Related Experiment Video
Updated: Aug 5, 2026
Probing the Brain in Autism Using fMRI and Diffusion Tensor Imaging
Published on: September 12, 2011
Predicting brain age in children aged 2-6 years with autism spectrum disorders using routine T1- and T2-weighted
Zunying Hu1, Rongjia Xiang2, Huanyu Luo1
1Department of Radiology Beijing Children's Hospital Capital Medical University National Center for Children's Health China.
Insights
This study developed a brain age prediction model using routine MRI scans for children aged 2-6 years. The model revealed delayed brain maturation in children with autism spectrum disorder (ASD), with varying patterns across early childhood.
Area of Science:
- Neuroscience
- Developmental Psychology
- Radiology
Background:
- Early childhood (2-6 years) is crucial for brain development and the onset of neurodevelopmental disorders like autism spectrum disorder (ASD).
- Brain maturation patterns during this period are not well understood, particularly using standard clinical imaging.
- Routine magnetic resonance imaging (MRI) has potential for assessing brain development in young children.
Purpose of the Study:
- To create a brain age prediction model utilizing routine MRI data.
- To identify and characterize brain maturation deviations in children diagnosed with ASD.
- To assess the utility of machine learning models for analyzing neurodevelopmental trajectories.
Main Methods:
- Retrospective analysis of MRI data from 2010 typically developing children (TDC) and 822 children with ASD (ages 2-6).
- Development of a brain age prediction model using T1- and T2-weighted MRI with machine learning (Ridge regression) in the TDC cohort.
- Application of the model to the ASD cohort to calculate brain age difference (BAD) and compare maturational patterns via age-matched and stratified analyses.
Main Results:
- The Ridge regression model achieved robust performance (MAE=0.526 years, PCC=0.812 in TDC; MAE=0.497 years, PCC=0.775 in ASD).
- Children with ASD exhibited significantly delayed brain maturation compared to TDC (P < 0.001).
- ASD subgroups showed nominal delays at ages 3-4 and 4-5 years, with a trend towards advanced predicted brain age by 5-6 years.
Conclusions:
- A routine MRI-based brain age prediction model effectively estimates brain age in children with and without ASD.
- The model highlights dynamic, age-related maturational patterns in children with ASD.
- Findings underscore the developmental heterogeneity within autism spectrum disorder during early childhood.
Importance:
Early childhood (ages 2-6 years) represents a dynamic phase of brain maturation and a critical window for the emergence of neurodevelopmental disorders, such as autism spectrum disorder (ASD). However, the maturational patterns of the brain during this period remain underexplored, especially regarding the utility of routine clinical imaging.
Objective:
To develop a brain age prediction model using routine magnetic resonance imaging (MRI) and characterize maturational deviations in children with ASD.
Methods:
We retrospectively collected MRI data from 2010 typically developing children (TDC) and 822 children with ASD (aged 2-6 years). A brain age prediction model based on T1- and T2-weighted MRI was developed using machine learning algorithms in the TDC cohort and subsequently applied to the ASD cohort. Model performance was assessed using the mean absolute error (MAE) and Pearson's correlation coefficient (PCC). Brain age difference (BAD) was compared between the two groups, followed by age-matched analyses and age-stratified comparisons.
Results:
The Ridge regression model demonstrated a robust performance in the TDC testing set (MAE = 0.526 years, PCC = 0.812) and showed comparable predictive performance in the ASD cohort (MAE = 0.497 years, PCC = 0.775). Age-matched analysis revealed significantly delayed brain maturation in ASD patients compared with TDC patients (P < 0.001). Stratified analysis identified nominal delays in ASD subgroups aged 3-4 years and 4-5 years, with a trend toward relatively advanced predicted brain age by ages 5-6 years.
Interpretation:
This routine MRI-based brain age prediction model demonstrated good performance, with low prediction error and high correlation between predicted and chronological age, in estimating the brain age of TDC and ASD. It revealed a dynamic, age-related pattern in children with ASD, highlighting developmental heterogeneity across early childhood.
