Normative Modeling via Conditional Variational Autoencoder and Adversarial Learning to Identify Brain Dysfunction in Alzheimer's Disease

TL;DR

This paper introduces a novel normative modeling approach using a conditional variational autoencoder combined with adversarial learning to detect brain dysfunction in Alzheimer's Disease, improving sensitivity and group differentiation.

Contribution

The study develops a new ACVAE-based normative model that enhances generalization and sensitivity in identifying AD-related brain abnormalities compared to existing models.

Findings

Higher sensitivity to AD in deviation maps

Better differentiation between AD and healthy controls

Effective identification of brain regions associated with AD

Abstract

Normative modeling is an emerging and promising approach to effectively study disorder heterogeneity in individual participants. In this study, we propose a novel normative modeling method by combining conditional variational autoencoder with adversarial learning (ACVAE) to identify brain dysfunction in Alzheimer's Disease (AD). Specifically, we first train a conditional VAE on the healthy control (HC) group to create a normative model conditioned on covariates like age, gender and intracranial volume. Then we incorporate an adversarial training process to construct a discriminative feature space that can better generalize to unseen data. Finally, we compute deviations from the normal criterion at the patient level to determine which brain regions were associated with AD. Our experiments on OASIS-3 database show that the deviation maps generated by our model exhibit higher sensitivity to AD compared to other deep normative models, and are able to better identify differences between the AD and HC groups.