Classification of Breast Cancer using PNN Classifier based on GLCM Feature Extraction and GMM Segmentation
Daffa Fajri Riesaputri, Christy Atika Sari, De Rosal Ignatius Moses Setiadi, Eko Hari Rachmawanto · 2020 International Seminar on Application for Technology of Information and Communication (iSemantic) · 2020
Breast cancer is the most cancer affecting women. Cases in this disease that continue to increase every year lead to the notion that this cancer cannot be cured. Doing early detection of breast cancer can be very helpful to minimize the effects of this disease on sufferers. This research proposes the classification of breast cancer based on mammographic images using Probabilistic Neural Network (PNN) as a classifier, to optimize PNN work preprocessing steps such as median filters are used to minimize noise, in addition to using Gaussian Mixture Model (GMM) segmentation, and extraction features of Gray Level Co-occurrence Matrix (GLCM). PNN classifier was chosen because it can work effectively on small datasets. Based on testing this method produces very good accuracy that is 100% accuracy.