Integration of Fuzzy and Wavelet Approaches towards Mammogram Contrast Enhancement

Abstract

Mammography is the most reliable, effective, low cost and high sensitive method for early detection of breast cancer. In breast cancer diagnosis, it is difficult for radiologists to detect the typical diagnostic signs because mammograms are low contrast and noisy images. In order to improve diagnosis accuracy, mammogram contrast enhancement technique is often used to enhance the contrast of mammogram and aid the radiologists. In this paper, a combined approach with fuzzy and wavelet towards improved enhancement of details and subtle features in digital mammogram images. The proposed contrast enhancement approach utilizes wavelet transform to decompose the mammogram, and then approximation coefficients are modified by fuzzy contrast enhancement approach and detail coefficients are by non-linear transformation. After that, inverse wavelet transform is applied on modified coefficients to obtain the enhanced mammogram. The proposed algorithm has been tested on a number of images in Digital Database for Screening Mammography (DDSM), comparing the results with histogram equalization which is a well-established image enhancement technique and Cheng’s enhancement algorithm based on wavelet transform. In order to accurately assess the proposed approach, enhanced mammogram images are evaluated through objective image quality assessment parameters: information entropy, contrast and peak signal-to-noise ratio (PSNR). Experimental results of the proposed approach are quite promising.