Automated diagnosis of breast cancer using multi-modal datasets: A deep convolution neural network based approach

This paper proposes a deep convolutional neural network (CNN) model for automated breast cancer classification from a different class of images, namely, mammograms and ultrasound. The model contains only five learnable layers: four convolutional layers and a fully connected layer. The model facilitates extracting prominent features automatically from the images with a smaller number of tunable parameters. Exhaustive simulation results on mammograms dataset, namely, MIAS, DDSM, and INbreast, as well as ultrasound datasets, namely, BUS-1 and BUS-2, depict that the suggested model outperforms the recent state-of-the-art schemes. Data augmentation technique has been employed to reduce overfitting and provide good generalization. The proposed CNN model achieves an accuracy of 96.55%, 90.68%, and 91.28% on MIAS, DDSM, and INbreast datasets, respectively. Similarly, the accuracies obtained are 100% and 89.73% on BUS-1 and BUS-2 datasets, respectively.