Classification of Alzheimer’s Disease Using Dual-Phase 18F-Florbetaben Image with Rank-Based Feature Selection and Machine Learning

18F-florbetaben (FBB) positron emission tomography is a representative imaging test that observes amyloid deposition in the brain. Compared to delay-phase FBB (dFBB), early-phase shows patterns related glucose metabolism 18F-fluorodeoxyglucose perfusion images. The purpose of this study prove classification accuracy higher when using dual-phase (dual FBB) versus dFBB quantitative analysis by machine learning and find an optimal model suitable for dual data. key features our method are (1) feature ranking each phase with cross-validated F1 score (2) diagnostic based on methods. We compared four models: support vector machine, naïve Bayes, logistic regression, random forest (RF). In composite standardized uptake value ratio, RF achieved best performance (F1: 78.06%) FBB, which was 4.83% than result dFBB. conclusion, regardless two methods, has classifies FBB. regions have greatest influence frontal temporal lobes.