Breast cancer classification using GLCM and BPNN

Among all the cancer in women, breast cancer is the most common and deadliest cancer. In 2018, there were 22.692 Indonesian women dead because of breast cancer. Until now, the main cause of breast cancer is still unknown. However, the possibility of recovery and survival rates can be increased through early detection. One of the most efficient ways of early detection is through mammography. Mammography produces images called mammograms. The main objective of this paper is to develop Computer Aided Diagnosis (CADx) system that can help radiologist determine breast cancer cases based on mammogram image. In this paper, a combination of the Gray-level Co-Occurrence matrix (GLCM) and Backpropagation Neural Network (BPNN) is used to classify normal-abnormal patient based on mammogram image. Using mammogram image provided by Mammography Imaging Analysis Society (MIAS), a test for the proposed method was concluded. The result was, accuracy 94.06%, Sensitivity 90.16% , and Specificity 95.57%.