PDF

Keywords

KEYWORDS
breast cancer
artificial neural network
root mean square

Abstract

Abstract In this paper,a computer aided diagnosis [CAD] system has been developed for tumor detection in digital mammography. The system consists of four parts: firstenhance the image,second Feature extraction using six decomposition levels of two dimensional Discrete wavelet transform (2DWT),the features are extracted from regions of interest(ROI),third Reducing the features extracted using two algorithm energy root mean square and mean algorithm of each set of coefficients in each decomposition level, fourth classification of tumor using three layers artificial neural network (ANN) with (19) features is proposed for classifying the marked regions into benign and malignant. Experiments are done on 63 benign tumors and 52 malignant one. The recognition rate of the malignant tumor is (96%) while that of the benign ones is (100%). The result shows that the proposed method can classify the breast tumors effectively when using root mean square algorithm. Keywords: Recognition,Breast Cancer, Artificial Neural Network,root mean square.
https://doi.org/10.33899/rengj.2012.63405
  PDF