Prediction of brain maturity based on cortical thickness at different spatial resolutions

Area of Science:

• Neuroscience
• Developmental Biology
• Medical Imaging

Background:

• Cortical thickness changes correlate with cognitive development.
• Delays in these changes are linked to neurodevelopmental disorders, including ADHD.
• Accurate brain maturity estimation is crucial for assessing normal development.

Purpose of the Study:

• To develop a highly accurate predictive model for estimating chronological age using cortical thickness.
• To investigate the impact of spatial parcellation scale on age prediction accuracy.
• To identify brain regions most predictive of biological maturity.

Main Methods:

• Utilized a large longitudinal dataset (n=308) of children and adolescents' structural MRI scans.
• Employed an elastic net penalized linear regression model for age prediction.
• Analyzed cortical thickness across various spatial parcellation scales (78 to 10,240 parcels).

Main Results:

• Achieved high accuracy in chronological age estimation (cross-validated correlation up to R=0.84).
• Age prediction accuracy improved with increased spatial parcellation resolution, peaking at 2560 and 10,240 parcels.
• Key predictors of brain maturity were identified in localized sensorimotor and association areas.

Conclusions:

• Cortical thickness from MRI is a reliable biomarker for estimating brain maturity in children and adolescents.
• The developed model offers a valuable tool for assessing biological maturity and understanding neurodevelopment.
• Estimated brain age correlates with functional and behavioral measures, highlighting clinical relevance.