Contrast Enhancement of Mammograms and Microcalcification Detection

Abstract

Mammography is an operative procedure for early detection of cancer present in breast. However, the pathological changes of the breast are difficult to interpret from low contrast mammograms. This research proposes a method to enhance the contrast of the mammogram that uses Non-subsampled contourlet transform (NSCT) based edge information. Instead of a directional filter bank in the conventional NSCT structure, this paper uses multiscale non-separable edge filters. These edge filters outputs intrinsic edge structure information based on simplified hyperbolic tangent function applied with two polarized schemes. This edge information further used to improve the local contrast. Adaptive histogram equalization (AHE) also used to increase the overall contrast of mammogram. Improved detection of microcalcification (MC) from enhanced mammogram images shows the success of this algorithm. This method has better enhancement measure (EME) than AHE and unsharp based mammogram enhancement method.

Digital Image Processing and Its Application for Medical Physics and Biomedical Engineering Area

“…It is the most widely used agent for this purpose because of the advantages of 99mTcsestamibi tagging and its great efficiency in detecting carcinomas [56]. • Enhancement based upon wavelet transform and morphology, morphological operations (enhancement of image using multi-scale morphology) [59] • Direct contrast enhancement techniques [60] • Adaptive neighborhood contrast enhancement [61] • Removal of noise using wiener function [62] • An intuitionistic fuzzification scheme based on the optimization of intuitionistic fuzzy entropy and contrast limited adaptive histogram equalization (CLAHE) [63] • Mammogram enhancement, non-subsampled pyramid (NSP), low pass filter (LPF), high pass filter (HPF), directional filter bank (DFB), 2D-directional edge filter (HTDE), combining directional and scale features, adaptive histogram equalization (AHE), one-dimensional spatial profile of difference of Gaussian and HTDE filter, detection of microcalcification (MC) [64,65]…”

A Novel Approach based on PSO Optimized K-Means in MRI Brain Image Segmentation

“…Vishnumurthy et al, [5] presented a technique for segmenting brain MRI using morphological techniques and the outcomes are equated against Maximum expectation technique and Fuzzy C-Means and various performance measures are analysed along with processing time. Abhisha Mano [12][15]and Anand et al [14] [13] proposed an efficient approach to enhance the contrast and obtain segmentations of retinal, mammograms, DNA fragments, brain etc.…”

Contrast Enhanced Superpixel Based Segmentation of Retinal Images

“…The overall contrast is improved by adaptive histogram equalization. Using this technique microcalcifications can be easily detected [12][13].…”