• DocumentCode
    264758
  • Title

    Lung Nodule Segmentation Using EM Algorithm

  • Author

    Qian Yiming ; Weng Guirong

  • Author_Institution
    Sch. of Mech. & Electr. Eng., Soochow Univ., Suzhou, China
  • Volume
    1
  • fYear
    2014
  • fDate
    26-27 Aug. 2014
  • Firstpage
    20
  • Lastpage
    23
  • Abstract
    Lung disease is often performed as nodules. Pulmonary nodule is one of important symbols of lung disease. Characteristics of pulmonary nodules always indicate the nature of lung disease. Detection of pulmonary nodules has great significance in diagnosing lung cancer. Study of pulmonary nodules is now a hot research. CT is a new type of medical imaging equipment with a high density resolution and adequate image information. But to detect small pulmonary nodes, radiologists need to read a lot of images. It could easily lead to misdiagnosis and miss-diagnosis. This paper uses EM algorithm in CT images for the lung nodule detection and segmentation. The application shows that the method of this paper is to improve the early detection rate of lung cancer nodules and one of the effective methods using computer-aided analysis of lung nodules. The algorithm used is simple, effective and practical.
  • Keywords
    computerised tomography; diseases; expectation-maximisation algorithm; image resolution; image segmentation; lung; medical image processing; object detection; CT images; EM algorithm; computer-aided analysis; high density resolution; image information; lung cancer diagnosis; lung disease; lung nodule detection; lung nodule segmentation; medical imaging equipment; misdiagnosis; miss-diagnosis; pulmonary nodes; pulmonary nodule detection; Cancer; Computed tomography; Filtering; Gray-scale; Histograms; Image segmentation; Lungs; expectation maximization algorithm; lung nodule; mathematical morphology;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Intelligent Human-Machine Systems and Cybernetics (IHMSC), 2014 Sixth International Conference on
  • Conference_Location
    Hangzhou
  • Print_ISBN
    978-1-4799-4956-4
  • Type

    conf

  • DOI
    10.1109/IHMSC.2014.13
  • Filename
    6917296