Department of Clinical Physiology and Nuclear Medicine, Rigshospitalet, University of Copenhagen, Denmark.
Danish Dementia Research Centre, Rigshospitalet, University of Copenhagen, Denmark.
Neuroimage. 2022 Oct 1;259:119412. doi: 10.1016/j.neuroimage.2022.119412. Epub 2022 Jun 24.
Positron Emission Tomography (PET) can support a diagnosis of neurodegenerative disorder by identifying disease-specific pathologies. Our aim was to investigate the feasibility of using activity reduction in clinical [F]FE-PE2I and [C]PiB PET/CT scans, simulating low injected activity or scanning time reduction, in combination with AI-assisted denoising.
A total of 162 patients with clinically uncertain Alzheimer's disease underwent amyloid [C]PiB PET/CT and 509 patients referred for clinically uncertain Parkinson's disease underwent dopamine transporter (DAT) [F]FE-PE2I PET/CT. Simulated low-activity data were obtained by random sampling of 5% of the events from the list-mode file and a 5% time window extraction in the middle of the scan. A three-dimensional convolutional neural network (CNN) was trained to denoise the resulting PET images for each disease cohort.
Noise reduction of low-activity PET images was successful for both cohorts using 5% of the original activity with improvement in visual quality and all similarity metrics with respect to the ground-truth images. Clinically relevant metrics extracted from the low-activity images deviated < 2% compared to ground-truth values, which were not significantly changed when extracting the metrics from the denoised images.
The presented models were based on the same network architecture and proved to be a robust tool for denoising brain PET images with two widely different tracer distributions (delocalized, ([C]PiB, and highly localized, [18F]FE-PE2I). This broad and robust application makes the presented network a good choice for improving the quality of brain images to the level of the standard-activity images without degrading clinical metric extraction. This will allow for reduced dose or scan time in PET/CT to be implemented clinically.
正电子发射断层扫描（PET）可以通过识别疾病特异性病理来支持神经退行性疾病的诊断。我们的目的是研究使用临床[F]FE-PE2I 和 [C]PiB PET/CT 扫描中的活性减少，模拟低注入活性或减少扫描时间，结合 AI 辅助降噪的可行性。
共有 162 名临床疑似阿尔茨海默病患者接受了淀粉样蛋白[C]PiB PET/CT 检查，509 名疑似帕金森病患者接受了多巴胺转运体（DAT）[F]FE-PE2I PET/CT 检查。模拟低活性数据是通过从列表模式文件中随机抽取 5%的事件和在扫描中间提取 5%的时间窗口获得的。为每个疾病队列训练了一个三维卷积神经网络（CNN）来对所得 PET 图像进行降噪。
对于两个队列，使用原始活动的 5%进行低活性 PET 图像的降噪都取得了成功，改善了视觉质量，并且与真实图像的所有相似性指标都有所提高。从低活性图像中提取的临床相关指标与真实值相差<2%，并且当从降噪图像中提取指标时，这些指标没有明显变化。
所提出的模型基于相同的网络架构，被证明是一种用于对具有两种广泛不同示踪剂分布（非局部化，[C]PiB 和高度局部化，[18F]FE-PE2I）的脑 PET 图像进行降噪的强大工具。这种广泛而强大的应用使得所提出的网络成为一种很好的选择，可以将脑图像的质量提高到标准活性图像的水平，而不会降低临床指标的提取。这将允许在 PET/CT 中减少剂量或扫描时间，以便在临床上实施。
