Age Prediction Performance Varies Across Deep, Superficial, and Cerebellar White Matter Connections

TL;DR

This study develops a deep learning model to predict age from white matter tractography, revealing that deep white matter connections are most informative for age estimation in young adults.

Contribution

It introduces a novel deep learning approach with specialized data augmentation and loss functions for white matter-based age prediction.

Findings

Deep white matter is most informative for age prediction.

The model achieves a mean absolute error of 2.59 years.

Thalamo-frontal and cerebellar tracts are highly predictive.

Abstract

The brain's white matter (WM) undergoes developmental and degenerative processes during the human lifespan. To investigate the relationship between WM anatomical regions and age, we study diffusion magnetic resonance imaging tractography that is finely parcellated into fiber clusters in the deep, superficial, and cerebellar WM. We propose a deep-learning-based age prediction model that leverages large convolutional kernels and inverted bottlenecks. We improve performance using novel discrete multi-faceted mix data augmentation and a novel prior-knowledge-based loss function that encourages age predictions in the expected range. We study a dataset of 965 healthy young adults (22-37 years) derived from the Human Connectome Project (HCP). Experimental results demonstrate that the proposed model achieves a mean absolute error of 2.59 years and outperforms compared methods. We find that the deep WM is the most informative for age prediction in this cohort, while the superficial WM is the least informative. Overall, the most predictive WM tracts are the thalamo-frontal tract from the deep WM and the intracerebellar input and Purkinje tract from the cerebellar WM.