English

Signed Laplacian Deep Learning with Adversarial Augmentation for Improved Mammography Diagnosis

Image and Video Processing 2019-09-17 v2 Machine Learning Machine Learning

Abstract

Computer-aided breast cancer diagnosis in mammography is limited by inadequate data and the similarity between benign and cancerous masses. To address this, we propose a signed graph regularized deep neural network with adversarial augmentation, named \textsc{DiagNet}. Firstly, we use adversarial learning to generate positive and negative mass-contained mammograms for each mass class. After that, a signed similarity graph is built upon the expanded data to further highlight the discrimination. Finally, a deep convolutional neural network is trained by jointly optimizing the signed graph regularization and classification loss. Experiments show that the \textsc{DiagNet} framework outperforms the state-of-the-art in breast mass diagnosis in mammography.

Keywords

Cite

@article{arxiv.1907.00300,
  title  = {Signed Laplacian Deep Learning with Adversarial Augmentation for Improved Mammography Diagnosis},
  author = {Heyi Li and Dongdong Chen and William H. Nailon and Mike E. Davies and David I. Laurenson},
  journal= {arXiv preprint arXiv:1907.00300},
  year   = {2019}
}

Comments

To appear in MICCAI October 2019

R2 v1 2026-06-23T10:07:41.984Z