doi:10.3850/978-981-08-7618-0_1250

ABSTRACT

Micro-calcifications are the earliest sign of breast carcinomas and their accurate detection is one of the key issues of breast cancer control. In this paper, a new image enhancement technique which would aid automated detection of microcalcifications, leading to efficient computer-aided diagnosis of breast cancer is proposed. The proposed non-linear transformation function used for contrast enhancement is a scaled version of a linear combination of double sigmoid function. The effect of this transformation function has been evaluated using two assessment parameters, viz., PSNR & a universal Q-Metric. The enhancement technique has been tested on different types of mammographic images (with various categories of background tissues) which usually suffer from poor contrast. Significant contrast improvement is the speciality of this technique, leading to more accurate detection of micro-calcifications in mammographic images.

Keywords: Micro-calcifications, Double sigmoid function, Contrast enhancement, PSNR, Q-metric.

© 2011 ICCA 2010 Organizers