Cross-modality PET image synthesis for Parkinson's Disease diagnosis: a leap from [ 18 F]FDG to [ 11 C]CFT

Dopamine transporter [ C]CFT PET is highly effective for diagnosing Parkinson's Disease (PD), whereas it is not widely available in most hospitals. To develop a deep learning framework to synthesize [ C]CFT PET images from real [ F]FDG PET images and leverage their cross-modal correlation to distinguish PD from normal control (NC). We developed a deep learning framework to synthesize [ C]CFT PET images from real [ F]FDG PET images, and leveraged their cross-modal correlation to distinguish PD from NC. A total of 604 participants (274 with PD and 330 with NC) who underwent [ C]CFT and [ F]FDG PET scans were included. The quality of the synthetic [ C]CFT PET images was evaluated through quantitative comparison with the ground-truth images and radiologist visual assessment. The evaluations of PD diagnosis performance were conducted using biomarker-based quantitative analyses (using striatal binding ratios from synthetic [ C]CFT PET images) and the proposed PD classifier (incorporating both real [ F]FDG and synthetic [ C]CFT PET images). Visualization result shows that the synthetic [ C]CFT PET images resemble the real ones with no significant differences visible in the error maps. Quantitative evaluation demonstrated that synthetic [ C]CFT PET images exhibited a high peak signal-to-noise ratio (PSNR: 25.0-28.0) and structural similarity (SSIM: 0.87-0.96) across different unilateral striatal subregions. The radiologists achieved a diagnostic accuracy of 91.9% (± 2.02%) based on synthetic [ C]CFT PET images, while biomarker-based quantitative analysis of the posterior putamen yielded an AUC of 0.912 (95% CI, 0.889-0.936), and the proposed PD Classifier achieved an AUC of 0.937 (95% CI, 0.916-0.957). By bridging the gap between [ F]FDG and [ C]CFT, our deep learning framework can significantly enhance PD diagnosis without the need for [ C]CFT tracers, thereby expanding the reach of advanced diagnostic tools to clinical settings where [ C]CFT PET imaging is inaccessible.