Résumé
Positron emission tomography (PET) can detect brain amyloid-beta (A beta) deposits, a diagnostic hallmark of Alzheimer's disease and a target for disease modifying treatment. However, PET-A beta is expensive, not widely available, and, unlike magnetic resonance imaging (MRI), exposes the patient to ionizing radiation. Here we propose a novel 3D multimodal generative adversarial network with contrastive learning to synthesize PET-A beta images from cheaper, more accessible, and less invasiveMRI scans (T1-weighted and fluid attenuated inversion recovery [FLAIR] images). In tests on independent samples of paired MRI/PET-A beta data, our synthetic PET-A beta images were of high quality with a structural similarity index measure of 0.94, which outperformed previously published methods. We also evaluated synthetic PET-A beta images by extracting standardized uptake value ratio measurements. The synthetic images could identify amyloid positive patients with a balanced accuracy of 79%, holding promise for potential future use in a diagnostic clinical setting.