Optimized Breast Cancer Premature Detection Method With Computational Segmentation

Abstract

Breast cancer is the most common cancer in women aged 59 to 69 years old. Studies have shown that early detection and treatment of breast cancer increases the chances of survival significantly. They also demonstrated that detecting small lesions early improves forecasting and results in a significant reduction in death cases. The most effective screening diagnostic technique in this case is mammography. However, interpretation of mammograms is difficult due to small differences in tissue densities within mammographic images. This is especially true for dense breasts, and this study suggests that screening mammography is more effective in fatty breast tissue than in dense breast tissue. This study focuses on breast cancer diagnosis as well as identifying risk factors and their assessments of breast cancer as well as premature detection of breast cancer by analyzing 3D MRI mammography methods and segmentation of mammographic images using machine learning.