A deep learning model for generating 18FFDG PET Images from early-phase 18FFlorbetapir and 18FFlutemetamol PET images

Introduction: Amyloid-β (Aβ) plaques is a significant hallmark of Alzheimer's disease (AD), detectable via amyloid-PET imaging. The Fluorine-18-Fluorodeoxyglucose (18FFDG) 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 18FFDG 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 (18FFBP) or Fluorine-18 Flutemetamol (18FFMM), and an 18FFDG PET scan. Two transformer-based DL models called SwinUNETR were trained separately to synthesize the 18FFDG from early phase 18FFBP and 18FFMM (eFBP/eFMM). A clinical similarity score (1: no similarity to 3: similar) was assessed to compare the imaging information obtained by synthesized 18FFDG as well as eFBP/eFMM to actual 18FFDG. Quantitative evaluations include region wise correlation and single-subject voxel-wise analyses in comparison with a reference 18FFDG PET healthy control database. Dice coefficients were calculated to quantify the whole-brain spatial overlap between hypometabolic (18FFDG PET) and hypoperfused (eFBP/eFMM) binary maps at the single-subject level as well as between 18FFDG PET and synthetic 18FFDG 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 18FFDG images are quite similar to the actual 18FFDG 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 18FFDG (eFBP: slope = 0.77, R2 = 0.61, P-value < 0.0001); eFMM: slope = 0.77, R2 = 0.61, P-value < 0.0001). This correlation improved for synthetic 18FFDG (synthetic 18FFDG generated from eFBP (slope = 1.00, R2 = 0.68, P-value < 0.0001), eFMM (slope = 0.93, R2 = 0.72, P-value < 0.0001)). Conclusion: We proposed a DL model for generating the 18FFDG 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 18FFDG PET normal reference databases for data analysis.