Unleashing the Power of Deep Neural Networks for Breast Cancer Diagnosis

Breast cancer occurs when cells or tissues of the breast grow abnormally. All over the world, In the United States, cancer is one of the leading causes of death, and among women, The most common type of cancer. According to the American Cancer Society, more than 266,000 women will be diagnosed with invasive breast cancer in 2020. The disease can also affect men. This paper proposes a method that relies on deep learning and convolutional neural networks is proposed for the classification of breast tissue images. Mammogram classification can help doctors detect cancer early. As part of this study,a convolutional neural network was trained (AlexNet and VGG16) using breast cancer images from the dataset for invasive ductal carcinoma (IDC), the most common and aggressive form of breast cancer. According to the results of training the VGG16 network, disease detection of 88.95%. AlexNet excelled in accuracy, with an accuracy of 90.06%. The purpose of this study is to propose and explore a method based on deep learning and convolutional neural networks for classification of breast tissue images. The primary goal is to assist clinicians in early detection of cancer by accurately identifying invasive ductal carcinoma (IDC), using trained convolutional neural networks (AlexNet and VGG16).