Federated Learning for MRI-based BrainAGE: a multicenter study on post-stroke functional outcome prediction

2025-06-18

AI Summary

Accurately estimating brain age gap estimation (BrainAGE) from FLAIR-MRI scans in ischemic stroke patients while preserving data privacy across multiple institutions remains challenging due to data heterogeneity and regulatory constraints. Method: We developed a privacy-preserving federated learning (FL) framework using FedAvg with a 3D ResNet architecture, trained on multi-center FLAIR-MRI data from 16 hospitals without sharing raw images. Contribution/Results: This is the first systematic validation of FL-based BrainAGE modeling in a stroke cohort. The federated model significantly outperformed single-site models in accuracy. Elevated BrainAGE was significantly associated with diabetes (p < 0.05) and independently predicted poor 3-month functional outcomes after adjusting for confounders (OR = 1.32, p < 0.01). These findings demonstrate the feasibility and clinical relevance of decentralized BrainAGE as a neuroimaging biomarker for stroke prognosis.

Technology Category

• Machine Learning: Privacy
• Natural Language Processing: Language Grounding & Multi-modal NLP
• Computer Vision: Bias, Fairness & Privacy

Application Category

• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Responsible Web: Data and user privacy-enhancing technologies for the Web
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG

Abstract

$ extbf{Objective:}$ Brain-predicted age difference (BrainAGE) is a neuroimaging biomarker reflecting brain health. However, training robust BrainAGE models requires large datasets, often restricted by privacy concerns. This study evaluates the performance of federated learning (FL) for BrainAGE estimation in ischemic stroke patients treated with mechanical thrombectomy, and investigates its association with clinical phenotypes and functional outcomes. $ extbf{Methods:}$ We used FLAIR brain images from 1674 stroke patients across 16 hospital centers. We implemented standard machine learning and deep learning models for BrainAGE estimates under three data management strategies: centralized learning (pooled data), FL (local training at each site), and single-site learning. We reported prediction errors and examined associations between BrainAGE and vascular risk factors (e.g., diabetes mellitus, hypertension, smoking), as well as functional outcomes at three months post-stroke. Logistic regression evaluated BrainAGE's predictive value for these outcomes, adjusting for age, sex, vascular risk factors, stroke severity, time between MRI and arterial puncture, prior intravenous thrombolysis, and recanalisation outcome. $ extbf{Results:}$ While centralized learning yielded the most accurate predictions, FL consistently outperformed single-site models. BrainAGE was significantly higher in patients with diabetes mellitus across all models. Comparisons between patients with good and poor functional outcomes, and multivariate predictions of these outcomes showed the significance of the association between BrainAGE and post-stroke recovery. $ extbf{Conclusion:}$ FL enables accurate age predictions without data centralization. The strong association between BrainAGE, vascular risk factors, and post-stroke recovery highlights its potential for prognostic modeling in stroke care.

Problem

• Evaluating federated learning for BrainAGE estimation in stroke patients
• Assessing BrainAGE's link to vascular risks and functional outcomes
• Comparing centralized, federated, and single-site learning strategies

Innovation

• Federated learning for decentralized BrainAGE estimation
• Multicenter MRI data analysis without data pooling
• Association of BrainAGE with stroke outcomes