A wavelet and adaptive threshold-based contrast enhancement of masses in mammograms for visual screening

Abstract

The screening of mammograms is a difficult task for the radiologist, due to variation in contrast and homogeneous structure of the masses and surrounding breast tissues. Therefore, an adaptive threshold-based contrast enhancement method is proposed in this paper for enhancement of suspicious masses in mammograms. Homomorphic filtering and wavelet-based denosing has been used prior to enhancement in the describe method. The approach contains, artefact suppression using pre-processing. Then wavelet transform is applied on the preprocessed mammogram, homomorphic filter is used to filter the approximate coefficient and wavelet shrinkage operator is applied on detail coefficients for denoising. Finally, contrast enhancement approach is used to enhance the suspicious region based on adaptive threshold technique. Two databases, namely Digital Database for Screening Mammography (DDSM) and Mammographic Image Analysis Society (MIAS), were used to test proposed method. The obtain results using proposed method gives better visibility for suspicious masses for all types of mammograms.