FedOnco-Bench: A Reproducible Benchmark for Privacy-Aware Federated Tumor Segmentation with Synthetic CT Data

TL;DR

FedOnco-Bench introduces a standardized benchmark for evaluating privacy-aware federated learning methods in tumor segmentation using synthetic CT data, highlighting privacy-utility trade-offs.

Contribution

It provides a reproducible, open-source platform for benchmarking federated learning approaches in medical imaging with a focus on privacy preservation.

Findings

FedAvg achieves high segmentation accuracy but with higher privacy leakage.

DP-SGD enhances privacy at the expense of some accuracy.

FedProx and FedBN perform well under data heterogeneity.

Abstract

Federated Learning (FL) allows multiple institutions to cooperatively train machine learning models while retaining sensitive data at the source, which has great utility in privacy-sensitive environments. However, FL systems remain vulnerable to membership-inference attacks and data heterogeneity. This paper presents FedOnco-Bench, a reproducible benchmark for privacy-aware FL using synthetic oncologic CT scans with tumor annotations. It evaluates segmentation performance and privacy leakage across FL methods: FedAvg, FedProx, FedBN, and FedAvg with DP-SGD. Results show a distinct trade-off between privacy and utility: FedAvg is high performance (Dice around 0.85) with more privacy leakage (attack AUC about 0.72), while DP-SGD provides a higher level of privacy (AUC around 0.25) at the cost of accuracy (Dice about 0.79). FedProx and FedBN offer balanced performance under heterogeneous data, especially with non-identical distributed client data. FedOnco-Bench serves as a standardized, open-source platform for benchmarking and developing privacy-preserving FL methods for medical image segmentation.