Layered Deep learning for Improved Breast Cancer Detection

Abstract

Breast cancer is the most serious disease affecting women around the world, and is the fifth leading cause of death in women. The contribution of this work is to help facilitate early diagnosis of the breast cancer. The introduction section highlights the importance of the problem, and gives insight to literature review, where existing research works conducted in this direction are surveyed. The proposed approach presents related dataset chosen to evaluate the approach investigated in this work. A layered deep learning model is investigated, which is trained using a dataset. Several evaluation metrics related to machine learning are employed to evaluate effectiveness of the proposed approach. The results suggest that accuracy of the proposed model is above 96% for both training and validation of the model. The training and validation results are discussed, and sample detection and classification results are presented.