UG-FedDA: Uncertainty-Guided Federated Domain Adaptation for Multi-Center Alzheimer's Disease Detection

2025-12-05

AI Summary

Existing multi-center Alzheimer’s disease (AD) classification methods often neglect site-specific heterogeneity and lack uncertainty quantification, compromising robustness and clinical applicability. To address these limitations, we propose a novel privacy-preserving, decentralized diagnostic framework integrating uncertainty-aware quantification with federated domain adaptation. Our method innovatively incorporates sample-level uncertainty into the federated feature alignment process, dynamically down-weighting high-uncertainty samples to mitigate distribution shift across sites. Furthermore, we employ a self-attention-based Transformer to extract features from multiple anatomical templates (ROIs), enabling cross-center knowledge transfer without sharing raw data. Evaluated on three independent cohorts—ADNI, AIBL, and OASIS—the framework achieves up to 90.54% accuracy in NC vs. AD binary classification. It significantly improves cross-domain generalization, stability under data heterogeneity, and clinical interpretability—key requirements for real-world deployment.

Technology Category

• Machine Learning: Transfer, Domain Adaptation, Multi-Task Learning
• Computer Vision: Adversarial Attacks & Robustness
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning

Application Category

• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Responsible Web: Algorithmic accountability and transparency on the web
• Security and Privacy: Data transparency and provenance

Abstract

Alzheimer's disease (AD) is an irreversible neurodegenerative disorder, and early diagnosis is critical for timely intervention. However, most existing classification frameworks face challenges in multicenter studies, as they often neglect inter-site heterogeneity and lack mechanisms to quantify uncertainty, which limits their robustness and clinical applicability. To address these issues, we proposed Uncertainty-Guided Federated Domain Adaptation (UG-FedDA), a novel multicenter AD classification framework that integrates uncertainty quantification (UQ) with federated domain adaptation to handle cross-site structure magnetic resonance imaging (MRI) heterogeneity under privacy constraints. Our approach extracts multi-template region-of-interest (RoI) features using a self-attention transformer, capturing both regional representations and their interactions. UQ is integrated to guide feature alignment, mitigating source-target distribution shifts by down-weighting uncertain samples. Experiments are conducted on three public datasets: the Alzheimer's Disease Neuroimaging Initiative (ADNI), the Australian Imaging, Biomarkers and Lifestyle study (AIBL), and the Open Access Series of Imaging Studies (OASIS). UG-FedDA achieved consistent cross-domain improvements in accuracy, sensitivity, and area under the ROC curve across three classification tasks: AD vs. normal controls (NC), mild cognitive impairment (MCI) vs. AD, and NC vs. MCI. For NC vs. AD, UG-FedDA achieves accuracies of 90.54%, 89.04%, and 77.78% on ADNI, AIBL and OASIS datasets, respectively. For MCI vs. AD, accuracies are 80.20% (ADNI), 71.91% (AIBL), and 79.73% (OASIS). For NC vs. MCI, results are 76.87% (ADNI), 73.91% (AIBL), and 83.73% (OASIS). These results demonstrate that the proposed framework not only adapts efficiently across multiple sites but also preserves strict privacy.

Problem

• Addresses cross-site MRI heterogeneity in Alzheimer's disease detection
• Integrates uncertainty quantification to guide federated domain adaptation
• Enhances classification robustness and privacy across multiple clinical datasets

Innovation

• Integrates uncertainty quantification with federated domain adaptation
• Uses self-attention transformer to extract multi-template RoI features
• Down-weights uncertain samples to mitigate source-target distribution shifts