Lai, S. M., Li, X., and Bischof, W. F. (1989). Automated detection of breast tumors. In A. Krzyzak, T. Kasvand, and C. Y. Suen (Eds.) Computer Vision and Shape Recognition (pp. 115-132). Singapore: World Scientific.
Mammography is an effective method for detecting breast cancer at the earliest possible stage. Mass screening of mammograms requires the development of automated systems to diagnose breast cancer reliably and efficiently. This paper reports an approach to the detection of one marker, circumscribed masses, using a combination of detection criteria used by experts. The criteria include the shape, brightness contrast and uniform density of tumor areas. Our techniques employ modified median filtering to enhance mammogram images and template matching to detect breast tumors. In the template matching step, suspicious areas are picked by thresholding the cross-correlation values and a percentile method is used to determine the threshold for each filem. In addition, two tests are designed to remove false alarms from the resulting candidates. The results obtained with 24 test images are reported.
Back to publications.