Classification System of Breast Cancer using Machine Learning on Hu Moment Invariants and GLCM Features
Yessi Jusman, Rika Nursanthika, C Anna Nur Nazilah · 2024
Breast cancer is a devastating disease with a high mortality rate. In most cases, women are the ones suffering from breast cancer. Mammogram screening is the most prevalent method to diagnose this disease. The mammogram images are manually examined by radiologists. Machine learning can help medical personnel and reduce the possibility of misdiagnosis. The Hu moment and Gray Level Co-occurrence Matrix (GLCM) were employed for feature extraction. Moreover, Support Vector Machine (SVM) and K-Nearest Neighbors (KNN) were utilized for breast cancer classification. The mammogram images in this study were taken from the Curated Breast Imaging Subset of Digital Database Screening Mammography (CBIS-DDSM). GLCM combined with Weighted KNN depicted the highest accuracy of 97.8%.