A deep learning model for generating [18F]FDG PET Images from early-phase [18F]Florbetapir and [18F]Flutemetamol PET images

Introduction Amyloid-beta (A beta) plaques is a significant hallmark of Alzheimer's disease (AD), detectable via amyloid-PET imaging. The Fluorine-(18)-Fluorodeoxyglucose ([F-18]FDG) PET scan tracks cerebral glucose metabolism, correlated with synaptic dysfunction and disease progression and is complementary for AD diagnosis. Dual-scan acquisitions of amyloid PET allows the possibility to use early-phase amyloid-PET as a biomarker for neurodegeneration, proven to have a good correlation to [F-18]FDG PET. The aim of this study was to evaluate the added value of synthesizing the later from the former through deep learning (DL), aiming at reducing the number of PET scans, radiation dose, and discomfort to patients. Methods A total of 166 subjects including cognitively unimpaired individuals (N = 72), subjects with mild cognitive impairment (N = 73) and dementia (N = 21) were included in this study. All underwent T1-weighted MRI, dual-phase amyloid PET scans using either Fluorine-18 Florbetapir ([F-18]FBP) or Fluorine-18 Flutemetamol ([F-18]FMM), and an [F-18]FDG PET scan. Two transformer-based DL models called SwinUNETR were trained separately to synthesize the [F-18]FDG from early phase [F-18]FBP and [F-18]FMM (eFBP/eFMM). A clinical similarity score (1: no similarity to 3: similar) was assessed to compare the imaging information obtained by synthesized [F-18]FDG as well as eFBP/eFMM to actual [F-18]FDG. Quantitative evaluations include region wise correlation and single-subject voxel-wise analyses in comparison with a reference [F-18]FDG PET healthy control database. Dice coefficients were calculated to quantify the whole-brain spatial overlap between hypometabolic ([F-18]FDG PET) and hypoperfused (eFBP/eFMM) binary maps at the single-subject level as well as between [F-18]FDG PET and synthetic [F-18]FDG PET hypometabolic binary maps. Results The clinical evaluation showed that, in comparison to eFBP/eFMM (average of clinical similarity score (CSS) = 1.53), the synthetic [F-18]FDG images are quite similar to the actual [18F]FDG images (average of CSS = 2.7) in terms of preserving clinically relevant uptake patterns. The single-subject voxel-wise analyses showed that at the group level, the Dice scores improved by around 13% and 5% when using the DL approach for eFBP and eFMM, respectively. The correlation analysis results indicated a relatively strong correlation between eFBP/eFMM and [F-18]FDG (eFBP: slope = 0.77, R-2 = 0.61, P-value < 0.0001); eFMM: slope = 0.77, R-2 = 0.61, P-value < 0.0001). This correlation improved for synthetic [F-18]FDG (synthetic [F-18]FDG generated from eFBP (slope = 1.00, R-2 = 0.68, P-value < 0.0001), eFMM (slope = 0.93, R-2 = 0.72, P-value < 0.0001)). Conclusion We proposed a DL model for generating the [F-18]FDG from eFBP/eFMM PET images. This method may be used as an alternative for multiple radiotracer scanning in research and clinical settings allowing to adopt the currently validated [F-18]FDG PET normal reference databases for data analysis.