文献速递神经核医学肿瘤 PET/CT

多巴胺能PET到SPECT的域适应:一种循环生成对抗网络翻译方法

Dopaminergic PET to SPECT domain adaptation: a cycle GAN translation approach.
PubMed 文献 · Eur J Nucl Med Mol Imaging · 2024-11-19

研究训练CycleGAN将[11C]CFT PET图像转换为[123I]FP-CIT SPECT图像,在真实PET测试集(n=67,75%PD)上生成合成SPECT。合成与真实SPECT的视觉评分无显著差异,基于合成SPECT训练的深度学习分类模型在真实SPECT上达到敏感度97.2%、特异度90.0%,纹状体特异性结合比无显著差异。

要点

  • CycleGAN生成的合成SPECT与真实SPECT视觉评分无显著差异,但合成图像诊断性能有所降低。
  • 基于合成SPECT训练的分类模型在真实SPECT上敏感度97.2%、特异度90.0%。
  • 合成SPECT的纹状体特异性结合比与真实SPECT无显著差异。

核心结论

  • CycleGAN生成的合成SPECT图像在视觉上与真实图像无法区分,并保留了疾病特异性信息,证明将[11C]CFT PET翻译为[123I]FP-CIT SPECT的可行性。
  • 这种跨模态合成可能提高进一步AI分类的准确性,支持PD和APS的诊断。

研究设计与样本

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

主要发现

  • Fréchet Inception Distance显示合成SPECT与真实SPECT的相似性高于合成SPECT与真实PET的相似性。
  • 基于合成SPECT训练的深度学习分类模型在真实SPECT图像上达到敏感度97.2%、特异度90.0%。
  • 合成SPECT的纹状体特异性结合比与真实SPECT无显著差异。
  • 纹状体左右差异和壳核结合比仅在PD队列中显著不同。
  • 真实PET和真实SPECT的对比噪声比高于合成SPECT。

临床怎么用

  • 原文未据此给出推荐。

局限性

  • 原文未报告局限性。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

原文

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.

来源:Eur J Nucl Med Mol Imaging,查看原文。版权归原作者所有。

引用

  1. Lopes L, Jiao F, Xue S, et al. Dopaminergic PET to SPECT domain adaptation: a cycle GAN translation approach. Eur J Nucl Med Mol Imaging. 2024. PMID: 39557690. doi:10.1007/s00259-024-06961-x

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。