Mapping Regional Brain Aging in Huntington's Disease Using Structural Magnetic Resonance Imaging and Machine Learning

Area of Science:

• Neuroscience
• Radiology
• Biomarkers

Background:

• Huntington's disease (HD) is a progressive neurodegenerative disorder characterized by accelerated brain aging.
• Existing brain age models often use a single whole-brain measure, limiting insights into region-specific aging patterns.
• Region-specific brain age models are underexplored in HD but could enhance biomarker sensitivity for clinical trials.

Purpose of the Study:

• To characterize region-specific brain aging patterns across different stages of the Huntington's Disease Integrated Staging System (HD-ISS).
• To evaluate the association between regional brain age gap and cognitive, motor, and functional scores in individuals with HD.

Main Methods:

• Machine learning models were trained on structural MRI data from 1936 controls to predict brain age.
• These models were applied to 531 individuals with HD to calculate regional brain age gaps.
• Statistical analyses assessed the relationship between regional brain age gap, HD-ISS stages, and clinical assessments.

Main Results:

• Whole-brain aging increased with HD-ISS stages 2 and 3.
• Subcortical, temporal, and parietal regions showed significant increases in brain age gap across HD stages.
• Elevated brain age gap in these regions correlated with poorer cognitive, motor, and functional performance.
• Insular and frontal regions displayed flatter aging patterns with no significant clinical associations.

Conclusions:

• Distinct region-specific aging components characterize Huntington's disease progression.
• Regional brain age gap analysis offers deeper insights into HD and potential sensitive biomarkers for therapeutic monitoring.
• Future research should investigate these findings in younger cohorts and explore network-specific aging using multimodal imaging.