Privacy-Preserving Chest X-ray Report Generation via Multimodal Federated Learning with ViT and GPT-2
This addresses privacy concerns in medical AI by enabling collaborative training without sharing sensitive data, though it is incremental as it applies existing FL methods to a specific domain.
The study tackled automated radiology report generation from chest X-ray images by proposing a multimodal federated learning framework using ViT and GPT-2, which matched or surpassed centralized models in performance across metrics like ROUGE and BLEU while preserving patient privacy.
The automated generation of radiology reports from chest X-ray images holds significant promise in enhancing diagnostic workflows while preserving patient privacy. Traditional centralized approaches often require sensitive data transfer, posing privacy concerns. To address this, the study proposes a Multimodal Federated Learning framework for chest X-ray report generation using the IU-Xray dataset. The system utilizes a Vision Transformer (ViT) as the encoder and GPT-2 as the report generator, enabling decentralized training without sharing raw data. Three Federated Learning (FL) aggregation strategies: FedAvg, Krum Aggregation and a novel Loss-aware Federated Averaging (L-FedAvg) were evaluated. Among these, Krum Aggregation demonstrated superior performance across lexical and semantic evaluation metrics such as ROUGE, BLEU, BERTScore and RaTEScore. The results show that FL can match or surpass centralized models in generating clinically relevant and semantically rich radiology reports. This lightweight and privacy-preserving framework paves the way for collaborative medical AI development without compromising data confidentiality.