Detection of microcalcifications in digital mammograms using wavelets

Abstract

This paper presents an approach for detecting microcalcifications in digital mammograms employing wavelet-based subband image decomposition. The microcalcifications appear in small clusters of few pixels with relatively high intensity compared with their neighboring pixels. These image features can be preserved by a detection system that employs a suitable image transform which can localize the signal characteristics in the original and the transform domain. Given that the microcalcifications correspond to high-frequency components of the image spectrum, detection of microcalcifications is achieved by decomposing the mammograms into different frequency subbands, suppressing the low-frequency subband, and, finally, reconstructing the mammogram from the subbands containing only high frequencies. Preliminary experiments indicate that further studies are needed to investigate the potential of wavelet-based subband image decomposition as a tool for detecting microcalcifications in digital mammograms.

An automatic microcalcification detection system based on a hybrid neural network classifier

“…Concerning image segmentation and specification of regions of interest (ROIs), several methods have been proposed such as classical image filtering and local thresholding [9,12,39,45], techniques based on mathematical morphology [13,60], stochastic fractal models [25,26], wavelet analysis [3,7,22,23,46,52,56,57] and multiscale analysis based on a specialized Gaussian and Peitgen [32]. Furthermore, various classification methodologies have been reported for the characterization of ROI such as, rule-based systems [9,12], fuzzy logic systems [11], statistical methods based on Markov random fields [20] and support vector machines [3].…”

Detection of Microcalcification Clusters Using Hessian Matrix and Foveal Segmentation Method on Multiscale Analysis in Digital Mammograms

“…Wang et al have proposed an algorithm for microcalcification detection in digital mammograms based on wavelet subband decomposition [8]. In their method, detection is achieved by decomposing a mammogram into different frequency subbands, suppressing the low-frequency subband and finally reconstructing an image from the subbands containing only high frequencies.…”

Associative Classifiers for Medical Images

“…All these things contribute to the decisions that are made on such images even more difficult. Different methods have been used to classify and detect anomalies in medical images, such as wavelets [4,15], fractal theory [8], statistical methods [6] and most of them used features extracted using image processing techniques [13]. In addition, some other methods were presented in the literature based on fuzzy set theory [3], Markov models [7] and neural networks [5,9].…”