Mining Multi-Center Heterogeneous Medical Data with Distributed Synthetic Learning

Abstract Overcoming barriers of multi-center data analysis is challenging due to privacy protection and data heterogeneity in the healthcare system. In this study, we propose Distributed Synthetic Learning (DSL) architecture to learn across multi-medical centers without leaking sensitive personal information. DSL emphasizes the building of a homogeneous data center with entirely synthetic medical images via a form of GAN-based synthetic learning. In particular, DSL architecture is extensible with three key variances: multi-modality learning, missing modality completion learning, and continuous learning over time. We systematically evaluate the performance of DSL on different medical applications using cardiac computed tomography angiography (CTA), brain tumor MRI, and histopathology nuclei datasets. Extensive experiments demonstrate the superior performance of DSL as a high-quality synthetic medical image provider for various image tasks from an ideal synthetic image quality metric called Dist-FID. We show that our model can be adapted to heterogeneous data and remarkably outperforms the real misaligned modalities segmentation model by 55% and the temporal datasets segmentation model by 8%. The proposed DSL framework demonstrates its potential for integrating multi-center heterogeneous data to support downstream clinical decision making.