Reducing bias and increasing utility by federated generative modeling of medical images using a centralized adversary
This addresses privacy concerns in medical image analysis by allowing data owners to benefit from others' data while keeping it private, though it is incremental as it builds on existing GAN architectures.
The paper tackles the problem of limited and biased medical image data by introducing FELICIA, a federated generative modeling method that enables collaborative learning without sharing private data, resulting in high-quality synthetic images that achieve performance on par with or better than real data in classification tasks.
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.