Breast Cancer Assessment Using a HybridANN-CNN Approach
Y. Venkat Vivek, K. Umamaheswari, T. Venkata Sai Sriharika, Riya T. Nikesh, G. Rupesh · 2024
Breast cancer is the most prevalent kind of cancer that affects women globally. Effective treatment requires early detection, which will reduce the risk factor. In the present era of healthcare technology advancements, significant progress has been made in the timely identification and avoidance of breast cancer. Mammography is a substantial technique for screening breast cancer, but it has limitations, including notable inter-observer variability and false-positive rates. Recent advancements in artificial neural networks (ANNs) and convolutional neural networks (CNNs) have demonstrated encouraging outcomes, enhancing the accuracy and effectiveness of breast cancer detection. The paper presents an ANN-CNN method for early breast cancer identification. Using a publicly available dataset, we train the machine to categorize breast histology images as cancerous or not. Our approach is evaluated based on crucial metrics, including accuracy, support, f1-score, and recall, all of which achieve nearly 90% or higher values.