Classification of breast tumors via parabolic modeling of their contours

The discrimination between malignant tumors and benign masses in mammograms can be difficult because of the diversity of tumor shape. In order to facilitate this discrimination, we propose a method of shape analysis based only on characterization of the boundaries of the tumors via parabolic modeling. The contours used were drawn (using XPAINT) on digitized mammograms by an expert radiologist (JELD). The classification of 54 tumors as benign or malignant was achieved with an accuracy of 76 percent.