Summary

This article presents a computer-aided diagnosis method for breast cancer classification using deep neural networks and transfer learning. Breast cancer classification in binary and multi-class is performed using pre-trained DNN’s: ResNet 18, ShuffleNet, and Inception-V3Net with transfer learning. BreakHis publicly available dataset was used in this regard for the classification task of breast cancer images. Our proposed method provides the maximum average accuracy for binary classification of benign or malignant cancer cases as 99.7%, 97.66%, and 96.94% for ResNet, InceptionV3Net, and ShuffleNet, respectively. Average accuracies for multi-class classification were 97.81%, 96.07% and 95.79% for ResNet, Inception-V3Net, and ShuffleNet, respectively.