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

TL;DR

This paper introduces Extended MixStyle, a novel method that uses higher-order feature moments to improve the domain generalization of MRI-based Alzheimer's disease classification models across diverse datasets.

Contribution

We propose Extended MixStyle, a new domain generalization framework leveraging skewness and kurtosis to enhance model robustness across different MRI cohorts.

Findings

Extended MixStyle improves cross-domain macro-F1 by 2.4 percentage points.

The method outperforms existing state-of-the-art SDG benchmarks.

Enhanced robustness demonstrated on three unseen cohorts.

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.