Explainable Brain Age Gap Prediction in Neurodegenerative Conditions using coVariance Neural Networks

TL;DR

This paper introduces an explainable neural network approach using coVariance Neural Networks to predict brain age gap in neurodegenerative diseases, providing interpretable biomarkers linked to specific anatomical patterns.

Contribution

The study applies VNNs to neuroimaging data, demonstrating their interpretability and ability to distinguish brain age gap patterns across different neurodegenerative conditions.

Findings

Distinct anatomical patterns for brain age gap in Alzheimer's, FTD, and Parkinsonian disorders.

VNN leverages eigenspectrum of covariance matrix for explainability.

VNN provides interpretable biomarkers linked to neurodegeneration.

Abstract

Brain age is the estimate of biological age derived from neuroimaging datasets using machine learning algorithms. Increasing \textit{brain age gap} characterized by an elevated brain age relative to the chronological age can reflect increased vulnerability to neurodegeneration and cognitive decline. Hence, brain age gap is a promising biomarker for monitoring brain health. However, black-box machine learning approaches to brain age gap prediction have limited practical utility. Recent studies on coVariance neural networks (VNN) have proposed a relatively transparent deep learning pipeline for neuroimaging data analyses, which possesses two key features: (i) inherent \textit{anatomically interpretablity} of derived biomarkers; and (ii) a methodologically interpretable perspective based on \textit{linkage with eigenvectors of anatomic covariance matrix}. In this paper, we apply the VNN-based approach to study brain age gap using cortical thickness features for various prevalent neurodegenerative conditions. Our results reveal distinct anatomic patterns for brain age gap in Alzheimer's disease, frontotemporal dementia, and atypical Parkinsonian disorders. Furthermore, we demonstrate that the distinct anatomic patterns of brain age gap are linked with the differences in how VNN leverages the eigenspectrum of the anatomic covariance matrix, thus lending explainability to the reported results.