Breast cancer diagnosis system using hybrid support vector machine-artificial neural network

Breast cancer is the second most common occurring in women. Early detection through mammogram screening can save more women’s lives. However, even senior radiologists may over-diagnose clinical condition. Machine learning (ML) used technique diagnosis of to help reduce human errors. This study aimed develop a computer-aided (CAD) system using ML for classification purposes. In this work, 80 digital mammograms normal breasts, 40 benign and malignant cases were chosen from mini MIAS dataset. These images denoised median filter after they segmented obtain region interest (ROI) enhanced histogram equalization. work compared performance artificial neural network (ANN), support vector machine (SVM), reduced features SVM hybrid SVM-ANN process statistical gray level co-occurrence matrix (GLCM) extracted images. It found that gives best accuracy 99.4% 100% differentiating abnormal, cases, respectively. model was deployed developing CAD which showed relatively good 98%.