Detection and Classification of Breast Cancer from Digital Mammograms using RF and RF-ELM Algorithm

Neural Network is utilized as a developing analytic tool for the diagnosis of breast cancer. The goal of this research is to determine breast tumor from digital mammograms with a machine learning technique in view of RF and combination of RF-ELM classifier. For digital mammogram images, MIAS database is used. Preprocessing is usually needed to enhance the low quality of the image. The region of interest (ROI) is determined in line with the scale of suspicious region. After the suspicious area is sectioned, features are extracted by texture analysis. GLCM is used as a texture attribute to extract the suspicious area. From all extracted features best features are selected with the help of CBF method. To enhance the exactness of classification, only six features are selected. These features are mean, standard deviation, kurtosis, variance, entropy and correlation coefficient. RF and RF-ELM are used as a classifier. The outcomes of present work show that the CAD system with the usage of RF-ELM classifier may be very powerful and achieves the exceptional results in the prognosis of breast cancer.