Convolutional Capsule Network for Classification of Breast Cancer Histology Images

Automatization of the diagnosis of any kind of disease is of great importance and its gaining speed as more and more deep learning solutions are applied to different problems. One of such computer-aided systems could be a decision support tool able to accurately differentiate between different types of breast cancer histological images - normal tissue or carcinoma (benign, in situ or invasive). In this paper authors present a deep learning solution, based on convolutional capsule network, for classification of four types of images of breast tissue biopsy when hematoxylin and eosin staining is applied. The cross-validation accuracy, averaged over four classes, was achieved to be 87% with equally high sensitivity.