Mammogram Classification Using Discrete Wavelet Transform Features and a Novel Vector Quantization Technique for Breast Cancer Detection
Ahmad M. Sarhan *
Department of Computer Engineering, College of Computers and Information Technology, Taif University, Taif, Saudi Arabia
Radaan A. Al-Dosari
Saudi Electricity Company, Riyadh, Saudi Arabia
*Author to whom correspondence should be addressed.
Abstract
In this paper, a digital mammogram classification system is presented. The proposed system uses the Discrete Wavelet Transform (DWT) to obtain features from the input mammogram image. The proposed system suggests a new algorithm for generating the codebook used by the vector quantization (VQ) algorithm to classify the input mammogram (malignant, benign, or normal). The obtained results on the DDSM database indicate the significant performance and superiority of the proposed method in comparison with the state of the art approaches. Simulation results show that the proposed system achieves a high accuracy and sensitivity.
Keywords: Medical images, breast cancer, discrete wavelet transform (DWT), vector quantization (VQ), mammogram