Title: A multi-resolution approach to denoising and enhancement of pre-cancerous features in mammograms

Authors: C. Gowri Shankar; T. Balakumaran; A. Shanmugam

Addresses: Department of EEE, K.S.R. College of Engineering, Tiruchengode 637215, Tamil Nadu, India. ' Department of ECE, Coimbatore Institute of Technology, Coimbatore 641 014, Tamil Nadu, India. ' Bannari Amman Institute of Technology, Sathyamangalam 638 401, Tamil Nadu, India

Abstract: Microcalcification is the earliest sign of breast carcinomas and their detection is the key issues for breast cancer control. The existence of noise degrades the subjective quality of image and makes the decision incorrect. A wide variety of filtering algorithms have been developed for preprocessing, but some causes unpleasant visual artifacts. Here multi-scale products are used at successive scales of Wavelet decomposition, obtained by multiplying the coefficients of successive wavelet scale. This would strengthen the significant features while weakening the noise. Testing shows that the proposed scheme better suppresses noise and enhances the objective areas than other methods.

Keywords: microcalcification; wavelet transform; multi-scale products; mammograms; denoising; breast cancer; breast carcinomas; image quality; medical imaging; pre-cancerous features; multi-resolution.

DOI: 10.1504/IJBET.2011.043297

International Journal of Biomedical Engineering and Technology, 2011 Vol.7 No.3, pp.242 - 256

Published online: 21 Jan 2015 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article