• DocumentCode
    534556
  • Title

    Intelligent pulmonary embolsim detection system

  • Author

    Tsai, Hao-Hung ; Chin, Chuin-Li ; Cheng, Yung-Chih

  • Author_Institution
    Dept. of Diagnostic Radiol., Chung Shan Med. Univ. Hosp., Taichung, Taiwan
  • Volume
    1
  • fYear
    2010
  • fDate
    16-18 Oct. 2010
  • Firstpage
    329
  • Lastpage
    335
  • Abstract
    Pulmonary embolism (PE) is a blockage of the pulmonary artery or one of its branches, usually occurring when a deep vein thrombus (blood clot from a vein) becomes dislodged from its site of formation and travels, or embolisms, to the arterial blood supply of one of the lungs. This process is termed thromboembolism. Most of the traditional detection of PE needs to rely on the professional judgments of physicians. With advances in CT technology, faster scanning and greatly enhanced the quality of image improve the diagnostic accuracy. Serious PE will lead to death. However, it is very important to diagnose PE. First, we use Multiple Active Contour Models (MACMs) combining the hierarchy of tree to obtain the regional lung, as well as the vessel distribution of the region. In the last step in our system, we use the Gabor Neural Network (GNN) to find the location of thrombosis.
  • Keywords
    blood; blood vessels; computerised tomography; edge detection; medical disorders; medical image processing; neural nets; CT; Gabor neural network; blood clot; deep vein thrombus; intelligent detection system; multiple active contour models; pulmonary artery; pulmonary embolism; regional lung; thrombosis; vein; vessel distribution; Arteries; Artificial neural networks; Biomedical imaging; Computed tomography; Gabor filters; Lungs; Medical services; CT; Gabor neural network; MACMs; Pulmonary embolism;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Biomedical Engineering and Informatics (BMEI), 2010 3rd International Conference on
  • Conference_Location
    Yantai
  • Print_ISBN
    978-1-4244-6495-1
  • Type

    conf

  • DOI
    10.1109/BMEI.2010.5639506
  • Filename
    5639506