Development of Efficient Brain Age Estimation Method Based on Regional Brain Volume From Structural Magnetic...

Area of Science:

• Neuroimaging
• Artificial Intelligence
• Cognitive Neuroscience

Background:

• Brain age estimation is a promising biomarker for brain health.
• Accurate and efficient methods for calculating brain age are needed.
• Regional brain volumes are key indicators of brain structure and function.

Purpose of the Study:

• To develop an efficient and valid predictive model for estimating brain age.
• To quantify brain age by analyzing regional brain volumes from MRI scans.
• To assess the model's ability to reflect cognitive function and reserve.

Main Methods:

• Utilized 2,560 structural brain MRI scans and associated data.
• Employed deep learning for automated MRI segmentation and regional volume calculation.
• Calculated brain age gaps using 12 regions of interest (ROIs), weighting ROIs based on cognitive impairment differences.

Main Results:

• Significant differences in brain age gaps were observed across cognitively unimpaired, mild cognitive impairment, and dementia groups.
• Brain age gaps showed significant correlations with education level and cognitive function measures (CDR-SB, K-MMSE).
• The developed brain age model demonstrated efficiency and validity.

Conclusions:

• The developed brain age model enables fast and efficient brain age calculations.
• Brain age effectively reflects individual cognitive function and cognitive reserve.
• This brain age model shows potential as a significant brain health marker in clinical practice.