Biomarkers.

Area of Science:

• Neuroimaging
• Radiology
• Biomedical Engineering

Background:

• Arterial spin labelling (ASL) MRI enables non-invasive measurement of cerebral blood flow (CBF).
• Regional hypoperfusion detected by ASL is linked to Alzheimer's disease (AD) progression, preceding observable brain atrophy.
• This study investigates the utility of ASL in diagnosing AD and monitoring its progression.

Purpose of the Study:

• To assess the diagnostic performance of ASL-based CBF measurements for Alzheimer's disease (AD).
• To evaluate ASL's capability in differentiating between cognitively normal (CN), mild cognitive impairment (MCI), and AD patients.
• To determine the effectiveness of ASL in predicting MCI progression to AD.

Main Methods:

• Utilized a subset of Alzheimer's Disease Neuroimaging Initiative (ADNI-3) participants.
• Processed ASL images using the qasl pipeline to generate calibrated CBF maps.
• Trained support vector machine (SVM) classifiers using ROI-based CBF, demographic covariates, and scanner type, with feature selection driven by ANOVA.

Main Results:

• Classifiers achieved high accuracy in distinguishing AD from CN (AUC=0.957) and MCI (AUC=0.936), with high specificity (0.98).
• Performance in differentiating CN from MCI was moderate (AUC=0.702).
• ASL demonstrated strong predictive power for MCI progression to AD (AUC > 0.9).

Conclusions:

• ASL-derived CBF measures can accurately predict clinical diagnosis and disease progression in Alzheimer's disease.
• The performance of ASL classifiers in this study surpassed that of previously reported PET and ASL analyses.
• ASL MRI represents a promising non-invasive tool for AD diagnosis and progression monitoring.