Brain Age Gap Prediction and Application to Alzheimer’s Disease Using Synthetic T1 and T2 Maps with Deep Learning

Motivation: Brain Age Gap (BAG), which measures the difference between chronological and predicted brain age, is valuable for assessing neurodegenerative disorders such as Alzheimer's disease (AD). Goal(s): This study used synthetic T1 and T2 maps to predict BAG and explored its value in detecting AD. Approach: Synthetic T1 and T2 maps were used as input to deep learning models, combined with bias-correction techniques, to enhance performance in brain age prediction. Results: Synthetic mappings improved accuracy and generalizability over traditional weighted MR images in predicting brain age. Integrating BAG in image analysis further enhanced disease classification, underscoring its clinical potential. Impact: The integration of T1 and T2 mapping improves brain age gap prediction and disease classification, offering a robust, accurate tool for early detection and monitoring of neurodegenerative diseases.