2017 IEEE International Conference on Wireless Communications, Signal Processing and Networking (WiSPNET 2017)

307 / 2017-02-14 19:00:40

Computer-aided Diagnosis System for Breast Cancer using RF Classifier

9734,12812,12813,12205,8751,12070,12452,9227

Breast Cancer is the most common cancer and one of the major causes of cancer death in women worldwide. The solution for this is early detection and diagnosis. Artificial Neural Network is used as emerging diagnostic tool for breast cancer. The main objective of this research is a diagnosis of breast cancer with a machine learning method based on random forest classifier. The digital mammogram images are taken from MIAS database. The database consists of 280 mammogram images. Preprocessing is generally needed to enhance the poor quality of the image. The region of interest (ROI) is the suspicious area which is segmented. Features are extracted by texture analysis. Feature selection technique is used for the detection of High-dimensional features.
A statistical method, gray-level co-occurrence matrix (GLCM) is used as the texture attribute to extract the suspicious area. From all extracted features best feature are selected with the help of FCBF which is fast correlation-based feature selection technique. The selected features to improve the accuracy of classification are mean, standard deviation, smoothness, angular second moment (ASM), entropy, and correlation. Random Forest (RF) is used as a classifier. The results of present work show that the proposed method has achieved the accuracy to the extent of 97.32%, sensitivity as high as 97.45%, specificity of about 98.13% and ROC is 97.28%.