Kawauchi Keisuke, Saito Mui, Nishigami Kentaro, Katoh Chietsugu
Graduate School of Biomedical Science and Engineering, Hokkaido University.
Faculty of Health Sciences, Graduate School of Hokkaido University, Sapporo, Japan.
Nucl Med Commun. 2023 Nov 1;44(11):1029-1037. doi: 10.1097/MNM.0000000000001752. Epub 2023 Aug 30.
Quantitative images of metabolic activity can be derived through dynamic PET. However, the conventional approach necessitates invasive blood sampling to acquire the input function, thus limiting its noninvasive nature. The aim of this study was to devise a system based on convolutional neural network (CNN) capable of estimating the time-radioactivity curve of arterial plasma and accurately quantify the cerebral metabolic rate of glucose (CMRGlc) directly from PET data, thereby eliminating the requirement for invasive sampling.
This retrospective investigation analyzed 29 patients with neurological disorders who underwent comprehensive whole-body 18 F-FDG-PET/CT examinations. Each patient received an intravenous infusion of 185 MBq of 18 F-FDG, followed by dynamic PET data acquisition and arterial blood sampling. A CNN architecture was developed to accurately estimate the time-radioactivity curve of arterial plasma.
The CNN estimated the time-radioactivity curve using the leave-one-out technique. In all cases, there was at least one frame with a prediction error within 10% in at least one frame. Furthermore, the correlation coefficient between CMRGlc obtained from the sampled blood and CNN yielded a highly significant value of 0.99.
The time-radioactivity curve of arterial plasma and CMRGlc was determined from 18 F-FDG dynamic brain PET data using a CNN. The utilization of CNN has facilitated noninvasive measurements of input functions from dynamic PET data. This method can be applied to various forms of quantitative analysis of dynamic medical image data.
代谢活性的定量图像可通过动态正电子发射断层扫描（PET）获得。然而，传统方法需要进行有创的血液采样来获取输入函数，从而限制了其无创性。本研究的目的是设计一种基于卷积神经网络（CNN）的系统，该系统能够估计动脉血浆的时间-放射性曲线，并直接从PET数据中准确量化脑葡萄糖代谢率（CMRGlc），从而消除对有创采样的需求。
这项回顾性研究分析了29例患有神经系统疾病并接受全面全身18F-FDG-PET/CT检查的患者。每位患者静脉注射185MBq的18F-FDG，随后进行动态PET数据采集和动脉血采样。开发了一种CNN架构以准确估计动脉血浆的时间-放射性曲线。
CNN使用留一法估计时间-放射性曲线。在所有情况下，至少有一帧在至少一帧内预测误差在10%以内。此外，从采样血液获得的CMRGlc与CNN之间的相关系数产生了0.99的高度显著值。
使用CNN从18F-FDG动态脑PET数据中确定动脉血浆的时间-放射性曲线和CMRGlc。CNN的使用有助于从动态PET数据中无创测量输入函数。该方法可应用于动态医学图像数据的各种形式的定量分析。
