Generating synthetic brain PET images of synaptic density based on MR T1 images using deep learning.

Abstract

Purpose: Synaptic vesicle glycoprotein 2 A (SV2A) in human brains is an important biomarker of synaptic loss associated with several neurological disorders. However, SV2A tracers, such as [¹¹C]UCB-J, are less available in practice due to constrains such as cost, radiation exposure and onsite cyclotron. We therefore aim to generate synthetic [¹¹C]UCB-J PET images based on MRI in this study.

Methods: We implemented a convolution-based 3D encoder-decoder to predict [¹¹C]UCB-J SV2A PET images. A total of 160 participants who underwent both MRI and [¹¹C]UCB-J PET imaging, including individuals with schizophrenia, cannabis use disorder, Alzheimer's disease, were used in this study. The model was trained on pairs of T1-weighted MRI and [¹¹C]UCB-J distribution volume ratio images, and tested through a 10-fold cross-validation process. The image translation accuracy was evaluated based on the mean squared error, structural similarity index, percentage bias and Pearson's correlation coefficient between the ground truth and the predicted images. Additionally, we assessed the prediction accuracy of selected regions of interest (ROIs) crucial for brain disorders to evaluate our results.

Results: The generated SV2A PET images are visually similar to the ground truth in terms of contrast and tracer distribution, quantitatively with low bias (< 2%) and high similarity (> 0.9). Across all diagnostic categories and ROIs, including the hippocampus, frontal, occipital, parietal, and temporal regions, the synthetic SV2A PET images exhibit an average bias of less than 5% compared to the ground truth. The model also demonstrates a capacity for noise reduction, producing images of higher quality compared to the low-dose scans.

Conclusion: We conclude that it is feasible to generate robust SV2A PET images with promising accuracy from MRI via a data-driven approach.