Similarity Weighted Aggregation with Global Differential Privacy for Federated Brain Lesion Segmentation
Muhammad Irfan Khan, Eero Lehtonen, Joni Obradovic, Elina Kontio, Esa Alhoniemi, Suleiman A. Khan, Mojtaba Jafaritadi
cs.AI, cs.CR, cs.CV
Submitted: 2026-08-01
License: http://creativecommons.org/licenses/by/4.0/
The gist: Federated Learning (FL) enables collaborative training of machine learning models across multiple institutions without sharing sensitive data, making it particularly suitable for medical imaging
Terminology
Abstract
Federated Learning (FL) enables collaborative training of machine learning models across multiple institutions without sharing sensitive data, making it particularly suitable for medical imaging applications. However, heterogeneous data distributions across institutions and potential information leakage through model updates remain important challenges. In this work, we propose DP-SimAgg, a privacy-preserving federated learning framework that integrates similarity-weighted aggregation with a server-side differential privacy mechanism. The proposed method applies L2 clipping to bound collaborator updates, computes similarity-based aggregation weights to mitigate the effects of non-IID data distributions, and injects calibrated Gaussian noise at the central server, providing per-round privacy guarantees under the assumed sensitivity bound. The framework is implemented using Intel's OpenFL platform and evaluated on the FeTS 2022 dataset consisting of 1251 multi-modal MRI scans for brain tumor segmentation. Experimental results demonstrate that DP-SimAgg maintains competitive segmentation performance while providing privacy protection. Under a strict per-round privacy budget (epsilon = 1, cumulative epsilon total = 20 over 20 rounds), the method achieves Dice scores of 0.6357, 0.5305, and 0.5274 for the enhancing tumor (ET), tumor core (TC), and whole tumor (WT) regions, respectively. With a more relaxed per-round budget (epsilon = 10, cumulative epsilon total = 200), performance approaches that of the non-private baseline while incorporating a central Gaussian mechanism with per-round (epsilon, delta)-DP accounting under the assumed sensitivity bound. These results highlight the potential of DP-SimAgg for enabling privacy-preserving collaborative learning in medical imaging applications.
Sources
- Federated Learning with Matched Averaging
- Regularized Weight Aggregation in Networked Federated Learning for Glioblastoma Segmentation
- Federated Learning with Non-IID Data
- Inverting Gradients -- How easy is it to break privacy in federated learning?
- Privacy Preservation in Federated Learning: An insightful survey from the GDPR Perspective
- Election of Collaborators via Reinforcement Learning for Federated Brain Tumor Segmentation
- Recommender Engine Driven Client Selection in Federated Brain Tumor Segmentation
- Biomedical image analysis competitions: The state of current participation practice
- PrivacyFL: A simulator for privacy-preserving and secure federated learning
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems