当前位置: X-MOL 学术Eur. J. Nucl. Med. Mol. Imaging › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Self-supervised neural network for Patlak-based parametric imaging in dynamic [18F]FDG total-body PET
European Journal of Nuclear Medicine and Molecular Imaging ( IF 8.6 ) Pub Date : 2024-12-02 , DOI: 10.1007/s00259-024-07008-x
Wenjian Gu, Zhanshi Zhu, Ze Liu, Yihan Wang, Yanxiao Li, Tianyi Xu, Weiping Liu, Gongning Luo, Kuanquan Wang, Yun Zhou

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.



中文翻译:


用于动态 [18F]FDG 全身 PET 中基于 Patlak 的参数成像的自监督神经网络


 目的


本研究的目的是使用自监督神经网络算法从缩短的 [18F]FDG 全身 PET 中生成可靠的 K 参数图像,用于临床应用。

 方法


我们提出了一种带有 Patlak 图形分析 (SN-Patlak) 的自我监督神经网络算法,无需 60 分钟的全动态基于 PET 的训练,即可从缩短的动态 [18F]FDG PET 生成 K 图像。该算法将神经网络架构与 Patlak 方法深度集成,采用 Patlak 图的拟合误差作为神经网络的损失函数。由于标准 Patlak 图要求的 0-60 分钟血液时间活动曲线 (TAC) 无法从缩短的动态 PET 扫描中获得,因此使用基于群体的“归一化时间”(积分与瞬时血药浓度比)将 t* 线性拟合到 60 分钟的 Patlak 图,然后将修改后的 Patlak 图方程合并到神经网络中。通过最小化输入层(测得的组织与血液浓度比)和输出层(预测的组织与血液浓度比)之间的差异来生成 K 图像。使用归一化均方误差 (NMSE) 和 Pearson 相关系数 (Pearson's r) 评估 t* (注射后 20 至 50 分钟)对 SN-Patlak 和标准 Patlak 生成的 K 图像的影响。

 结果


SN-Patlak 生成的 K 图像对动态 PET 扫描持续时间具有鲁棒性,SN-Patlak 仅从注射后 10 分钟(注射后 50-60 分钟)动态 [18F]FDG 全身 PET 扫描生成的 K 图像与标准 Patlak 方法在注射后 40 分钟(注射后 20-60 分钟)生成的 K 图像相当,NMSE = 0.15 ± 0.03 和 Pearson 的 r = 0.93 ± 0.01。

 结论


SN-Patlak 参数成像算法对于定量 10 分钟动态 [18F]FDG 全身 PET 是稳健可靠的。

更新日期:2024-12-02
down
wechat
bug