Mammographic feature enhancement based on second generation curvelet transform

The early detection of breast cancer is clearly a key ingredient of any strategy designed to reduce breast cancer mortality. The paper shows that second generation curvelet transform coefficients, modified by non-linear operators, can reconstruct mammography and make more obvious barely seen features of mammography in order to detect breast cancer more early and accurately. The edge protection index and the contrast improvement index are used to evaluate the quality of proceeded image regions containing verified lesions. Results of the experiment show the efficiency of the method.