Published in:
01-12-2020 | Alzheimer's Disease | Research article
Predicting MCI progression with FDG-PET and cognitive scores: a longitudinal study
Published in: BMC Neurology | Issue 1/2020
Login to get accessAbstract
Background
Mild cognitive impairment (MCI) is an intermediate stage between normal aging and dementia. Studies on MCI progression are important for Alzheimer’s disease (AD) prevention. 18F fluoro-deoxy-glucose positron emission tomography (FDG-PET) has been proven to be a powerful tool for measuring cerebral glucose metabolism. In this study, we proposed a classification framework for MCI prediction with both baseline and multiple follow-up FDG-PET scans as well as cognitive scores of 33 progressive MCI (pMCI) patients and 46 stable MCI (sMCI) patients from the Alzheimer’s Disease Neuroimaging Initiative (ADNI).
Method
First, PET images were normalized using the Yakushev normalization procedure and registered to the Brainnetome Atlas (BNA). The average metabolic intensities of brain regions were defined as static features. Dynamic features were the intensity variation between baseline and the other three time points and change ratios with the intensity obtained at baseline considered as reference. Mini-mental State Examination (MMSE) scores and Alzheimer’s disease Assessment Scale-Cognitive section (ADAS-cog) scores of each time point were collected as cognitive features. And F-score was applied for feature selection. Finally, support vector machine (SVM) with radial basis function (RBF) kernel was used for the three above features.
Results
Dynamic features showed the best classification performance in accuracy of 88.61% than static features (accuracy of 78.48%). And the combination of cognitive features and dynamic features improved the classification performance in specificity of 95.65% and Area Under Curve (AUC) of 0.9308.
Conclusion
Our results reported that dynamic features are more representative in longitudinal research for MCI prediction work. And dynamic features and cognitive scores complementarily enhance the classification performance in specificity and AUC. These findings may predict the disease course and clinical changes in individuals with mild cognitive impairment.