Reducing bias and increasing utility by federated generative modeling of medical images using a centralized adversary
Authors:
Preprint
Abstract
We introduce FELICIA (FEderated LearnIng with a CentralIzed Adversary) a generative mechanism enabling collaborative learning. In particular, we show how a data owner with limited and biased data could benefit from other data owners while keeping data from all the sources private. This is a common scenario in medical image analysis where privacy legislation prevents data from being shared outside local premises. FELICIA works for a large family of Generative Adversarial Networks (GAN) architectures including vanilla and conditional GANs as demonstrated in this work. We show that by using the FELICIA mechanism, a data owner with limited image samples can generate high-quality synthetic images with high utility while neither data owners has to provide access to its data. The sharing happens solely through a central discriminator that has access limited to synthetic data. Here, utility is defined as classification performance on a real test set. We demonstrate these benefits on several realistic healthcare scenarions using benchmark image datasets (MNIST, CIFAR-10) as well as on medical images for the task of skin lesion classification. With multiple experiments, we show that even in the worst cases, combining FELICIA with real data gracefully achieves performance on par with real data while most results significantly improves the utility.Keywords
All Related Versions
This publication has 8 references indexed in Scilit:
- Deep learning-enabled medical computer visionnpj Digital Medicine, 2021
- Detect and correct bias in multi-site neuroimaging datasetsMedical Image Analysis, 2021
- Private data sharing between decentralized users through the privGAN architecture2020
- The future of digital health with federated learningnpj Digital Medicine, 2020
- Synthesis of diagnostic quality cancer pathology images by generative adversarial networksThe Journal of Pathology, 2020
- LOGAN: Membership Inference Attacks Against Generative ModelsProceedings on Privacy Enhancing Technologies, 2018
- The HAM10000 dataset, a large collection of multi-source dermatoscopic images of common pigmented skin lesionsScientific Data, 2018
- The Algorithmic Foundations of Differential Privacy2013