Purpose This study aims to develop and validate a dual-time-window (DTW) Patlak plot method that eliminates the need for invasive blood sampling and reduces scan duration. We seek to improve the accuracy of the net influx constant (<InlineEquation ID="IEq1"> <EquationSource Format="TEX">\(K_i\)</EquationSource> </InlineEquation>) estimation, addressing the inaccuracies inherent in traditional DTW and single-time-window methods, which often introduce bias and hinder comparability across different cohorts. Method We developed an unsupervised, multi-branch neural network (NN) to assist in estimating missing data intervals within the DTW protocol, thereby facilitating accurate Patlak analysis. The model fits the mapping from time to the time-activity curve (TAC), generating multiple pseudo input functions (IFs). A correlation coefficient is then computed between each pseudo IF and the voxel-level measured data, extracting statistical information guided by the kinetic process. These correlation scores were used to construct a weighted statistic, serving as the final IF (NNIF). Our approach was validated using both simulation and clinical data, including <InlineEquation ID="IEq2"> <EquationSource Format="TEX">\(^{18}\rm{F}\)</EquationSource> </InlineEquation>-FDG PET scans from 67 lung cancer subjects. Additionally, we compared the performance of our method with other simplified quantification techniques to demonstrate its efficacy in achieving high-quality parametric imaging and reliable quantitative analysis within abbreviated scanning protocols. Result Our proposed method achieved high accuracy in the estimation of IF, with a maximum mean absolute deviation (MAD) of 0.04 in a real patient study. The regressed <InlineEquation ID="IEq3"> <EquationSource Format="TEX">\(K_i\)</EquationSource> </InlineEquation> derived from different DTW scan protocols exhibited good consistency. In simulation studies , the best relative absolute error (RAE) was 0.0302. In real patient study, the optimal average peak signal-to-noise ratio (PSNR) of parametric imaging reached 97.40 dB, while the best average R-squared (<InlineEquation ID="IEq4"> <EquationSource Format="TEX">\(R^{2}\)</EquationSource> </InlineEquation>) in ROI-based quantitative analysis reached 0.991. Conclusions We demonstrate the feasibility of using a weighted statistic, constructed from a multi-branch neural network, to accurately estimate the complete IF. This approach enables the generation of high-quality parametric images with shortened scan protocols, effectively reducing scanning time while ensuring accurate Patlak analysis.

Neural network-aided unsupervised input function estimation for dual-time-window PET Patlak analysis

期刊论文
出版模式：

开放获取
发表日期：

2025年12月8日

查看全文

Wenrui Shao,
Yarong Zhang,
Fen Du,
Fangxiao Cheng,
Yixin Chen,
Xiangxi Meng,
Ying Liang,
Zhaoheng Xie

摘要

Purpose

This study aims to develop and validate a dual-time-window (DTW) Patlak plot method that eliminates the need for invasive blood sampling and reduces scan duration. We seek to improve the accuracy of the net influx constant ( \(K_i\) ) estimation, addressing the inaccuracies inherent in traditional DTW and single-time-window methods, which often introduce bias and hinder comparability across different cohorts.

Method

We developed an unsupervised, multi-branch neural network (NN) to assist in estimating missing data intervals within the DTW protocol, thereby facilitating accurate Patlak analysis. The model fits the mapping from time to the time-activity curve (TAC), generating multiple pseudo input functions (IFs). A correlation coefficient is then computed between each pseudo IF and the voxel-level measured data, extracting statistical information guided by the kinetic process. These correlation scores were used to construct a weighted statistic, serving as the final IF (NNIF). Our approach was validated using both simulation and clinical data, including \(^{18}\rm{F}\) -FDG PET scans from 67 lung cancer subjects. Additionally, we compared the performance of our method with other simplified quantification techniques to demonstrate its efficacy in achieving high-quality parametric imaging and reliable quantitative analysis within abbreviated scanning protocols.

Result

Our proposed method achieved high accuracy in the estimation of IF, with a maximum mean absolute deviation (MAD) of 0.04 in a real patient study. The regressed \(K_i\) derived from different DTW scan protocols exhibited good consistency. In simulation studies , the best relative absolute error (RAE) was 0.0302. In real patient study, the optimal average peak signal-to-noise ratio (PSNR) of parametric imaging reached 97.40 dB, while the best average R-squared ( \(R^{2}\) ) in ROI-based quantitative analysis reached 0.991.

Conclusions

We demonstrate the feasibility of using a weighted statistic, constructed from a multi-branch neural network, to accurately estimate the complete IF. This approach enables the generation of high-quality parametric images with shortened scan protocols, effectively reducing scanning time while ensuring accurate Patlak analysis.