Sharing Generative Models Instead of Private Data: A Simulation Study on Mammography Patch Classification

TL;DR

This study explores sharing trained generative models, specifically GANs, between clinical centres to enhance mammography classification performance without sharing sensitive patient data.

Contribution

It demonstrates that sharing GANs can effectively augment training data, improving classification accuracy across different models and addressing privacy concerns.

Findings

Shared GANs improve classification performance

GAN-based data augmentation increases dataset heterogeneity

Approach is viable as an alternative to data sharing

Abstract

Early detection of breast cancer in mammography screening via deep-learning based computer-aided detection systems shows promising potential in improving the curability and mortality rates of breast cancer. However, many clinical centres are restricted in the amount and heterogeneity of available data to train such models to (i) achieve promising performance and to (ii) generalise well across acquisition protocols and domains. As sharing data between centres is restricted due to patient privacy concerns, we propose a potential solution: sharing trained generative models between centres as substitute for real patient data. In this work, we use three well known mammography datasets to simulate three different centres, where one centre receives the trained generator of Generative Adversarial Networks (GANs) from the two remaining centres in order to augment the size and heterogeneity of its training dataset. We evaluate the utility of this approach on mammography patch classification on the test set of the GAN-receiving centre using two different classification models, (a) a convolutional neural network and (b) a transformer neural network. Our experiments demonstrate that shared GANs notably increase the performance of both transformer and convolutional classification models and highlight this approach as a viable alternative to inter-centre data sharing.