• DocumentCode
    304718
  • Title

    3D image analysis of the lung area using thin section CT images and its application to differential diagnosis

  • Author

    Tozaki, Tetsuya ; Kawata, Yoshiki ; Niki, Noboru ; Ohmatsu, Hironobu ; Eguchi, Kenji ; Moriyama, Noriyuki

  • Author_Institution
    Dept. of Inf. Sci., Tokushima Univ., Japan
  • Volume
    1
  • fYear
    1996
  • fDate
    16-19 Sep 1996
  • Firstpage
    281
  • Abstract
    The lung area has a very complicated structure which consists of the bronchus, the pulmonary artery, and the pulmonary vein. So it is difficult for even medical specialists to understand the spatial relationships between the tumor, the bronchus, and the blood vessels. Here we present a 3D image analysis method of the lung area using thin section CT images, and we apply this system to the differential diagnosis of abnormal tissue to determine if it is of malignant or benign nature. This system consists of two steps. The first step is the analysis and classification of the structure of the lung area, and the second step is the 3D visualization and their quantitative analysis of pre-classified pulmonary organs for quantitative analysis
  • Keywords
    computerised tomography; image classification; lung; medical image processing; 3D image analysis; 3D image analysis method; 3D visualization; X-ray CT scanner; abnormal tissue; benign nature; blood vessels; bronchus; classification; differential diagnosis; lung area; lung cancer; malignant nature; pre-classified pulmonary organs; pulmonary artery; pulmonary vein; quantitative analysis; thin section CT images; tumor; Arteries; Biomedical imaging; Blood vessels; Cancer; Computed tomography; Image analysis; Lungs; Medical diagnostic imaging; Neoplasms; Veins;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Image Processing, 1996. Proceedings., International Conference on
  • Conference_Location
    Lausanne
  • Print_ISBN
    0-7803-3259-8
  • Type

    conf

  • DOI
    10.1109/ICIP.1996.560808
  • Filename
    560808