Predicting FDG PET from Multi-contrast MRIs using Deep Learning in Patients with Brain Neoplasms

PET is a widely used imaging technique, but it requires exposing subjects to radiation and is not offered in the majority of medical centers in the world. Here, we proposed to synthesize FDG-PET images from multi-contrast MR images using a U-Net-based network with attention modules and transformer blocks. The experiments on a dataset with 87 brain lesions in 59 patients demonstrated that the proposed method was able to generate high-quality PET from MR images without the need for radiotracer injection. We also demonstrate methods to handle potential missing or corrupted sequences.