Segmentation of tumor in digital mammograms using wavelet transform modulus maxima on a low cost parallel computing system

Abstract

Parallel Computing System (PCS) is currently used widely in many applications of complex problems involving high computations. This is because it has the capability to process computations efficiently using a parallel scheme. ARS cluster is a low-cost PCS developed to implement processing of full-field digital mammograms. In this system eight processors are used to communicate via the Ethernet network using LINUX which is Fedora 7 as the operating system and Matlab Distributed Computing Server (MDCS) as a platform to process the digital mammograms. In this paper the Wavelet Transforms Modulus Maxima (WTMM) method is used to detect the edge of tumor in digital mammogram implemented on the ARS cluster. The study involved 80 digitized mammographic images obtained from the Malaysian National Cancer Center (NCC). The performance of the PCS in detecting the edge of tumors in digital mammograms using WTMM on the ARS cluster is reported. The experimental results showed that the speedup of the PCS improves when the number of processors is increased. © 2011 Springer-Verlag.