Multimodal normative modeling in Alzheimers Disease with introspective variational autoencoders

2026-02-08

AI Summary

This work addresses the limitations of existing variational autoencoder-based multimodal normative modeling in Alzheimer’s disease research, which struggles to accurately fit the healthy reference distribution and suffers from insufficient information integration and false-positive bias under conventional posterior fusion strategies. To overcome these issues, the authors propose mmSIVAE, a novel model that integrates a soft introspective variational autoencoder with a Mixture-of-Product-of-Experts (MOPOE) fusion mechanism. This approach simultaneously computes individual deviation scores from the healthy distribution in both latent and feature spaces and enhances regional interpretability through statistical significance mapping. Experiments on ADNI data demonstrate that mmSIVAE achieves superior reconstruction performance and yields deviation scores with greater discriminative power and higher likelihood ratios, effectively distinguishing between control subjects and individuals across the Alzheimer’s disease spectrum while accurately revealing disease-related regional abnormality patterns.

Technology Category

• Computer Vision: Multi-modal Vision
• Machine Learning: Multimodal Learning
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Semantics and Knowledge: Methods, algorithms and applications for the development of semantic models, knowledge graphs and other forms of structured data models with machine-interpretable semantics

Abstract

Normative modeling learns a healthy reference distribution and quantifies subject-specific deviations to capture heterogeneous disease effects. In Alzheimers disease (AD), multimodal neuroimaging offers complementary signals but VAE-based normative models often (i) fit the healthy reference distribution imperfectly, inflating false positives, and (ii) use posterior aggregation (e.g., PoE/MoE) that can yield weak multimodal fusion in the shared latent space. We propose mmSIVAE, a multimodal soft-introspective variational autoencoder combined with Mixture-of-Product-of-Experts (MOPOE) aggregation to improve reference fidelity and multimodal integration. We compute deviation scores in latent space and feature space as distances from the learned healthy distributions, and map statistically significant latent deviations to regional abnormalities for interpretability. On ADNI MRI regional volumes and amyloid PET SUVR, mmSIVAE improves reconstruction on held-out controls and produces more discriminative deviation scores for outlier detection than VAE baselines, with higher likelihood ratios and clearer separation between control and AD-spectrum cohorts. Deviation maps highlight region-level patterns aligned with established AD-related changes. More broadly, our results highlight the importance of training objectives that prioritize reference-distribution fidelity and robust multimodal posterior aggregation for normative modeling, with implications for deviation-based analysis across multimodal clinical data.

Problem

• normative modeling
• Alzheimer's disease
• multimodal neuroimaging
• variational autoencoder
• posterior aggregation

Innovation

• normative modeling
• variational autoencoder
• multimodal fusion
• Alzheimer's disease
• MOPOE