End-to-end Training for Whole Image Breast Cancer Diagnosis using An All Convolutional Design

Li Shen

Published 2017-08-30Version 1

We develop an end-to-end training algorithm for whole-image breast cancer diagnosis based on mammograms. It has the advantage of training a deep learning model without relying on cancer lesion annotations. Our approach is implemented using an all convolutional design that is simple yet provides superior performance in comparison with the previous methods. With modest model averaging, our best models achieve an AUC score of 0.91 on the DDSM data and 0.96 on the INbreast data. We also demonstrate that a trained model can be easily transferred from one database to another with different color profiles using only a small amount of training data. Code and model availability: https://github.com/lishen/end2end-all-conv