Analysis of Hippocampus Evolution Patterns and Prediction of Conversion in Mild Cognitive Impairment Using...

Area of Science:

• Neuroimaging
• Alzheimer's Disease Research
• Cognitive Neurology

Background:

• Mild cognitive impairment (MCI) is a precursor to Alzheimer's disease (AD), characterized by hippocampal morphological changes.
• Conventional methods lack precision in quantifying hippocampal deformation and ignore disease progression.
• Hippocampal changes are critical indicators of MCI and its potential conversion to AD.

Purpose of the Study:

• To investigate the temporal evolution patterns of MCI using multivariate morphometry statistics (MMS).
• To predict the conversion of MCI to AD by analyzing dynamic MMS (DMMS) features.
• To identify specific brain regions affected by atrophy or expansion in MCI patients.

Main Methods:

• Extracted MMS features from MRI scans of MCI converters (MCIc), stable MCI (MCIs), and healthy controls (HC).
• Defined dynamic MMS (DMMS) features to incorporate temporal information.
• Utilized statistical analysis for group comparisons, dimensionality reduction techniques, and the GentleBoost ensemble classifier for MCIc/MCIs classification.

Main Results:

• Longitudinal analysis showed progressive hippocampal atrophy in both MCIc and MCIs, primarily in dorsal CA1, spreading to other regions.
• MCIc exhibited larger and more significant atrophy areas compared to MCIs.
• Incorporating longitudinal information improved MCI to AD conversion prediction accuracy to 91.76%.

Conclusions:

• Dynamic hippocampal information is crucial for understanding MCI pathology.
• Temporal analysis of hippocampal morphometry offers a promising avenue for early AD detection.
• The study highlights the potential of DMMS features in predicting MCI conversion to AD.