• DocumentCode
    518927
  • Title

    A breast region extraction scheme for digital mammograms using gradient vector flow Snake

  • Author

    Yu, Shyr-Shen ; Tsai, Chung-Yen ; Liu, Chen-Chung

  • Author_Institution
    Dept. of Comput. Sci. & Eng., Nat. Chung-Hsing Univ., Taichung, Taiwan
  • fYear
    2010
  • fDate
    11-13 May 2010
  • Firstpage
    715
  • Lastpage
    720
  • Abstract
    Extracting the breast region accurately from a mammogram is a kernel stage for the breast mass analysis. It significantly influences the overall analysis accuracy and processing speed of the whole breast mass analysis. This paper presents an algorithm to extract the breast region from a mammogram. The presented algorithm first combines the median filtering, the morphological erosion processing, Sobel edge detector, and thresholding to find the rough boundary of the breast boundary, then uses the gradient vector flow snake (GVF- Snake) with gradient map adjustment to obtain the accurate breast boundary from the rough breast boundary. The presented algorithm is tested on the digital mammograms from the Mammogram Image Analysis Society (MIAS) database. The experimental results show that the breast region extracted by the presented algorithm approximately follows that extracted by an expert radiologist.
  • Keywords
    edge detection; feature extraction; gradient methods; image segmentation; mammography; median filters; medical image processing; Sobel edge detector; breast mass analysis; breast region extraction scheme; digital mammograms; gradient map adjustment; gradient vector flow Snake; mammogram image analysis society database; median filtering; morphological erosion processing; Active contours; Breast; Computer science; Deformable models; Detectors; Filtering algorithms; Histograms; Image edge detection; Kernel; Testing; GVF-snake; Mammogram; breast; extrapolation; mean error;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    New Trends in Information Science and Service Science (NISS), 2010 4th International Conference on
  • Conference_Location
    Gyeongju
  • Print_ISBN
    978-1-4244-6982-6
  • Electronic_ISBN
    978-89-88678-17-6
  • Type

    conf

  • Filename
    5488523