自监督神经网络用于动态[18F]FDG全身PET的Patlak参数成像
研究提出自监督神经网络算法SN-Patlak,无需60分钟全动态PET训练即可从缩短的动态[18F]FDG全身PET生成Ki参数图。仅用注射后50–60分钟的10分钟动态扫描生成的Ki图与标准Patlak法40分钟(20–60分钟)生成的Ki图相当,NMSE=0.15±0.03,Pearson r=0.93±0.01。
要点
- SN-Patlak将Patlak图拟合误差作为神经网络损失函数,无需全动态PET训练。
- 10分钟(50–60分钟)动态全身PET生成的Ki图与标准Patlak 40分钟法相当。
- SN-Patlak生成的Ki图对动态PET扫描时长具有稳健性。
核心结论
- SN-Patlak参数成像算法对10分钟动态[18F]FDG全身PET的定量稳健且可靠。
研究设计与样本
- 提出自监督神经网络算法SN-Patlak,将神经网络架构与Patlak方法深度融合,以Patlak图拟合误差作为损失函数。
- 因缩短动态PET无法获取标准Patlak所需的0–60分钟血时间活度曲线,采用基于人群的「归一化时间」(积分与瞬时血浓度之比)用于t*至60分钟的Patlak线性拟合,并将修正的Patlak方程纳入神经网络。
- 通过最小化输入层(实测组织-血浓度比)与输出层(预测组织-血浓度比)之间的差异生成Ki图。
- 评估t*(注射后20至50分钟)对SN-Patlak与标准Patlak生成的Ki图的影响,指标为归一化均方误差(NMSE)和Pearson相关系数(Pearson r)。
主要发现
- SN-Patlak生成的Ki图对动态PET扫描时长具有稳健性。
- 仅用10分钟(注射后50–60分钟)动态[18F]FDG全身PET扫描,SN-Patlak生成的Ki图与标准Patlak法40分钟(注射后20–60分钟)生成的Ki图相当,NMSE=0.15±0.03,Pearson r=0.93±0.01。
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: The objective of this study is to generate reliable Ki parametric images from a shortened [18F]FDG total-body PET for clinical applications using a self-supervised neural network algorithm. METHODS: We proposed a self-supervised neural network algorithm with Patlak graphical analysis (SN-Patlak) to generate Ki images from shortened dynamic [18F]FDG PET without 60-min full-dynamic PET-based training. The algorithm deeply integrates neural network architecture with a Patlak method, employing the fitting error of the Patlak plot as the neural network's loss function. As the 0-60 min blood time activity curve (TAC) required by the standard Patlak plot is unobtainable from shortened dynamic PET scans, a population-based "normalized time" (integral-to-instantaneous blood concentration ratio) was used for the linear fitting of Patlak plot of t* to 60 min, and the modified Patlak plot equation was then incorporated into the neural network. Ki images were generated by minimizing the difference between the input layer (measured tissue-to-blood concentration ratios) and the output layer (predicted tissue-to-blood concentration ratios). The effects of t* (20 to 50 min post injection) on the Ki images generated from the SN-Patlak and standard Patlak was evaluated using the normalized mean square error (NMSE), and Pearson's correlation coefficient (Pearson's r). RESULTS: The Ki images generated by the SN-Patlak are robust to the dynamic PET scan duration, and the Ki images generated by the SN-Patlak from just a 10-minute (50-60 min post-injection) dynamic [18F]FDG total-body PET scan are comparable to those generated by the standard Patlak method from 40-min (20-60 min post injection) with NMSE = 0.15 ± 0.03 and Pearson's r = 0.93 ± 0.01. CONCLUSIONS: The SN-Patlak parametric imaging algorithm is robust and reliable for quantification of 10-min dynamic [18F]FDG total-body PET.
引用
- Gu W, Zhu Z, Liu Z, et al. Self-supervised neural network for Patlak-based parametric imaging in dynamic [18F]FDG total-body PET. Eur J Nucl Med Mol Imaging. 2024. PMID: 39621094. doi:10.1007/s00259-024-07008-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。