Digital mammograms contrast enhancement using wavelets — A comparative study

Abstract

Mammography is the most used diagnosis method for the breast cancer. The challenge of this exam is to obtain good contrast and resolution with small radiation doses. In recent years, several efforts have been done to improve the detection efficiency of mammograms by using the potential offered by digital image processing. In this work, the potential benefits of applying the wavelet transform for microcalcifications enhancement in the digital mammograms is studied. Several contrast enhancement methods based on wavelets found in literature were adjusted and applied to a digital mammogram dataset. Their performance was evaluated by appropriate quantitative metrics, and the advantages and disadvantages of each them are described in this study. This study represents a good starting point to choose an adequate enhancement method based on wavelet transform for a specific problem.

Wavelet-Based Local Contrast Enhancement for Satellite, Aerial and Close Range Images

“…The term "multiscale local contrast" is very often applied, based on the definition given by Peli [39]: the ratio of the coefficients after the upper-pass transformation to the image coefficients after the lower-pass transformation. These particular solutions use linear or non-linear functions for scaling the wavelet coefficients, with thresholds for large coefficients [12,37,40]. One paper [41] has reported successful enhancement via the employment of a non-linear function based on the local dispersion of the wavelet coefficients modelled as a bivariate Cauchy distribution.…”

“…Finally, the proposed enhancement can be realised by the summation of signal and details. The WLCE concept is based on ideas presented in papers [12,37,40]. The form of scaling function and the output image reconstruction by summation of scaling wavelets components is innovative.…”

Multiple-level Logarithmic Wavelets for Mammographic Contrast Enhancement: A Statistical Analysis for Wavelet Selection

“…It means that if the image is constant or do not vary 'too much' in the support of a wavelet, then its wavelet transform will be zero or very small, this is how wavelets provide information about the local contrast of an image [28]. This fact is useful because anomalies can be detected with the detail coefficients and can be isolated to improve the contrast against the surrounding region [22,19,28].…”

“…Some methods apply heuristics over the wavelets coefficients, e.g. Simple, Threshold, Correlation and Local Correlation methods [22]. In [37] we demonstrated that the most effective method is the Local Correlation.…”

“…This paper proposes a methodology to select the decomposition levels to be process in wavelet-based algorithms. A contrast improvement is performed by modifying the wavelet coefficients using the Local Correlation method in a logarithmic framework [4,22]. Quantitative contrast measures [34] and Principal Components Analysis [15] are used to select the best combination of decomposition levels.…”