A novel fuzzy logic approach to mammogram contrast enhancement

Breast cancer continues to be a significant public health problem in the United States. Primary prevention seems impossible since the causes of this disease still remain unknown. Early detection is the key to improving breast cancer prognosis. Mammography has been one of the most reliable methods for early detection of breast carcinomas. However, it is difficult for radiologists to provide both accurate and uniform evaluation for the enormous number of mammograms generated in widespread screening. Automated breast cancer diagnosis attracts much attention of the researchers. However, the fuzzy nature of the mammograms and the low contrast between the breast cancer and its surroundings make the automated breast cancer detection very difficult. Mammogram contrast enhancement is critical and essential to breast cancer diagnosis.This paper uses an adaptive fuzzy logic contrast enhancement method to enhance mammographic features. We first normalize the mammograms to reduce the effects of different illuminations. Then, we fuzzify the normalized images based on the maximum fuzzy entropy principle. The local contrast is measured and enhanced by utilizing both the global and local information so that the fine details of mammograms can be enhanced and the noise can be suppressed. The histogram of the mammogram provides the global information and the fuzzy entropy of local window is computed to analyze the local information. Then, we use both the global and local information to define and enhance the contrast. Finally, the defuzzification is performed to transform the enhanced mammogram back to the spatial domain. The experiments demonstrate that the proposed method can effectively enhance the contours and fine details of the mammographic features which will be useful for breast cancer diagnosis.