Enhancing Brain Age Estimation with a Multimodal 3D CNN Approach Combining Structural MRI and AI-Synthesized Cerebral Blood Volume Data
This work addresses brain aging assessment for aging populations by providing a more accurate biomarker, though it is incremental as it combines existing modalities with a standard deep learning approach.
The paper tackled brain age estimation by integrating structural MRI with AI-synthesized cerebral blood volume data, achieving a mean absolute error of 3.95 years and an R² of 0.943, outperforming existing models.
The increasing global aging population necessitates improved methods to assess brain aging and its related neurodegenerative changes. Brain Age Gap Estimation (BrainAGE) offers a neuroimaging biomarker for understanding these changes by predicting brain age from MRI scans. Current approaches primarily use T1-weighted magnetic resonance imaging (T1w MRI) data, capturing only structural brain information. To address this limitation, AI-generated Cerebral Blood Volume (AICBV) data, synthesized from non-contrast MRI scans, offers functional insights by revealing subtle blood-tissue contrasts otherwise undetectable in standard imaging. We integrated AICBV with T1w MRI to predict brain age, combining both structural and functional metrics. We developed a deep learning model using a VGG-based architecture for both modalities and combined their predictions using linear regression. Our model achieved a mean absolute error (MAE) of 3.95 years and an $R^2$ of 0.943 on the test set ($n = 288$), outperforming existing models trained on similar data. We have further created gradient-based class activation maps (Grad-CAM) to visualize the regions of the brain that most influenced the model's predictions, providing interpretable insights into the structural and functional contributors to brain aging.