifetime. Women over 50 years of age in particular are encouraged to have screening using digital mammograms so that cancer can be detected at its early stages. Radiologists are able to examine the images by zooming in, changing contrast and brightness and flag any suspicious areas that require further checkup, however in some cases radiologists are unable to spot tumors. Another challenge for radiologists is to classify the tumors once spotted as a benign or malignant diagnosis. This challenge has brought together computer vision and computational intelligence researchers in order to develop new intelligent techniques that can help radiologists.
  • Keywords
    cancer; computer vision; diagnostic radiography; image classification; learning (artificial intelligence); mammography; medical image processing; neural nets; patient diagnosis; Australia; benign diagnosis; breast cancer detection; breast cancer diagnosis; computational intelligence; computer vision; digital mammogram; malignant diagnosis; mass classification; radiologists; tumor classification; variable hidden neuron ensemble; Biological neural networks; Biomedical monitoring; Breast cancer; Cancer; Classification algorithms; Mammograms; Radiology; Tumors;
  • fLanguage
    English
  • Journal_Title
    Computational Intelligence Magazine, IEEE
  • Publisher
    ieee
  • ISSN
    1556-603X
  • Type

    jour

  • DOI
    10.1109/MCI.2012.2228598
  • Filename
    6410717