Higher-Order Domain Generalization in Magnetic Resonance-Based Assessment of Alzheimer's Disease

2026-01-04

arXiv.org

AI Summary

This work addresses the performance degradation of Alzheimer’s disease (AD) diagnostic models on structural MRI (sMRI) data due to domain shift when applied to unseen datasets. To mitigate this issue, the authors propose the Extended MixStyle framework, which, for the first time, incorporates higher-order statistical moments—specifically skewness and kurtosis—into single-domain generalization. By blending these higher-order feature moments, the method simulates diverse distributional shifts, thereby enhancing model robustness to unseen domains. Integrated within a deep learning architecture and combined with the proposed data augmentation strategy, the model achieves a 2.4 percentage point improvement in average macro F1 score across three unseen cohorts in the three-class classification task distinguishing normal controls (NC), mild cognitive impairment (MCI), and AD, significantly outperforming existing single-domain generalization baselines.

Technology Category

• Machine Learning: Transfer, Domain Adaptation, Multi-Task Learning
• Computer Vision: Adversarial Attacks & Robustness
• Multiagent Systems: Adversarial Agents

Application Category

• Search and Retrieval-Augmented AI: Vertical and domain-specific search
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for heterogeneous, signed, attributed, multi-relational, temporal, higher-order, and annotated Web-related graphs
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

Despite progress in deep learning for Alzheimer's disease (AD) diagnostics, models trained on structural magnetic resonance imaging (sMRI) often do not perform well when applied to new cohorts due to domain shifts from varying scanners, protocols and patient demographics. AD, the primary driver of dementia, manifests through progressive cognitive and neuroanatomical changes like atrophy and ventricular expansion, making robust, generalizable classification essential for real-world use. While convolutional neural networks and transformers have advanced feature extraction via attention and fusion techniques, single-domain generalization (SDG) remains underexplored yet critical, given the fragmented nature of AD datasets. To bridge this gap, we introduce Extended MixStyle (EM), a framework for blending higher-order feature moments (skewness and kurtosis) to mimic diverse distributional variations. Trained on sMRI data from the National Alzheimer's Coordinating Center (NACC; n=4,647) to differentiate persons with normal cognition (NC) from those with mild cognitive impairment (MCI) or AD and tested on three unseen cohorts (total n=3,126), EM yields enhanced cross-domain performance, improving macro-F1 on average by 2.4 percentage points over state-of-the-art SDG benchmarks, underscoring its promise for invariant, reliable AD detection in heterogeneous real-world settings. The source code will be made available upon acceptance at https://github.com/zobia111/Extended-Mixstyle.

Problem

• domain generalization
• Alzheimer's disease
• structural MRI
• domain shift
• cross-domain performance

Innovation

• Extended MixStyle
• higher-order moments
• single-domain generalization
• Alzheimer's disease
• domain shift