使用早期[18F]-FP-CIT PET成像开发基于AI的多巴胺转运蛋白（DAT）图像生成技术
Development of AI-based dopamine transporter (DAT) image generation technique using early phase [18F]-FP-CIT PET imaging.
摘要(中文译文)
开发并验证一种基于深度学习的模型，能够从早期[18F]-FP-CIT正电子发射断层扫描（PET）成像生成多巴胺转运体（DAT）图像。使用传统PET系统采集的477例双时相[¹⁸F]-FP-CIT PET扫描训练条件生成对抗网络。该模型从早期动态扫描（注射后30-40分钟）生成延迟期图像，使用五个相邻轴位切片预测中央延迟期切片。模型使用来自同一扫描仪的内部验证集和来自数字PET系统的独立前瞻性验证集进行评估。使用Pearson相关分析和受试者工作特征曲线下面积（AUC）分析比较纹状体结合比值（SNBR）和亚区间的比值。生成的图像与真实延迟期图像显示出高度相似性。整个纹状体的SNBR在真实图像与生成图像之间呈强相关（内部验证集和独立验证集分别为R = 0.93和0.90）。诊断性能相当，最高AUC见于后壳核（真实 vs 生成：1.00 vs 0.98，p > 0.2）。视觉评估未发现无法判读的图像，且可判读性无显著差异。在内部验证集中，生成图像对异常（p = 0.453）和退行性帕金森综合征（DP）（p = 1.000）检测的诊断准确性与真实图像相当。在独立验证集中，DP检测仍相当（p = 0.25），而真实图像在异常检测方面表现出显著更高的准确性（p < 0.001）。基于深度学习的模型生成的DAT图像在内部和独立验证集的定量和视觉评估中均达到令人满意的性能。
Abstract
To develop and validate a deep learning-based model capable of generating dopamine transporter (DAT) images from early-phase [18F]-FP-CIT positron emission tomography (PET) imaging. Conditional generative adversarial network was trained using 477 dual-phase [¹⁸F]-FP-CIT PET scans acquired with a conventional PET system. The model generated delayed-phase images from early-phase dynamic scans (30-40 min post-injection), using five adjacent axial slices to predict the central delayed-phase slice. The model was evaluated using an internal validation set from the same scanner and an independent prospective validation set from a digital PET system. Striatal binding ratios (SNBR) and inter-subregional ratios were compared using Pearson's correlation and receiver operating characteristic-area under the curve (AUC) analyses. Generated images showed high similarity to real delayed images. SNBRs for the whole striatum correlated strongly between real and generated images (R = 0.93 and 0.90 for internal and independent sets, respectively). Diagnostic performance was comparable with the highest AUC observed in the posterior putamen (real vs generated: 1.00 vs 0.98, p > 0.2). Visual assessments revealed no uninterpretable images, and interpretability did not differ significantly. Diagnostic accuracy of generated images was comparable to that of real images in the internal validation set for detection of abnormality (p = 0.453) and degenerative parkinsonism (DP) (p = 1.000). In the independent validation set, DP detection remained comparable (p = 0.25), whereas real images demonstrated significantly higher accuracy for abnormality detection (p < 0.001). Deep learning-based model generated DAT images achieve satisfactory performance in quantitative and visual assessments across internal and independent validation sets.
如何引用
AMA
Changhwan Sung, Jungsu S Oh, Sun Young Chae, Dong Yun Lee, Minyoung Oh, Sang Ju Lee, et al. Development of AI-based dopamine transporter (DAT) image generation technique using early phase [18F]-FP-CIT PET imaging.. PloS one. 2026; doi:10.1371/journal.pone.0349375.
APA
Changhwan Sung, Jungsu S Oh, Sun Young Chae, Dong Yun Lee, Minyoung Oh, Sang Ju Lee, et al (2026). Development of AI-based dopamine transporter (DAT) image generation technique using early phase [18F]-FP-CIT PET imaging.. PloS one. https://doi.org/10.1371/journal.pone.0349375
GB/T 7714
Changhwan Sung, Jungsu S Oh, Sun Young Chae, Dong Yun Lee, Minyoung Oh, Sang Ju Lee, et al. Development of AI-based dopamine transporter (DAT) image generation technique using early phase [18F]-FP-CIT PET imaging.[J]. PloS one, 2026 doi:10.1371/journal.pone.0349375.
在 PubMed增强版 阅读全文
翻译全文 · AI 文献问答 · PDF 原文下载 · 引用导出