What type of study is this?

This is a Quantitative Study study.

September 17, 2025

Enhancing Brain Age Estimation with a Multimodal 3D CNN Approach Combining Structural MRI and AI-Synthesized Cerebral Blood Volume Data

JJJordan JomskyUniversity of Southern California ZLZongyu LiColumbia University YZYiren ZhangAlzheimer’s Disease Neuroimaging Initiative

Key Points

The integrated model shows a lower mean absolute error of 3.95, indicating better accuracy than traditional methods.
Utilizing AI-derived cerebral blood volume data enhances the effectiveness of brain age predictions significantly.
The study employs a 3D CNN-VGG architecture, seamlessly integrating structural MRI with functional data.
This approach may open new avenues for early detection of neurodegenerative diseases, enhancing clinical assessment.

Abstract

Motivation: An aging population calls for better ways to understand brain aging's impact on cognitive health and neurological disorders. Current brain age estimation models using T1w MRI lack functional insights, limiting their potential. Goal(s): To improve brain age prediction by integrating structural T1w MRI with AI-derived Cerebral Blood Volume (AICBV), a non-invasive functional biomarker. Approach: Using a 3D CNN-VGG architecture, we combined the predicted ages from T1w MRI and AICBV-derived functional data with linear regression. Results: The integrated model outperformed traditional T1w-only models, showing a lower mean absolute error of 3.95 and higher R² of 0.943, promising enhanced clinical utility for brain health assessment. Impact: By integrating functional AICBV data with structural T1w MRI, this study enhances brain age estimation, offering a non-invasive, cost-effective tool for early diagnosis of cognitive decline. It opens new research avenues in neurodegenerative disease detection and personalized brain health assessments.

Ask AI

Helpful

Bookmark

View Full Paper