Multiclass Breast Cancer Classification Using Convolutional Neural Network

Nowadays, the quality of classification systems depends on the presentation of the dataset, a process that takes time to use in-depth knowledge to produce specific characteristics. Meanwhile, deep learning can extract features from a dataset, without having to design feature extractors. Convolutional Neural Network (CNN) is a special type of deep learning that achieves many accomplishments in speech recognition, image recognition and classification. In this paper, we use CNN to classify and recognize breast cancer images from public BreakHis dataset. This dataset includes 7,909 breast cancer (BC) histopathology images with four benign subclasses and four malignant subclasses. Our new task with this dataset is the automated multi-classification of these breast cancer images in eight classes, which can help reducing death rates and saving people's lives in the world. Our method based on the resizing original images for building CNN model and classifying breast cancer classes.