Mass Detection in Digital Mammograms System Based on PSO Algorithm
Wei Chen Lin, Shih Chang Hsu, An Cheng · 2014
For the early detection of breast cancer, radio logists often rely on their experiences and read mammograms with the naked eye. This method of detection, however, leaves many breast cancer lesions undetected. In this article, we discuss the development of a new technology, which identifies masses in mammograms. This technology is able to mark the positions of possible masses, allowing further assessment by the radiologists and effectively increasing the rate of correct diagnosis of breast cancer. Because masses in mammograms present themselves as low frequency signals, we have established the following steps for detecting them: Firstly, the original image undergoes wavelet transformation and enhances the mass signals before being inverse-transformed backward to an image, an image with enhanced processes would make masses easier to discern. Second, possible masses are identified and positioned using particle swarm optimization, PSO. Mammograms used in this study were sourced from the Mammographic Image Analysis Society (MIAS) database in Europe. Experimental results show that a detection rate of 94.44% or higher can be achieved using this method, hence improved accuracy in breast cancer lesion detection.