A Deep CNN Technique for Detection of Breast Cancer Using Histopathology Images

Analysis of Histopathology images is an essential technique used for the detection process of breast cancer at an early stage. To enhance efficiency of BC i.e. Breast Cancer detection using histopathology images and also to reduce the burden from doctors, we design a deep learning methodology to diagnose cancer using medical images. Here in this paper, we use deep learning technology Convolutional Neural Network (CNN) for the recognition process. Features are extracted by using the CNN model called DenseNet-201. The classification task has two classes: Malignant and Benign. The dataset we used for classification process is BreakHis (Breast cancer Histopathological dataset) highest classification accuracy obtained is 95.58%, precision and recall are 0.90 and 0.99 respectively and F1-score obtained is 0.89. Experimental results and comparison of other related work explain quite reliable performance and the efficiency of proposed work.