Introduction: 18F-Fluoro-deoxyglucose-positron emission tomography (FDG-PET) is a supportive biomarker in dementia with Lewy bodies (DLB) diagnosis and its advanced analysis methods, including radiomics and machine learning (ML), were developed recently. The aim of this study was to evaluate the FDG-PET diagnostic performance in predicting a DLB versus Alzheimer's disease (AD) diagnosis.
Methods: FDG-PET scans were visually and semi-quantitatively analyzed in 61 patients. Radiomics and ML analyses were performed, building five ML models: (1) clinical features; (2) visual and semi-quantitative PET features; (3) radiomic features; (4) all PET features; and (5) overall features.
Results: At follow-up, 34 patients had DLB and 27 had AD. At visual analysis, DLB PET signs were significantly more frequent in DLB, having the highest diagnostic accuracy (86.9%). At semi-quantitative analysis, the right precuneus, superior parietal, lateral occipital, and primary visual cortices showed significantly reduced uptake in DLB. The ML model 2 had the highest diagnostic accuracy (84.3%).
Discussion: FDG-PET is a valuable tool in DLB diagnosis, having visual and semi-quantitative analyses with the highest diagnostic accuracy at ML analyses.
Keywords: 18F‐FDG; Lewy body dementia; PET‐CT; artificial intelligence; biomarkers; dementia; machine learning; radiomics.
© 2023 The Authors. Alzheimer's & Dementia: Diagnosis, Assessment & Disease Monitoring published by Wiley Periodicals LLC on behalf of Alzheimer's Association.