Outcome classification of preschool children with autism spectrum disorders using MRI brain measures

Area of Science:

• Neuroimaging
• Developmental Neuroscience
• Pediatric Neurology

Background:

• Autism Spectrum Disorder (ASD) is a complex neurodevelopmental condition.
• Early identification and understanding of factors influencing functional outcome in ASD are crucial.
• Magnetic Resonance Imaging (MRI) offers detailed insights into brain structure.

Purpose of the Study:

• To determine if early childhood MRI brain measures can differentiate children with ASD from typically developing peers.
• To investigate the association between these brain measures and functional outcomes in children with ASD.

Main Methods:

• Quantitative MRI was used to measure gray and white matter volumes (cerebrum, cerebellum), total brain volume, and cerebellar vermis area.
• The study included 52 boys with a provisional ASD diagnosis (1.9-5.2 years) and 15 typically developing children (1.7-5.2 years).
• Diagnostic confirmation and cognitive outcome data were collected after age 5.

Main Results:

• Discriminant function analysis achieved high classification accuracy: 95.8% for ASD cases and 92.3% for controls.
• MRI measures also predicted functional levels within the ASD group, classifying 85% of lower-functioning and 68% of higher-functioning cases.
• Variability in cerebellar and cerebral size was a key differentiator.

Conclusions:

• Early childhood brain MRI measures are effective in distinguishing ASD from typical development.
• Cerebellar and cerebral size variability is linked to both the diagnosis and functional prognosis of ASD.
• These findings highlight the potential of neuroimaging for early ASD assessment and outcome prediction.