Modeling refined differences of cortical folding patterns via spatial, morphological, and temporal fusion...

Area of Science:

• Neuroscience
• Brain Imaging
• Computational Biology

Background:

• Cortical folding patterns, like gyri and sulci, are crucial for brain structure-function integration.
• Voxel-level studies struggle with precise spatial relationships in variable cortical folding patterns.
• Existing methods may not fully capture subtle variations in cortical morphology and function.

Purpose of the Study:

• To develop a novel model for analyzing complex cortical folding patterns, specifically 2-Hinge and 3-Hinge folds.
• To integrate spatial distribution, morphological structure, and functional magnetic resonance imaging (fMRI) data.
• To identify biomarkers for brain structure-function correlations using advanced representations.

Main Methods:

• Utilized spatio-morphological residual representations to extract subtle variations in cortical structure.
• Integrated these representations with fMRI data using self-attention mechanisms for spatio-morphological-temporal analysis.
• Tested the model's efficacy in identifying cortical folding patterns (sulci, gyri, 2-Hinge, 3-Hinge) and evaluating phenotypic impacts.

Main Results:

• The novel model demonstrated superior performance in identifying cortical folding patterns.
• Significant differences in cortical folding patterns were observed under various stimuli.
• Gender-based differences in sulci and gyri folds were identified, with 3-Hinge folds showing greater variation.

Conclusions:

• The developed spatio-morphological-temporal representations are effective for analyzing cortical folding patterns.
• These representations can serve as potential biomarkers for understanding brain structure-function relationships.
• The findings highlight the influence of stimuli and gender on cortical folding patterns.