Deep learning-based model for breast cancer histopathology image classification

Breast cancer is the most commonly found cancer in India and the world. As per Global Cancer Observatory, in 2020 this cancer alone was the reason for the death of more than 6.8 million women throughout the world. There is no single cause of breast cancer but it could be a combination of one's environment, one's genes and the way one lives her life. These breast tumors can be benign (non- cancerous) or malignant (potentially-cancerous). Therefore, it becomes essential to identify them properly for appropriate treatment. Although histopathology images are used to judge breast cancer, there is always a chance of human error. This paper aims to simplify the breast cancer classification process for everyone. We propose a deep learning based Convolutional Neural Network model to detect and classify the breast cancer using histopathology images. This method uses pretrained neural network DenseNet-201 for features extraction from the images, which then used to predict for classification. Our model reached an accuracy of 97.05%.