Does pre-training on brain-related tasks results in better deep-learning-based brain age biomarkers?

TL;DR

This study explores whether pre-training deep learning models on brain-related tasks enhances brain age prediction accuracy and biomarker reliability, finding that improved prediction does not necessarily lead to better biomarkers.

Contribution

The paper introduces pre-training on brain-related tasks for brain age prediction models, achieving state-of-the-art results and providing insights into biomarker reliability.

Findings

Pre-training on brain tasks improves age prediction accuracy.

Better prediction models do not always produce more reliable biomarkers.

State-of-the-art results achieved on ADNI data.

Abstract

Brain age prediction using neuroimaging data has shown great potential as an indicator of overall brain health and successful aging, as well as a disease biomarker. Deep learning models have been established as reliable and efficient brain age estimators, being trained to predict the chronological age of healthy subjects. In this paper, we investigate the impact of a pre-training step on deep learning models for brain age prediction. More precisely, instead of the common approach of pre-training on natural imaging classification, we propose pre-training the models on brain-related tasks, which led to state-of-the-art results in our experiments on ADNI data. Furthermore, we validate the resulting brain age biomarker on images of patients with mild cognitive impairment and Alzheimer's disease. Interestingly, our results indicate that better-performing deep learning models in terms of brain age prediction on healthy patients do not result in more reliable biomarkers.