• DocumentCode
    2561702
  • Title

    A method of image enhancement and fractal dimension for detection of microcalcifications in mammogram

  • Author

    Nam, Sang Hee ; Choi, Jun Young

  • Author_Institution
    Dept. of Biomed. Eng., Inje Univ., Kyungnahm, South Korea
  • Volume
    2
  • fYear
    1998
  • fDate
    29 Oct-1 Nov 1998
  • Firstpage
    1009
  • Abstract
    Some research related to the digital image processing and analysis of mammograms have been conducted to solve the problems in interpreting mammograms. In X-ray film-screen mammography, the contrast between benign and malignant cancer is not so distinct. This study was performed to help radiologists with interpreting mammograms by providing fractal dimensions of three types of data. Raw data of the 90 patients (30 for each group: `mass´, `mass and microcalcifications´, and `microcalcifications´ groups) were obtained in conditions of 0.1 mm resolution, 12 bit gray scale images. The image enhancement was performed and the fractal dimensions were extracted to represent the roughness and the irregularity of the images. The mass showed a smooth shape. However, microcalcification symptoms had more rough figures. In conclusion, the calculation of the fractal dimension could improve the early detection of breast cancer. The fractal dimension could be applied for the diagnosis of breast cancer
  • Keywords
    cancer; fractals; image enhancement; mammography; medical image processing; 12 bit gray scale images; benign disease; breast cancer; fractal dimension; image enhancement method; image irregularity; image roughness; mammograms; medical diagnostic imaging; microcalcifications detection; Breast cancer; Data mining; Digital images; Fractals; Image analysis; Image enhancement; Image resolution; Mammography; Shape; X-ray imaging;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Engineering in Medicine and Biology Society, 1998. Proceedings of the 20th Annual International Conference of the IEEE
  • Conference_Location
    Hong Kong
  • ISSN
    1094-687X
  • Print_ISBN
    0-7803-5164-9
  • Type

    conf

  • DOI
    10.1109/IEMBS.1998.745620
  • Filename
    745620