Purpose

Dopamine transporter imaging is routinely used in Parkinson’s disease (PD) and atypical parkinsonian syndromes (APS) diagnosis. While [¹¹C]CFT PET is prevalent in Asia with a large APS database, Europe relies on [¹²³I]FP-CIT SPECT with limited APS data. Our aim was to develop a deep learning-based method to convert [¹¹C]CFT PET images to [¹²³I]FP-CIT SPECT images, facilitating multicenter studies and overcoming data scarcity to promote Artificial Intelligence (AI) advancements.

Methods

A CycleGAN was trained on [¹¹C]CFT PET (n = 602, 72%PD) and [¹²³I]FP-CIT SPECT (n = 1152, 85%PD) images from PD and non-parkinsonian control (NC) subjects. The model generated synthetic SPECT images from a real PET test set (n = 67, 75%PD). Synthetic images were quantitatively and visually evaluated.

Results

Fréchet Inception Distance indicated higher similarity between synthetic and real SPECT than between synthetic SPECT and real PET. A deep learning classification model trained on synthetic SPECT achieved sensitivity of 97.2% and specificity of 90.0% on real SPECT images. Striatal specific binding ratios of synthetic SPECT were not significantly different from real SPECT. The striatal left-right differences and putamen binding ratio were significantly different only in the PD cohort. Real PET and real SPECT had higher contrast-to-noise ratio compared to synthetic SPECT. Visual grading analysis scores showed no significant differences between real and synthetic SPECT, although reduced diagnostic performance on synthetic images was observed.

Conclusion

CycleGAN generated synthetic SPECT images visually indistinguishable from real ones and retained disease-specific information, demonstrating the feasibility of translating [¹¹C]CFT PET to [¹²³I]FP-CIT SPECT. This cross-modality synthesis could enhance further AI classification accuracy, supporting the diagnosis of PD and APS.

中文翻译：

---

多巴胺能 PET 到 SPECT 结构域的适应：一种循环 GAN 翻译方法

 目的

多巴胺转运蛋白成像通常用于帕金森病 （PD） 和非典型帕金森综合征 （APS） 诊断。虽然 [¹¹C]CFT PET 在亚洲普遍存在，拥有庞大的 APS 数据库，而欧洲则依赖于 [¹²³I]FP-CIT SPECT 的 APS 数据有限。我们的目标是开发一种基于深度学习的方法，将 [¹¹C]CFT PET 图像转换为 [¹²³I]FP-CIT SPECT 图像，促进多中心研究并克服数据稀缺，以促进人工智能 （AI） 的进步。

 方法

CycleGAN 在来自 PD 和非帕金森病对照 （NC） 受试者的 [¹¹C]CFT PET （n = 602， 72%PD） 和 [¹²³I]FP-CIT SPECT （n = 1152， 85%PD） 图像上进行训练。该模型从真实的 PET 测试集 （n = 67， 75%PD） 生成合成 SPECT 图像。对合成图像进行定量和视觉评估。

 结果

Fréchet Inception Distance 表明合成 SPECT 和真实 SPECT 之间的相似性高于合成 SPECT 和真实 PET 之间的相似性。在合成 SPECT 上训练的深度学习分类模型在真实 SPECT 图像上实现了 97.2% 的灵敏度和 90.0% 的特异性。合成 SPECT 的纹状体特异性结合比与真实 SPECT 没有显著差异。纹状体左右差异和壳核结合比仅在 PD 队列中显著差异。与合成 SPECT 相比，真实 PET 和真实 SPECT 具有更高的对比度噪声比。视觉分级分析评分显示真实和合成 SPECT 之间没有显着差异，尽管观察到合成图像的诊断性能降低。

 结论

CycleGAN 生成的合成 SPECT 图像在视觉上与真实图像没有区别，并保留了疾病特异性信息，证明了将 [¹¹C]CFT PET 转换为 [¹²³I]FP-CIT SPECT 的可行性。这种跨模态综合可以进一步提高 AI 分类的准确性，支持 PD 和 APS 的诊断。