Breast Cancer Research Today is a free monthly online journal that collates and summarizes the latest research about Breast Cancer, including details on symptoms, genetics, screening, treatment, information.

Multiplexed wavelet transform technique for detection of microcalcification in digitized mammograms.

Mini MG, Devassia VP, Thomas T

Department of Electronics, Cochin University of Science & Technology, Cochin, Kerala, India.

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.

Published 4 February 2005 in J Digit Imaging, 17(4): 285-91.
Full-text of this article is available online (may require subscription).

© 2004-2008 Breast Cancer Research Today. All Rights Reserved.