What question did this study set out to answer?

To examine changes in cerebellar amyloid plaque deposition connectivity networks during Alzheimer’s progression using PET imaging.

February 19, 2026PLoS ONEOpen Access

Early diagnosis of Alzheimer’s Disease: Graph theoretical analysis of cerebellar network features based on 18F-AV45 PET

View Full Paper

Ask AI

Bookmark

Authors

Graph theoretical analysis reveals cerebellar connectivity changes in Alzheimer’s patients, suggesting improved early diagnosis methods.

To examine changes in cerebellar amyloid plaque deposition connectivity networks during Alzheimer’s progression using PET imaging.
Analyzed 18F-AV45 PET imaging data from 612 subjects in the ADNI dataset.
Applied graph theoretical analysis to study cerebellar network connectivity.
Examined differences in connectivity across cognitively normal, early mild cognitive impairment, late mild cognitive impairment, and Alzheimer’s disease groups.
Combined graph features with standardized uptake value ratio for machine learning models.
Evaluated model performance using area under the curve (AUC) metrics.
Observed significant changes in cerebellar connectivity as cognitive decline progressed.
Notable changes in betweenness centrality across multiple cerebellar regions at different cognitive stages.
Machine learning model achieved an AUC of 0.950 for distinguishing Alzheimer’s from cognitively normal individuals, indicating high accuracy for early diagnosis.
The model also showed strong performance with AUCs of 0.995 for cognitively normal vs. early mild cognitive impairment and 0.964 for early vs. late mild cognitive impairment.

Li et al. (2026) studied this question.

View Full Paper

Ask AI

Bookmark

Graph theoretical analysis reveals cerebellar connectivity changes in Alzheimer’s patients, suggesting improved early diagnosis methods.