Enhancing Reliability of MRI-based Brain Morphometry by Synthetic MPRAGE Generation

Motivation: Brain morphometry is increasingly recognized as potential biomarker for tracking neurodegenerative disease progression. However, variations in MRI acquisition parameters, common in clinical practice, compromise the reliability of morphometric measures. Goal(s): To achieve contrast-invariant morphometry across MPRAGE images with varying grey/white matter contrasts. Approach: We retrained a deep-learning-based segmentation tool (DL+DiReCT) by modeling MPRAGE contrast variations as a function of MRI parameters (TI and TR). Cortical thickness variability was assessed before and after retraining. Results: The retrained model improved contrast invariance, reducing the contrast-related cortical thickness dependence from 5% to 2% across clinically relevant parameters. Impact: We created a contrast-invariant segmentation tool that improves brain morphometry accuracy across variable MRI settings, enabling more reliable monitoring of neurodegenerative disease progression. This tool improves assessment accuracy across longitudinal and multi-parameter MRI acquisitions common in clinical practice.