<title>Hexagonal wavelet processing of digital mammography</title>

Abstract

This paper introduces a novel approach for accomplishing mammographic feature analysis through overcomplete multiresolution representations. We show that efficient representations may be identified from digital mammograms and used to enhance features of importance to mammography within a continuum of scale-space. We present a method of contrast enhancement based on an overcomplete, non-separable multiscale representation: The hexagonal wavelet transform. Mammograms are reconstructed from transform coefficients modified at one or more levels by local and global non-linear operators. Multiscale edges identified within distinct levels of transform space provide local support for enhancement In addition, we show that transform coefficients, modified (globally within each level) by an adaptive non-linear operator (histogram specification), can make more obvious unseen or barely seen features of mammography without requiring additional radiation. In each case, multiscale edges and gain parameters are id€ ntified adaptively by the measure of energy within each level of scale space We demonstrate that features extracted from multiresolution representations can provide an adaptive mechanism for accomplishing local contrast enhancement We suggest that multiscale detection and local enhancement of singularities may be effectively employed for the visualization of breast pathology without excessive noise amplification. By improving the visualization of breast pathology we can improve chances of early detection (improve quality) while requiring less time to evaluate mammograms for most patients (lower costs).

Contrast enhancement for image by WNN and GA combining PSNR with information entropy

“…Based on DSWT, a non-linear enhancement operator, which was proposed by Laine in 1994, is employed to enhance the local contrast for image (Laine and Schuler 1993). For convenience, let us define following transform function to enhance the high frequency sub-band images in each decomposition level, respectively: In order to obtain detail image, inverse discrete stationary wavelet transform is done to reconstruct detail image.…”

“…B. Fitness function In this paper, Shannon's entropy function is used to quantify the gray-level histogram complexity (Laine and Schuler 1993). The entropy function traditionally used in thermodynamics was first introduced by Claude Shannon in 1948 for the measurement of uncertainly in the information theory.…”

Modification of Mammograms for Early Diagnosis of Breast Cancer Using Wavelet and Neural Networks

“…However, sometimes this process is disturbed and cells begin to reproduce themselves in an abnormal way, building a tumor. [1,4,3] The breast cancer is a prevalent cancer among women that often is beginning from lobules and duct. It is divided to invasive and non-invasive types.…”

Global and Local Contrast Enhancement for Image by Genetic Algorithm and Wavelet Neural Network

“…Laine in 1994, is employed to enhance the local contrast for image [7]. For convenience, let us define following transform function to enhance the high frequency subband images in each decomposition level respectively: Fig.6 (a).…”