Validation of eleven federated learning strategies for multi-contrast image-to-image MRI data synthesis from heterogeneous sources

Abstract

Deep learning (DL)-based image synthesis has recently gained enormous interest in medical imaging, allowing for generating multi-contrast data and therefore, the recovery of missing samples from interrupted or artefact-distorted acquisitions. However, the accuracy of DL models heavily relies on the representativeness of the training datasets naturally characterized by their distributions, experimental setups or preprocessing schemes. These complicate generalizing DL models across multi-site heterogeneous datasets while maintaining the confidentiality of the data. One of the possible solutions is to employ federated learning (FL), which enables the collaborative training of a DL model in a decentralized manner, demanding the involved sites to share only the characteristics of the models without transferring their sensitive medical data. The paper presents a DL-based magnetic resonance (MR) data translation in a FL way. We introduce a new aggregation strategy called FedBAdam that couples two methods with complementary strengths by incorporating momentum in the aggregation scheme and skipping the batch normalization layers. The work comprehensively validates 11 FL-based strategies for an image-to-image multi-contrast MR translation, considering healthy and tumorous brain scans from five different institutions. Our study has revealed that the FedBAdam achieves superior results in terms of mean squared error and structural similarity index compared with standard FL-based aggregation techniques, such as FedAvg or FedProx, and is on par with or superior to personalised methods, while exhibiting more stable convergence in a multi-site, multi-vendor, heterogeneous environment. The FedBAdam has prevented the overfitting of the model and gradually reached the optimal model parameters, exhibiting no oscillations.