Edinburgh Research Explorer

Signed Laplacian Deep Learning with Adversarial Augmentation for Improved Mammography Diagnosis

Research output: Contribution to conferencePaper

Related Edinburgh Organisations

Documents

  • Download as Adobe PDF

    2.66 MB, PDF document

Original languageUndefined/Unknown
Publication statusPublished - 30 Jun 2019
Event22nd International Conference on Medical Image Computing and Computer Assisted Intervention - InterContinental Shenzhen, Shenzhen, China
Duration: 13 Oct 201917 Oct 2019
Conference number: 22
https://www.miccai2019.org/

Conference

Conference22nd International Conference on Medical Image Computing and Computer Assisted Intervention
Abbreviated titleMICCAI 2019
CountryChina
CityShenzhen
Period13/10/1917/10/19
Internet address

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.

    Research areas

  • eess.IV, cs.LG, stat.ML

???studenttheses-relations???

  • Deep Learning for Computer Aided Diagnosis in Mammography

    Student thesis: Doctoral Thesis

ID: 114917505