Scale-dependent brain age with higher-order statisticsfrom structural magnetic resonance imaging

Abstract

Inferring chronological age from magnetic resonance imaging (MRI) brain data has become a valuable tool for the early detection of neurodegenerative diseases. We present a method inspired by cosmological techniques for analyzing galaxy surveys, utilizing higher-order summary statistics with multivariate two- and three-point analyses in 3D Fourier space. This method identifies outliers while offering physiological interpretability, allowing the detection of scales where brain anatomy differs across age groups and providing insights into brain aging processes. Similarly to the evolution of cosmic structures, the brain structure also evolves naturally but displays contrasting behaviors at different scales. On larger scales, structure loss occurs with age, possibly due to ventricular expansion, while smaller scales show increased structure, likely related to decreased cortical thickness and gray/white matter volume. Using MRI data from the OASIS-3 database for the complete sample of 864 sessions (reduced sample: 827 sessions), our method predicts chronological age with a Mean Absolute Error (MAE) of ~3.8 years (~3.6 years) for individuals aged ~40-100 (50-85), while providing information as a function of scale. A neural density posterior estimation shows that the 1-sigma uncertainty for each individual varies between ~3 and 7 years, suggesting that, beyond sample variance, complex genetic or lifestyle-related factors may influence brain aging. Applying this method to an independent database, Cam-CAN, validates our analysis, yielding a MAE of ~3.4 for the age range from 18 to 88 years. This work demonstrates the utility of interdisciplinary research, bridging cosmological methods and neuroscience.