Detection of Abnormal Masses in Mammogram Images

Masses in the breast can be located in digital mammogram images by computationally analysing various feature statistics from the image. Any algorithm used to analyse digital mammogram images can be both time-consuming and errorprone because many areas of these images appear to have features that are mass-like but not masses. Thus false positives are produced which detract from the effectiveness of the algorithm. In this paper an efficient-straightforward algorithm to locate and record suspicious areas in a mammogram image is presented. Mammography is at present one of the available method for early detection of masses or abnormalities which is related to breast cancer. The most common said abnormalities that may indicate breast cancer are masses and calcifications. The challenge is to early and accurately detect to overcome the development of breast cancer, which affects more and more women throughout the world. Masses appear in a mammogram as fine, granular clusters, which are often difficult to identify in a raw mammogram. Digital mammogram is one of the best technologies currently being used for diagnosing breast cancer. Breast cancer is diagnosed at advanced stages with the help of the digital mammogram image. In the paper a method is proposed to make a supporting tool to easy and less time consuming of identification of abnormal masses in digital mammography images. The technique uses a form of template matching at multiple scales to locate pixels in the image, which may be part of a mass. The resulting image is adaptively thresholded to a predetermined level of accuracy and then the remaining pixels are grouped together and extracted. The type of masses, orientation of masses, shape and distribution of masses, size of masses, position of masses, density of masses, and symmetry between two pair are clearly sited after proposed method is executed on raw mammogram for easy and early detection abnormality.