Multiplexed Wavelet Transform Technique for Detection of Microcalcification in Digitized Mammograms

Abstract

Wavelet transform (WT) is a potential tool for the detection of microcalcifications, an early sign of breast cancer. This article describes the implementation and evaluates the performance of two novel WT-based schemes for the automatic detection of clustered microcalcifications in digitized mammograms. Employing a one-dimensional WT technique that utilizes the pseudo-periodicity property of image sequences, the proposed algorithms achieve high detection efficiency and low processing memory requirements. The detection is achieved from the parent-child relationship between the zero-crossings [Marr-Hildreth (M-H) detector] /local extrema (Canny detector) of the WT coefficients at different levels of decomposition. The detected pixels are weighted before the inverse transform is computed, and they are segmented by simple global gray level thresholding. Both detectors produce 95% detection sensitivity, even though there are more false positives for the M-H detector. The M-H detector preserves the shape information and provides better detection sensitivity for mammograms containing widely distributed calcifications.

Microcalcification Detection by Morphology, Singularities of Contourlet Transform and Neural Network

“…Recently, wavelet-based enhancement approaches [3][4] [5] [6] have been employed to acquire better performances. Natural images have higher geometrical characteristics [7], and the discontinuity is always along the smooth curve.…”

Deep Learning Capabilities for the Categorization of Microcalcification

“…Microcalcification is the most common mammographic indication of DCIS. DCIS is not severe, but it can lead to invasive breast cancer after some time [ 1 , 3 ]. Microcalcifications are small size deposits of calcium, which is brighter, compared with normal breast tissues.…”

“…Multiresolution decomposition-based approaches have earlier been applied to mammograms enhancement. Mini et al applied wavelet-based techniques for microcalcification detection and achieved 95% accuracy on the MIAS dataset [ 3 ]. Bocchi et al used Radon transform-based features for shape analysis of microcalcification to detect its malignancy by using Radon and moment-based features [ 4 ].…”

Calcifications Attenuation in Left Coronary Artery CT Images Using FDA Domain

“…Introduce computer aided two separate techniques for mass and micro-calcification segmentation in digital mammograms using several steps of operations (Hanmandlu, Vineel, Madasu, & Vasikarla, 2008). The computer aided micro-calcification detection based on regular wavelets, multiplexed wavelet transform technique and wavelet domain hidden Markov tree model (Lemaur, Drouiche, & DeConinck, 2003;Mini, Devassia, & Thomas, 2004;Nakayama, Uchiyama, Yamamoto, Watanabe, & Namba, 2006;Regentova, Zhang, Zheng, & Veni, 2007). The image filtering methods are described on computer-aided detection of micro-calcification clusters in mammograms and the performance of those methods (Eddaoudi & Regragui, 2011;El-Naqa, & Yang, 2005;Jing, Yang, & Nishikawa, 2011;Kabbadj, Regragui, & Himmi, 2012;Lemaur et al, 2003;Tang, Rangayyan, Xu, El-Naqa, & Yang, 2009;Zhang et al, 2013).…”