Generation of synthetic PET images of synaptic density and amyloid from 18 F-FDG images using deep learning

Abstract

Purpose: Positron emission tomography (PET) imaging with various tracers is increasingly used in Alzheimer's disease (AD) studies. However, access to PET scans using new or less-available tracers with sophisticated synthesis and short half-life isotopes may be very limited. Therefore, it is of great significance and interest in AD research to assess the feasibility of generating synthetic PET images of less-available tracers from the PET image of another common tracer, in particular ¹⁸ F-FDG.

Methods: We implemented advanced deep learning methods using the U-Net model to predict ¹¹ C-UCB-J PET images of synaptic vesicle protein 2A (SV2A), a surrogate of synaptic density, from ¹⁸ F-FDG PET data. Dynamic ¹⁸ F-FDG and ¹¹ C-UCB-J scans were performed in 21 participants with normal cognition (CN) and 33 participants with Alzheimer's disease (AD). Cerebellum was used as the reference region for both tracers. For ¹¹ C-UCB-J image prediction, four network models were trained and tested, which included 1) ¹⁸ F-FDG SUV ratio (SUVR) to ¹¹ C-UCB-J SUVR, 2) ¹⁸ F-FDG K_i ratio to ¹¹ C-UCB-J SUVR, 3) ¹⁸ F-FDG SUVR to ¹¹ C-UCB-J distribution volume ratio (DVR), and 4) ¹⁸ F-FDG K_i ratio to ¹¹ C-UCB-J DVR. The normalized root mean square error (NRMSE), structure similarity index (SSIM), and Pearson's correlation coefficient were calculated for evaluating the overall image prediction accuracy. Mean bias of various ROIs in the brain and correlation plots between predicted images and true images were calculated for ROI-based prediction accuracy. Following a similar training and evaluation strategy, ¹⁸ F-FDG SUVR to ¹¹ C-PiB SUVR network was also trained and tested for ¹¹ C-PiB static image prediction.

Results: The results showed that all four network models obtained satisfactory ¹¹ C-UCB-J static and parametric images. For ¹¹ C-UCB-J SUVR prediction, the mean ROI bias was -0.3% ± 7.4% for the AD group and -0.5% ± 7.3% for the CN group with ¹⁸ F-FDG SUVR as the input, -0.7% ± 8.1% for the AD group, and -1.3% ± 7.0% for the CN group with ¹⁸ F-FDG K_i ratio as the input. For ¹¹ C-UCB-J DVR prediction, the mean ROI bias was -1.3% ± 7.5% for the AD group and -2.0% ± 6.9% for the CN group with ¹⁸ F-FDG SUVR as the input, -0.7% ± 9.0% for the AD group, and -1.7% ± 7.8% for the CN group with ¹⁸ F-FDG K_i ratio as the input. For ¹¹ C-PiB SUVR image prediction, which appears to be a more challenging task, the incorporation of additional diagnostic information into the network is needed to control the bias below 5% for most ROIs.

Conclusions: It is feasible to use 3D U-Net-based methods to generate synthetic ¹¹ C-UCB-J PET images from ¹⁸ F-FDG images with reasonable prediction accuracy. It is also possible to predict ¹¹ C-PiB SUVR images from ¹⁸ F-FDG images, though the incorporation of additional non-imaging information is needed.

Keywords: brain PET; deep learning; image processing; multi-tracer; parametric image.