Classification of breast cancer images using new transfer learning techniques

Abstract

Breast cancer is one of the most common types of cancer among women, which requires building smart systems to help doctors and early detection of cancer. Deep learning applications have emerged in many fields, especially in health care, but there are still some limitations in this technique, such as the small number of classified medical images needed to train deep learning models, so this paper aims to find a solution to this problem by using new techniques for transfer learning by taking advantage of the presence of unclassified medical images of the same disease. The proposed approach was applied to the modified Xception model to classify the histological images of breast cancer in the ICIAR 2018 dataset into four classes: invasive carcinoma, in situ carcinoma, benign tumor, and normal tissue. The proposed approach has obtained 99%,  99.003%,  98.995%,  99%, 98.55%, and  99.14% for accuracy, precision, recall, F1-score, sensitivity, and specificity respectively. Our work has been compared with previous works.