MuCALD-SplitFed: Causal-Latent Diffusion for Privacy-Preserving Multi-Task Split-Federated Medical Image Segmentation

TL;DR

MuCALD-SplitFed introduces a multi-task split federated learning framework with causal latent diffusion, enhancing medical image segmentation accuracy and privacy protection across decentralized clinical settings.

Contribution

It integrates causal representation learning and latent diffusion into multi-task SplitFed, improving convergence, segmentation performance, and privacy in federated medical imaging.

Findings

MuCALD-SplitFed outperforms baseline SplitFed in convergence and segmentation accuracy.

The approach reduces information leakage and mitigates privacy attacks.

It surpasses state-of-the-art personalized and multi-task federated learning methods.

Abstract

Federated Learning enables decentralized training by aggregating model updates across clients without sharing raw data, while Split Federated Learning further partitions the model between clients and a server to reduce computation and communication at the client side. However, decentralized medical institutions rarely operate on a single shared task, making standard Federated and SplitFed collaborations poorly aligned with real clinical workflows. Multi-task FL extends these frameworks by allowing clients to handle different tasks, but often introduces instability and privacy vulnerabilities. This study proposes \textbf{MuCALD-SplitFed}, a multi-task SplitFed framework that integrates causal representation learning and latent diffusion. Experiments show MuCALD-SplitFed consistently improves segmentation, while baseline SplitFed fails to converge. The proposed approach further reduces information leakage at split points, mitigating reconstruction-based and membership inference attacks. Additionally, MuCALD SplitFed outperforms state-of-the-art personalized FL and multi-task FL approaches. The code repository is: https://github.com/ChamaniS/MuCALD_SplitFed.